QuickBooks Online vs Mercury Books

Agent access

1. ai-native userPoint an agent at llms.txt or agent-oriented docs

   weight 2 · round to QuickBooks Online
   QuickBooks Online~partialprobed4/10

   llms.txt explicitly returns 404 (no dedicated agent-readable docs file), and no OpenAPI spec was found at standard locations either. However, Intuit does document an official MCP server for QuickBooks Online (developer.intuit.com/.../mcp and a GitHub repo with 145 tools/29 entities), which constitutes agent-oriented documentation an AI agent could be pointed at instead of llms.txt. Missing for 10: an actual llms.txt or equivalent single agent-readable manifest, and independent confirmation the MCP docs page is comprehensive/discoverable rather than a niche developer page.

   • [probe] “PROBE llms.txt: HTTP 404 at https://developer.intuit.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developer.intuit.com/openapi.json, https://developer.intuit.com/swagger.json, https://develo…”
   • [probe] “official MCP server documented at https://developer.intuit.com/app/developer/qbo/docs/develop/mcp”
   • [github] “145 Total Tools - Complete coverage of QuickBooks Online API”
   • [github] “It includes full CRUD operations for 29 entity types and 11 financial reports, giving you comprehensive access to QuickBooks Online function…”

   proof ↗⚑ flag

   Mercury Books!disputedcontradicted2/10

   Mercury's blog promises a future MCP layer for agents, but direct probes show no llms.txt file (404) and no discoverable OpenAPI/agent-oriented docs at any candidate path, meaning there is currently nothing an agent could be pointed at. Missing for 10: a live llms.txt or agent-readable docs file, a shipped API/MCP endpoint, any evidence of the promised MCP layer actually existing.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

2. ai-native userRun the product headlessly / in CI for automation

   weight 2 · round to QuickBooks Online
   QuickBooks Online~partialclaimed5/10

   QuickBooks Online exposes a REST API with official OAuth SDKs (Node.js, PHP) and an official MCP server with 145 tools covering CRUD across 29 entities and 11 reports, all of which can be scripted/automated without a UI — and a sandbox environment plus write-safety toggles (QUICKBOOKS_DISABLE_WRITE/UPDATE) support automated, non-interactive testing akin to CI use. However, there is no explicit documentation of a CLI, CI pipeline integration, or headless-run instructions/examples specifically for automation pipelines. Missing for 10: explicit CI/pipeline documentation or examples, a dedicated CLI for scripted automation, and independent evidence of successful headless/CI usage in practice.

   • [github] “A Node.js client for Intuit's OAuth 2.0 implementation.”
   • [github] “145 Total Tools - Complete coverage of QuickBooks Online API”
   • [github] “It includes full CRUD operations for 29 entity types and 11 financial reports, giving you comprehensive access to QuickBooks Online function…”
   • [claimed-docs] “Intuit's official OAuth client documents a first-class sandbox environment: the client is constructed with "environment: 'sandbox', // or 'p…”
   • [claimed-docs] “Intuit's official QuickBooks Online MCP server README documents the same sandbox/production environment split for agent integrations: "Sandb…”
   • [github] “restrict which tool categories are registered (default: all enabled)”
   • [claimed-docs] “PHP client for connecting to the QuickBooks Online V3 REST API.”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Mercury explicitly frames a full API and MCP layer as a future roadmap item ('Soon...'), and direct probes for API/OpenAPI/llms.txt endpoints all returned 404s, confirming no headless/CI-usable interface exists today. Command is a plain-language, in-app assistant, not a scriptable or automatable interface.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

3. ai-native userPlug MCP servers into this product so it can use their tools

   weight 3 · round drawn
   QuickBooks Online—none0/10

   The evidence describes QuickBooks Online publishing its own MCP server (allowing external AI agents to call into QuickBooks), not QuickBooks acting as an MCP client that can ingest and use external MCP servers' tools within its own AI features (e.g., Intuit Intelligence). No documentation shows a mechanism for a user to plug third-party MCP servers into QuickBooks so its AI can call their tools.

   • [github] “145 Total Tools - Complete coverage of QuickBooks Online API”
   • [github] “It includes full CRUD operations for 29 entity types and 11 financial reports, giving you comprehensive access to QuickBooks Online function…”
   • [claimed-docs] “Intuit's official QuickBooks Online MCP server README documents the same sandbox/production environment split for agent integrations: "Sandb…”
   • [claimed-docs] “Speed up business by telling Intuit Intelligence chat to create invoices, help resolve anomalies, run payroll, generate reports, estimate ta…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   The only MCP-related evidence is a forward-looking statement that an MCP layer is coming 'soon' to let external agents call Mercury Books' own actions — this describes Mercury exposing an MCP server, not the product consuming external MCP servers' tools, and it is explicitly not yet shipped (confirmed by 404 probes for API/openapi endpoints). There is no evidence users can plug third-party MCP servers into Mercury Books today.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

4. ai-native userConnect an agent via an official MCP server

   weight 3 · round to QuickBooks Online
   QuickBooks Online✓fullprobed8/10

   Intuit publishes an official MCP server (github.com/intuit/quickbooks-online-mcp-server) with 145 tools covering 29 entity types and 11 financial reports, full CRUD, sandbox/production environment switching, and write-safety toggles for scoping agent actions, and Intuit's developer docs also list the MCP server under official docs. Missing for 10: independent/community hands-on validation of the MCP server itself (only vendor/GitHub-authored evidence) and clearer production-readiness signals (e.g., versioning/maturity status).

   • [github] “145 Total Tools - Complete coverage of QuickBooks Online API”
   • [github] “It includes full CRUD operations for 29 entity types and 11 financial reports, giving you comprehensive access to QuickBooks Online function…”
   • [github] “11 Financial Reports - Balance Sheet, P&L, Cash Flow, and more”
   • [github] “29 Entity Types - Full CRUD operations (Create, Read, Update, Delete, Search)”
   • [github] “restrict which tool categories are registered (default: all enabled)”
   • [claimed-docs] “Intuit's official QuickBooks Online MCP server README documents the same sandbox/production environment split for agent integrations: "Sandb…”
   • [probe] “official MCP server documented at https://developer.intuit.com/app/developer/qbo/docs/develop/mcp”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Mercury only states that an MCP layer is coming 'soon' for AI agents, with no evidence it currently exists; probes for API/OpenAPI/llms.txt endpoints all return 404s, confirming no official MCP server is live today.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

5. ai-native userUse an official CLI

   weight 2 · round drawn
   QuickBooks Online—none0/10

   Evidence shows SDKs (Node.js OAuth client, PHP SDK) and an official MCP server for agent integration, but nothing indicates an official command-line interface (CLI) tool for QuickBooks Online. Missing for 10: any mention of a first-party CLI binary/package, CLI installation instructions, or CLI command examples.

   • [github] “A Node.js client for Intuit's OAuth 2.0 implementation.”
   • [claimed-docs] “PHP client for connecting to the QuickBooks Online V3 REST API.”
   • [github] “145 Total Tools - Complete coverage of QuickBooks Online API”

   proof ↗⚑ flag

   Mercury Books—none0/10

   No evidence of a CLI; only future-planned API/MCP layer is mentioned, and probes for llms.txt/openapi endpoints returned 404s, indicating no current programmatic or CLI tooling exists.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

6. ai-native userDrive the product through a documented public API

   weight 3 · round to QuickBooks Online
   QuickBooks Online✓fullprobed8/10

   QuickBooks Online exposes a documented public REST API with official OAuth2 SDKs (Node.js, PHP) supporting full CRUD across many entity types, plus a sandbox environment for safe integration testing, and an official MCP server with 145 tools covering 29 entities and 11 reports for agentic access. Probes show no discoverable llms.txt or OpenAPI spec at expected paths, and no independent third-party corroboration of API robustness beyond vendor docs. missing for 10: publicly discoverable OpenAPI/llms.txt spec, independent developer reviews of the API's completeness/reliability.

   • [github] “A Node.js client for Intuit's OAuth 2.0 implementation.”
   • [github] “QuickBooks Fault object parsing for detailed validation errors”
   • [github] “145 Total Tools - Complete coverage of QuickBooks Online API”
   • [github] “It includes full CRUD operations for 29 entity types and 11 financial reports, giving you comprehensive access to QuickBooks Online function…”
   • [github] “11 Financial Reports - Balance Sheet, P&L, Cash Flow, and more”
   • [github] “29 Entity Types - Full CRUD operations (Create, Read, Update, Delete, Search)”
   • [github] “restrict which tool categories are registered (default: all enabled)”
   • [claimed-docs] “OAuth 2.0 authentication flow”
   • [claimed-docs] “PHP client for connecting to the QuickBooks Online V3 REST API.”
   • [claimed-docs] “Create, Update, Read, and Delete Examples”
   • [claimed-docs] “Intuit's official OAuth client documents a first-class sandbox environment: the client is constructed with "environment: 'sandbox', // or 'p…”
   • [claimed-docs] “Intuit's official QuickBooks Online MCP server README documents the same sandbox/production environment split for agent integrations: "Sandb…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://developer.intuit.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developer.intuit.com/openapi.json, https://developer.intuit.com/swagger.json, https://develo…”
   • [probe] “official MCP server documented at https://developer.intuit.com/app/developer/qbo/docs/develop/mcp”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Mercury explicitly says a full accounting API and MCP layer are coming 'soon,' not currently available, and direct probes for llms.txt and OpenAPI docs both returned 404s, confirming no public API exists today.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

7. ai-native userIssue scoped/least-privilege API credentials for an agent

   weight 2 · round to QuickBooks Online
   QuickBooks Online~partialclaimed5/10

   Intuit's official MCP server exposes environment variables (QUICKBOOKS_DISABLE_WRITE, QUICKBOOKS_DISABLE_UPDATE) and lets you restrict which tool categories are registered, and the OAuth client supports a sandbox/production split—giving some coarse-grained, least-privilege-style control over what an agent can do. However this is app-level config rather than true per-agent scoped OAuth credentials/roles, and there's no documented fine-grained scope system (e.g., read-only vs specific entity scopes) issued per credential. Missing for 10: granular OAuth scope definitions, role-based API key issuance per agent, and independent confirmation these toggles are enforced server-side rather than just client config.

   • [claimed-docs] “Intuit's official QuickBooks Online MCP server README documents the same sandbox/production environment split for agent integrations: "Sandb…”
   • [github] “restrict which tool categories are registered (default: all enabled)”
   • [claimed-docs] “Intuit's official OAuth client documents a first-class sandbox environment: the client is constructed with "environment: 'sandbox', // or 'p…”
   • [claimed-docs] “Manage what others can see and set custom roles, workflows, and fields to find more efficiency.”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Evidence only mentions a future accounting API and MCP layer as 'soon' (not yet shipped), with no mention of API keys, OAuth scopes, or least-privilege credential issuance; probes confirm no OpenAPI/spec or docs endpoints currently exist. There is no evidence Mercury Books lets a user issue scoped credentials for an agent today.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

8. ai-native userBuild against official SDKs

   weight 2 · round to QuickBooks Online
   QuickBooks Online✓fullprobed8/10

   Intuit maintains official SDKs (oauth-jsclient for Node.js, QuickBooks-V3-PHP-SDK for PHP) with documented OAuth flows, CRUD examples, and sandbox/production environment switches for safe development, plus an official MCP server exposing 145 tools across 29 entity types and 11 financial reports with write-safety toggles — directly enabling AI-native/agentic development against QuickBooks Online. missing for 10: no discoverable OpenAPI/swagger spec or llms.txt (both probed 404), and no independent developer corroboration of SDK/MCP quality beyond first-party docs.

   • [github] “A Node.js client for Intuit's OAuth 2.0 implementation.”
   • [github] “QuickBooks Fault object parsing for detailed validation errors”
   • [claimed-docs] “OAuth 2.0 authentication flow”
   • [claimed-docs] “PHP client for connecting to the QuickBooks Online V3 REST API.”
   • [claimed-docs] “Create, Update, Read, and Delete Examples”
   • [claimed-docs] “OAuth 2.0 authentication flow - Token management and refresh”
   • [github] “145 Total Tools - Complete coverage of QuickBooks Online API”
   • [github] “It includes full CRUD operations for 29 entity types and 11 financial reports, giving you comprehensive access to QuickBooks Online function…”
   • [github] “11 Financial Reports - Balance Sheet, P&L, Cash Flow, and more”
   • [github] “29 Entity Types - Full CRUD operations (Create, Read, Update, Delete, Search)”
   • [github] “restrict which tool categories are registered (default: all enabled)”
   • [claimed-docs] “Intuit's official OAuth client documents a first-class sandbox environment: the client is constructed with "environment: 'sandbox', // or 'p…”
   • [claimed-docs] “Intuit's official QuickBooks Online MCP server README documents the same sandbox/production environment split for agent integrations: "Sandb…”
   • [probe] “official MCP server documented at https://developer.intuit.com/app/developer/qbo/docs/develop/mcp”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Mercury explicitly frames the accounting API and MCP layer as future ('Soon'), and probes confirm no live OpenAPI/llms.txt endpoints exist yet — there is no official SDK currently available to build against.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

9. ai-native userSubscribe to events via webhooks

   weight 2 · round drawn
   QuickBooks Online—none0/10

   The evidence pack contains no mention of webhooks, event subscriptions, or push notifications anywhere in QuickBooks' docs, GitHub SDKs, or MCP server materials — only OAuth clients, REST CRUD operations, and polling-style API access are documented. Webhook subscription is a plausible capability for an API-driven accounting platform, but no evidence shows QuickBooks Online supports it.

   • [github] “A Node.js client for Intuit's OAuth 2.0 implementation.”
   • [github] “145 Total Tools - Complete coverage of QuickBooks Online API”
   • [claimed-docs] “Intuit's official QuickBooks Online MCP server README documents the same sandbox/production environment split for agent integrations: "Sandb…”
   • [claimed-docs] “PHP client for connecting to the QuickBooks Online V3 REST API.”

   proof ↗⚑ flag

   Mercury Books—none0/10

   No evidence pack item mentions webhooks or event subscriptions; the only programmatic-access claim is a forward-looking 'soon' API/MCP mention, and probes confirm no public API/openapi spec exists yet. Missing for 10: any webhook documentation, event types, or subscription mechanism.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

Agentic features

1. ai-native userGet AI-generated insights and suggestions from my data inside the product

   weight 2 · round to QuickBooks Online
   QuickBooks Online✓fullclaimed8/10

   QuickBooks documents Intuit Intelligence/AI features that generate insights directly from user data: an AI chat that answers questions like "What's driving my profit?" and "How are my invoices doing this month?", instant reports on top expenses/sales trends/industry benchmarking, AI-driven anomaly resolution and tax savings estimation, and Payroll AI that spots inconsistencies proactively. These are first-party vendor claims without independent hands-on corroboration. Missing for 10: independent/community validation that these AI insights work as described, and detail on accuracy/reliability of the suggestions.

   • [claimed-docs] “Speed up business by telling Intuit Intelligence chat to create invoices, help resolve anomalies, run payroll, generate reports, estimate ta…”
   • [claimed-docs] “Ask for the reports that matter most to your business—top expenses, sales trends, industry benchmarking—and get them instantly.”
   • [claimed-docs] “Ask anything—from “What’s driving my profit?” to “How are my invoices doing this month?”—and get instant, contextual answers in clear, conci…”
   • [claimed-docs] “Your Payroll AI proactively collects time and attendance data from your employees and spots inconsistencies, allowing you to run payroll mor…”
   • [claimed-docs] “Payroll AI proactively collects time and attendance data from your employees, spots inconsistencies, and texts your admin updates—so you can…”
   • [claimed-docs] “See funding options based on your real-time financials, understand what affects your approval odds for a QuickBooks Term Loan or QuickBooks …”

   proof ↗⚑ flag

   Mercury Books✓fullclaimed7/10

   Mercury Command lets users ask natural-language questions about their financial data and get AI-grounded answers, plus AI-driven GL code suggestions and categorization, directly inside Books. missing for 10: independent/hands-on verification of insight quality, no detail on proactive suggestion generation beyond categorization/GL coding, and Mercury's own caveat that automation is not full autopilot.

   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [claimed-docs] “The banking side feeds clean data to any ledger: "Transactions on Mercury are now automatically assigned GL codes based on your categorizati…”
   • [claimed-docs] “Ask Mercury Command a question about your books, or hand off a bookkeeping task to it directly, in plain language.”
   • [claimed-docs] “Mercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can e…”

   proof ↗⚑ flag

2. ai-native userSet up automations that run autonomously in the background

   weight 2 · round to QuickBooks Online
   QuickBooks Online~partialcommunity6/10

   QuickBooks ships several rule-based automations (bank-rule categorization, automated payment reminders, automatic bank-feed import, automatic reconciliation reports) and Intuit Intelligence/Payroll AI that proactively monitor data and flag issues, plus an official MCP server exposing 145 tools across 29 entities and financial reports for agent-driven access with sandbox and write-safety toggles. However, these are mostly triggered rules or on-demand AI chat interactions rather than a documented capability for a user to configure agents that run continuously/autonomously in the background without external orchestration; the MCP server itself is a tool interface for agents built by developers, not a built-in scheduler. missing for 10: native scheduling/trigger builder for persistent background automations, evidence of fully autonomous unattended agent runs, independent corroboration of agentic automation reliability.

   • [claimed-docs] “Avoid late payments with automated payment reminders.”
   • [claimed-docs] “Connect QuickBooks to your bank, credit cards, PayPal, Square, and more1 and we’ll import your transactions for you.”
   • [claimed-docs] “When you finish reconciling accounts, QuickBooks automatically generates a reconciliation report.”
   • [community] “"For the obvious ones, I already have automatic rules build right into QuickBooks Online." - noting existing rule-based transaction categori…”
   • [claimed-docs] “Speed up business by telling Intuit Intelligence chat to create invoices, help resolve anomalies, run payroll, generate reports, estimate ta…”
   • [claimed-docs] “Your Payroll AI proactively collects time and attendance data from your employees and spots inconsistencies, allowing you to run payroll mor…”
   • [claimed-docs] “Payroll AI proactively collects time and attendance data from your employees, spots inconsistencies, and texts your admin updates—so you can…”
   • [github] “145 Total Tools - Complete coverage of QuickBooks Online API”
   • [github] “It includes full CRUD operations for 29 entity types and 11 financial reports, giving you comprehensive access to QuickBooks Online function…”
   • [claimed-docs] “Intuit's official QuickBooks Online MCP server README documents the same sandbox/production environment split for agent integrations: "Sandb…”
   • [github] “restrict which tool categories are registered (default: all enabled)”

   proof ↗⚑ flag

   Mercury Books~partialclaimed5/10

   Mercury Books documents continuous, automatic categorization/reconciliation and a Command assistant that can be handed bookkeeping tasks in plain language (bulk GL coding, categorization rules), which is real background automation. However, the vendor itself explicitly cautions that 'a connected system isn't the same as fully automated' and that it should not be treated as 'putting your books on autopilot,' and the promised MCP/agent layer for end-to-end autonomous handling is described as 'soon,' not shipped. Missing for 10: a live, user-configurable autonomous automation/agent layer (MCP) with independent confirmation it runs unattended in production.

   • [claimed-docs] “Reconciliation and categorization are automatic and continuous: "Data across banking, cards, invoicing, and more are categorized automatical…”
   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [claimed-docs] “Use Mercury Command to bulk assign GL codes, create categorization rules, and more”
   • [claimed-docs] “Mercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can e…”
   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”

   proof ↗⚑ flag

3. ai-native userDelegate tasks to a built-in AI assistant inside the product

   weight 3 · round drawn
   QuickBooks Online✓fullclaimed7/10

   QuickBooks has a built-in AI assistant ("Intuit Intelligence") that users can chat with to create invoices, resolve anomalies, run payroll, generate reports, and get instant contextual answers — a direct in-product delegation experience, not a separate tool. missing for 10: independent/hands-on verification of the assistant's reliability and scope beyond vendor marketing copy.

   • [claimed-docs] “Speed up business by telling Intuit Intelligence chat to create invoices, help resolve anomalies, run payroll, generate reports, estimate ta…”
   • [claimed-docs] “Ask for the reports that matter most to your business—top expenses, sales trends, industry benchmarking—and get them instantly.”
   • [claimed-docs] “Ask anything—from “What’s driving my profit?” to “How are my invoices doing this month?”—and get instant, contextual answers in clear, conci…”
   • [claimed-docs] “Your Payroll AI proactively collects time and attendance data from your employees and spots inconsistencies, allowing you to run payroll mor…”
   • [claimed-docs] “Payroll AI proactively collects time and attendance data from your employees, spots inconsistencies, and texts your admin updates—so you can…”

   proof ↗⚑ flag

   Mercury Books✓fullclaimed7/10

   Mercury Books ships a built-in AI assistant called Command that users can query in plain language and delegate bookkeeping tasks to (journal entries, chart of accounts organization, bulk categorization), described as 'AI built-in, not bolted on.' Missing for 10: independent/hands-on verification of Command's task-delegation reliability, and the vendor's own caveat that automation isn't 'autopilot' tempers full agentic delegation claims.

   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [claimed-docs] “Ask Mercury Command a question about your books, or hand off a bookkeeping task to it directly, in plain language.”
   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”
   • [claimed-docs] “Mercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can e…”

   proof ↗⚑ flag

4. ai-native userOperate the product with natural-language commands

   weight 2 · round to Mercury Books
   QuickBooks Online~partialclaimed6/10

   QuickBooks offers 'Intuit Intelligence' chat where users can issue natural-language commands to create invoices, run payroll, generate reports, and get answers to questions like 'What's driving my profit?' — this directly supports natural-language operation. However, this is a limited chat assistant layered on top of the core UI rather than full natural-language control of all product functions, and there's no independent/hands-on evidence corroborating its reliability or scope beyond vendor claims. Missing for 10: independent verification of the chat's command coverage/reliability, evidence of natural-language control beyond the listed use cases, and hands-on user reports confirming it works as described.

   • [claimed-docs] “Speed up business by telling Intuit Intelligence chat to create invoices, help resolve anomalies, run payroll, generate reports, estimate ta…”
   • [claimed-docs] “Ask for the reports that matter most to your business—top expenses, sales trends, industry benchmarking—and get them instantly.”
   • [claimed-docs] “Ask anything—from “What’s driving my profit?” to “How are my invoices doing this month?”—and get instant, contextual answers in clear, conci…”
   • [claimed-docs] “Payroll AI proactively collects time and attendance data from your employees, spots inconsistencies, and texts your admin updates—so you can…”

   proof ↗⚑ flag

   Mercury Books✓fullclaimed7/10

   Mercury Command lets users ask questions and hand off bookkeeping tasks 'in plain language,' directly matching the natural-language command story, and this is documented across multiple first-party sources describing bulk actions, categorization, and Q&A. Missing for 10: independent/hands-on verification of Command's NL capabilities and confirmation that the broader agent-facing API/MCP layer (still described as 'soon') doesn't gate deeper command coverage.

   • [claimed-docs] “Ask Mercury Command a question about your books, or hand off a bookkeeping task to it directly, in plain language.”
   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [claimed-docs] “Use Mercury Command to bulk assign GL codes, create categorization rules, and more”

   proof ↗⚑ flag

Api quality

1. ai-native userExplore an interactive API reference with runnable examples

   weight 2 · round drawn
   QuickBooks Online—none0/10

   Evidence includes only static SDK README code snippets (PHP/Node OAuth examples) and explicit probes showing the developer site lacks an interactive OpenAPI/Swagger explorer (openapi.json 404) and no llms.txt, with no mention of a live, runnable API explorer or sandbox console. missing for 10: interactive browser-based API reference, runnable request/response console, discoverable OpenAPI spec.

   • [probe] “PROBE llms.txt: HTTP 404 at https://developer.intuit.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developer.intuit.com/openapi.json, https://developer.intuit.com/swagger.json, https://develo…”
   • [claimed-docs] “Create, Update, Read, and Delete Examples”
   • [claimed-docs] “PHP client for connecting to the QuickBooks Online V3 REST API.”

   proof ↗⚑ flag

   Mercury Books—none0/10

   There is no evidence of any interactive API reference or runnable examples; the API is described only as 'soon' coming, and probes for openapi/llms.txt specs both returned 404s, indicating no public API docs exist yet.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

2. ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)

   weight 2 · round drawn
   QuickBooks Online—none0/10

   Direct probes for an OpenAPI/swagger spec on Intuit's developer domain returned 404s at all standard locations, and no other evidence shows a downloadable machine-readable API spec; the MCP server and SDKs (Node/PHP) are wrapper tools, not an OpenAPI spec itself.

   • [probe] “PROBE llms.txt: HTTP 404 at https://developer.intuit.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developer.intuit.com/openapi.json, https://developer.intuit.com/swagger.json, https://develo…”
   • [github] “A Node.js client for Intuit's OAuth 2.0 implementation.”
   • [claimed-docs] “PHP client for connecting to the QuickBooks Online V3 REST API.”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Direct probes for llms.txt and OpenAPI/Swagger spec files all return 404, and docs only mention a future accounting API/MCP layer as an upcoming feature, not something currently downloadable. No machine-readable API spec exists today.

   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”
   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”

   proof ↗⚑ flag

3. ai-native userTest against a sandbox environment without touching production data

   weight 1 · round to QuickBooks Online
   QuickBooks Online✓fullprobed8/10

   Intuit's official OAuth client and MCP server docs explicitly document a sandbox/production environment split, with sandbox using isolated company data and localhost redirect URIs, plus write-safety toggles for agent scoping. This directly supports AI-native testing against sandbox without touching production. Missing for 10: independent/hands-on confirmation of sandbox parity with production and no evidence of persistent sandbox data limitations or resets.

   • [claimed-docs] “Intuit's official OAuth client documents a first-class sandbox environment: the client is constructed with "environment: 'sandbox', // or 'p…”
   • [claimed-docs] “Intuit's official QuickBooks Online MCP server README documents the same sandbox/production environment split for agent integrations: "Sandb…”
   • [github] “restrict which tool categories are registered (default: all enabled)”
   • [probe] “official MCP server documented at https://developer.intuit.com/app/developer/qbo/docs/develop/mcp”

   proof ↗⚑ flag

   Mercury Books—none0/10

   No evidence of any sandbox, staging, or test environment for Mercury Books; the API/MCP layer is described only as forthcoming with no mention of a non-production mode, and probes for docs/OpenAPI endpoints returned 404s.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

4. ai-native userRely on versioned APIs with a documented deprecation policy

   weight 2 · round drawn
   QuickBooks Online—none0/10

   Evidence shows QuickBooks has a versioned REST API (V3 SDK, OAuth client) and even an official MCP server, but nothing in the pack documents a deprecation policy, versioning cadence, or sunset timeline for API versions; probes for openapi/llms.txt docs both 404, suggesting no discoverable machine-readable API reference either. Missing for 10: explicit deprecation policy documentation, version lifecycle/support windows, and any changelog or sunset notice practice.

   • [claimed-docs] “PHP client for connecting to the QuickBooks Online V3 REST API.”
   • [probe] “PROBE llms.txt: HTTP 404 at https://developer.intuit.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developer.intuit.com/openapi.json, https://developer.intuit.com/swagger.json, https://develo…”
   • [github] “145 Total Tools - Complete coverage of QuickBooks Online API”

   proof ↗⚑ flag

   Mercury Books—none0/10

   The API is described as forthcoming ('Soon, a full accounting API will make every core Books action available programmatically'), and direct probes for openapi/llms.txt specs return 404s, showing no versioned API or deprecation policy currently exists.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

1. ai-native userPerform bulk operations across many items at once

   weight 2 · round to Mercury Books
   QuickBooks Online—none0/10

   Evidence shows QuickBooks Online supports per-entity CRUD via API/MCP server (29 entity types, 11 reports) and vague mentions of 'syncing data in spreadsheets' for Advanced tier, but nowhere is a genuine bulk/batch operation (e.g., a batch API endpoint or agent tool for acting on many records in one call) documented. Missing for 10: explicit bulk/batch API documentation, MCP tool for multi-item operations, or hands-on evidence of processing many items in a single automated action.

   • [github] “145 Total Tools - Complete coverage of QuickBooks Online API”
   • [github] “It includes full CRUD operations for 29 entity types and 11 financial reports, giving you comprehensive access to QuickBooks Online function…”
   • [github] “29 Entity Types - Full CRUD operations (Create, Read, Update, Delete, Search)”
   • [claimed-docs] “QuickBooks Online Advanced can sync data in spreadsheets to reduce your manual work.”

   proof ↗⚑ flag

   Mercury Books~partialprobed6/10

   Mercury Command explicitly supports bulk actions like bulk GL code assignment, categorization rules, and clearing categorization backlogs in bulk, which directly addresses bulk operations for an AI-native user. However, this is limited to bookkeeping/categorization tasks rather than a general-purpose bulk API, and the promised full accounting API/MCP layer for broader programmatic bulk actions is only 'coming soon,' with probes confirming no public API/OpenAPI spec exists yet. missing for 10: a live public API or MCP layer enabling arbitrary bulk operations, independent/hands-on verification of bulk actions working at scale, and documentation of bulk operation limits or scope beyond categorization/GL codes.

   • [claimed-docs] “Use Mercury Command to bulk assign GL codes, create categorization rules, and more”
   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

2. ai-native userDefine rules that trigger actions automatically on events

   weight 3 · round drawn
   QuickBooks Online~partialcommunity5/10

   QuickBooks Online ships built-in 'bank rules' for automatic transaction categorization (confirmed independently in community discussion), plus automated payment reminders and auto-generated reconciliation reports, and docs mention custom workflows/roles as an Advanced feature — all of which are rule-based, event-triggered actions. However, these are narrow, product-specific automations (categorization, reminders, reconciliation) rather than a general-purpose, user-definable rules/triggers engine that an AI-native user could configure to fire arbitrary actions on arbitrary events; the MCP server exposes CRUD tools but no explicit rule-trigger framework. Missing for 10: a generalized event-condition-action rule builder, evidence of AI/MCP-driven custom automation creation, and independent hands-on confirmation of workflow automation beyond categorization.

   • [community] “"For the obvious ones, I already have automatic rules build right into QuickBooks Online." - noting existing rule-based transaction categori…”
   • [claimed-docs] “Avoid late payments with automated payment reminders.”
   • [claimed-docs] “When you finish reconciling accounts, QuickBooks automatically generates a reconciliation report.”
   • [claimed-docs] “Manage what others can see and set custom roles, workflows, and fields to find more efficiency.”
   • [github] “145 Total Tools - Complete coverage of QuickBooks Online API”
   • [github] “29 Entity Types - Full CRUD operations (Create, Read, Update, Delete, Search)”

   proof ↗⚑ flag

   Mercury Books~partialclaimed5/10

   Mercury Command explicitly supports creating 'categorization rules' and bulk GL code assignment, which is a form of user-defined rule-based automation triggered by transaction events, and automatic categorization/reconciliation is built-in. However, there's no evidence of a general-purpose rule/trigger-action framework beyond categorization (e.g., rules for invoicing, alerts, or other business events), and Mercury's own docs caution that automation isn't full autopilot. Missing for 10: broader event types beyond categorization, explicit rule configuration UI/API details, and independent confirmation of rule reliability.

   • [claimed-docs] “Use Mercury Command to bulk assign GL codes, create categorization rules, and more”
   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [claimed-docs] “Mercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can e…”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   QuickBooks Online—none0/10

   The evidence pack details QuickBooks' MCP server (145 tools, CRUD across 29 entities, sandbox/production split, write-safety toggles) but nowhere describes a mechanism for scheduling recurring jobs or workflows via API/MCP—no cron-like triggers, recurring-transaction API, or workflow scheduler for AI agents is documented. Mentions of 'automated payment reminders' or automatic bank imports are built-in consumer features, not an AI-native scheduling/automation primitive exposed to agents.

   • [github] “145 Total Tools - Complete coverage of QuickBooks Online API”
   • [github] “It includes full CRUD operations for 29 entity types and 11 financial reports, giving you comprehensive access to QuickBooks Online function…”
   • [claimed-docs] “Intuit's official QuickBooks Online MCP server README documents the same sandbox/production environment split for agent integrations: "Sandb…”
   • [claimed-docs] “Avoid late payments with automated payment reminders.”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Evidence shows automatic categorization/reconciliation and an AI assistant (Command) that can be asked to do tasks, but there is no mention of user-defined recurring/scheduled jobs or workflows; the API/MCP layer that might enable this is explicitly described as 'soon' (not yet shipped), and probes for API endpoints 404. Missing for 10: any documented scheduling/recurring-workflow feature, evidence of a live automation API or MCP layer, and independent confirmation of scheduled task execution.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

4. ai-native userVersion, review, and roll back my automations

   weight 1 · round drawn
   QuickBooks Online—none0/10

   The evidence shows QuickBooks has automation-adjacent features (rules, invoice reminders, MCP server with write toggles) and 'backup and restore to undo mistakes' at the account/data level, but there is no evidence of versioning, reviewing, or rolling back specific automations/workflows themselves — no automation history, diff view, or automation-specific rollback mechanism is documented.

   • [claimed-docs] “Grow confidently with custom access for up to 25 users, Priority Circle expert support, and backup and restore to undo mistakes instantly an…”
   • [github] “restrict which tool categories are registered (default: all enabled)”
   • [claimed-docs] “Intuit's official QuickBooks Online MCP server README documents the same sandbox/production environment split for agent integrations: "Sandb…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Evidence shows Mercury Books has automation features (Command AI assistant, categorization rules, bulk GL code assignment) but nothing about versioning automation rules, reviewing changes, or rolling back automated actions/decisions. No audit trail, undo, or history/version-control feature is mentioned anywhere in the pack.

   ⚑ flag

Ai reconciliation

1. ai-native userHave an agent reconcile a month end-to-end, matching transactions, flagging exceptions, and preparing the close for human review

   weight 3 · round drawn
   QuickBooks Online~partialclaimed5/10

   QuickBooks ships real building blocks an agent could use—bank-feed transaction matching and reconciliation reports (quickbooks-docs-6/7/8/9), an official MCP server exposing 29 entity types, 11 financial reports, and full CRUD for agent integrations (quickbooks-gh-3/4/5/6/7), plus an 'Intuit Intelligence' chat that claims to 'help resolve anomalies' (quickbooks-docs-19). However, there is no documented tool or workflow that performs the reconciliation itself autonomously, flags exceptions, and packages a close for human review as one orchestrated task; reconciliation is presented as a human-driven feature ('Reconcile bank statements in minutes') and the MCP server's docs list generic CRUD/report access rather than a reconcile-specific or exception-flagging capability. Missing for 10: an explicit agent-driven reconciliation/close workflow tool, documented exception-flagging logic, and evidence of an agent actually completing an end-to-end month-end close.

   • [claimed-docs] “Reconcile bank statements in minutes with QuickBooks.”
   • [claimed-docs] “Connect QuickBooks to your bank, credit cards, PayPal, Square, and more1 and we’ll import your transactions for you.”
   • [claimed-docs] “When you finish reconciling accounts, QuickBooks automatically generates a reconciliation report.”
   • [claimed-docs] “There are several reports – such as the The Reconciliation Discrepancy Report, the Missing Checks Report, and the Transaction Detail Report …”
   • [claimed-docs] “Speed up business by telling Intuit Intelligence chat to create invoices, help resolve anomalies, run payroll, generate reports, estimate ta…”
   • [github] “145 Total Tools - Complete coverage of QuickBooks Online API”
   • [github] “It includes full CRUD operations for 29 entity types and 11 financial reports, giving you comprehensive access to QuickBooks Online function…”
   • [github] “11 Financial Reports - Balance Sheet, P&L, Cash Flow, and more”
   • [github] “29 Entity Types - Full CRUD operations (Create, Read, Update, Delete, Search)”
   • [github] “restrict which tool categories are registered (default: all enabled)”

   proof ↗⚑ flag

   Mercury Books~partialclaimed5/10

   Mercury Books has continuous automatic reconciliation/categorization and Command can answer questions and offload bookkeeping tasks like journal entries and bulk categorization, but Mercury explicitly states automation is not 'autopilot' and requires human decision-making, and there's no evidence of an agent autonomously running a full month-end close with exception flagging and review prep end-to-end — the MCP/agent layer is only announced as 'soon'. missing for 10: evidence of an actual agent (not just Command chat) performing a full month-end close, explicit exception-flagging workflow, and a shipped MCP/API layer rather than a 'soon' roadmap item.

   • [claimed-docs] “Reconciliation and categorization are automatic and continuous: "Data across banking, cards, invoicing, and more are categorized automatical…”
   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [claimed-docs] “Mercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can e…”
   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”

   proof ↗⚑ flag

Bank feeds

1. founderConnect bank and credit-card accounts so transactions import automatically every day

   weight 3 · round drawn
   QuickBooks Online✓fullcommunity8/10

   QuickBooks docs directly state bank/credit-card/PayPal/Square connections auto-import transactions daily, plus existing rule-based categorization is corroborated by a community comment, and reconciliation reports confirm ongoing automated matching. Missing for 10: independent hands-on verification of daily-sync reliability and no direct evidence addressing sync frequency/outage issues raised in community comments about QBO reliability.

   • [claimed-docs] “Connect QuickBooks to your bank, credit cards, PayPal, Square, and more1 and we’ll import your transactions for you.”
   • [claimed-docs] “Reconcile bank statements in minutes with QuickBooks.”
   • [claimed-docs] “When you finish reconciling accounts, QuickBooks automatically generates a reconciliation report.”
   • [community] “"For the obvious ones, I already have automatic rules build right into QuickBooks Online." - noting existing rule-based transaction categori…”

   proof ↗⚑ flag

   Mercury Books✓fullclaimed8/10

   Mercury Books explicitly supports linking external bank accounts, cards, and payroll platforms with transactions pulled in automatically and reconciled/categorized continuously in real time, directly matching the founder story. Multiple first-party docs corroborate this (linking, auto-categorization, continuous reconciliation) and Mercury even publishes an honest caveat that 'connected' isn't 'fully automated,' showing transparency rather than contradiction. missing for 10: independent/hands-on verification beyond Mercury's own docs, and detail on daily import cadence/reliability guarantees.

   • [claimed-docs] “Link external bank accounts, cards, payroll platforms, and more for the complete story of your business.”
   • [claimed-docs] “Reconciliation and categorization are automatic and continuous: "Data across banking, cards, invoicing, and more are categorized automatical…”
   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”
   • [claimed-docs] “Third-party data flows in alongside Mercury's own: Books "connects to a growing set of third-party platforms, including Stripe, PayPal, and …”
   • [claimed-docs] “Mercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can e…”

   proof ↗⚑ flag

Categorization

1. founderGet automatic categorization suggestions for imported transactions that learn from my corrections

   weight 2 · round to Mercury Books
   QuickBooks Online~partialcommunity4/10

   QuickBooks docs mention auto-sorting expenses (quickbooks-docs-28) and community evidence confirms built-in automatic categorization rules (quickbooks-comm-3), but neither source explicitly describes a machine-learning mechanism that adapts based on the founder's manual corrections. Missing for 10: explicit documentation of ML-based re-categorization suggestions, first-party confirmation that the system improves from user corrections, and independent hands-on validation of this adaptive behavior.

   • [claimed-docs] “Automatically sort expenses to stay ready for tax time”
   • [community] “"For the obvious ones, I already have automatic rules build right into QuickBooks Online." - noting existing rule-based transaction categori…”

   proof ↗⚑ flag

   Mercury Books✓fullclaimed8/10

   Mercury explicitly states that transactions are 'automatically assigned GL codes based on your categorization history and AI-driven suggestions,' directly supporting the idea of categorization suggestions that improve from past corrections, and Command lets users bulk-adjust GL codes and create rules that presumably feed this history. Mercury's own blog post also candidly notes automation has limits and isn't 'autopilot,' which sets realistic expectations rather than contradicting the feature. Missing for 10: independent/hands-on verification that suggestions specifically adapt after user corrections, and a public API/schema showing the correction-learning mechanism.

   • [claimed-docs] “The banking side feeds clean data to any ledger: "Transactions on Mercury are now automatically assigned GL codes based on your categorizati…”
   • [claimed-docs] “Reconciliation and categorization are automatic and continuous: "Data across banking, cards, invoicing, and more are categorized automatical…”
   • [claimed-docs] “Use Mercury Command to bulk assign GL codes, create categorization rules, and more”
   • [claimed-docs] “Mercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can e…”

   proof ↗⚑ flag

Reconciliation

1. accountantReconcile each bank account against the ledger with matched, unmatched, and duplicate transactions surfaced for review

   weight 3 · round to QuickBooks Online
   QuickBooks Online✓fullclaimed7/10

   QuickBooks Online docs explicitly describe connecting bank/credit-card feeds, automatic transaction import and matching, a reconciliation workflow, an auto-generated reconciliation report, and discrepancy-focused reports (Reconciliation Discrepancy Report, Missing Checks Report, Transaction Detail Report) that help surface unmatched/duplicate items for review, directly matching the accountant story. Missing for 10: explicit documentation of a distinct 'duplicate transaction' flag/UI and independent hands-on verification of the reconciliation workflow's accuracy (community evidence is generic and not reconciliation-specific).

   • [claimed-docs] “Reconcile bank statements in minutes with QuickBooks.”
   • [claimed-docs] “Connect QuickBooks to your bank, credit cards, PayPal, Square, and more1 and we’ll import your transactions for you.”
   • [claimed-docs] “When you finish reconciling accounts, QuickBooks automatically generates a reconciliation report.”
   • [claimed-docs] “There are several reports – such as the The Reconciliation Discrepancy Report, the Missing Checks Report, and the Transaction Detail Report …”
   • [claimed-docs] “When customers pay through QuickBooks invoices, we’ll record and match it for you.”

   proof ↗⚑ flag

   Mercury Books~partialclaimed5/10

   Mercury Books claims accounts 'reconcile in real time' automatically with categorization pulled directly from linked banking data (mercury-books-supp-auto-rec, mercury-books-supp-launch), and Mercury's own honest-scope post acknowledges that full automation still requires human review of ambiguous decisions (mercury-books-supp-honest-scope), implying some reconciliation review workflow exists. However, none of the evidence specifically describes a UI or workflow that surfaces matched, unmatched, and duplicate transactions as distinct categories for accountant review — the emphasis is on automation eliminating manual reconciliation work entirely rather than a structured review interface. Missing for 10: explicit documentation of matched/unmatched/duplicate transaction states, a dedicated reconciliation review screen, and independent/hands-on confirmation of this workflow.

   • [claimed-docs] “Reconciliation and categorization are automatic and continuous: "Data across banking, cards, invoicing, and more are categorized automatical…”
   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”
   • [claimed-docs] “Mercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can e…”

   proof ↗⚑ flag

Bill management

1. accountantCapture vendor bills, route them for approval, and schedule payments from one workflow

   weight 2 · round to Mercury Books
   QuickBooks Online—none0/10

   The evidence pack covers invoicing, A/R, bank reconciliation, and generic 'custom roles/workflows' language, but contains no documentation of vendor bill capture, bill approval routing, or scheduled bill payments — the core AP workflow described in the story. Missing for 10: bill capture/entry feature, approval workflow for bills, scheduled/bill-pay payment functionality, any hands-on or docs evidence of an AP module.

   • [claimed-docs] “Manage what others can see and set custom roles, workflows, and fields to find more efficiency.”

   proof ↗⚑ flag

   Mercury Books~partialclaimed3/10

   Evidence only shows that 'bill pay' transactions are pulled into Mercury Books automatically alongside banking and invoicing data, implying some underlying bill-pay capability exists, but there is no description of a capture-to-approval-to-payment-scheduling workflow, approval routing, or scheduled payments within Books itself. missing for 10: vendor bill capture/OCR, approval routing rules, payment scheduling UI, evidence tying bill pay into an AP-specific workflow rather than just a transaction category.

   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”

   proof ↗⚑ flag

Payables

1. accountantSee accounts payable aging and vendor balances at any point in time

   weight 2 · round drawn
   QuickBooks Online—none0/10

   The evidence pack documents an A/R aging report and accounts-receivable tracking (quickbooks-docs-18, quickbooks-docs-37) but contains no mention of an accounts payable aging report or vendor balance reporting; the MCP server's financial reports list (Balance Sheet, P&L, Cash Flow) does not name AP aging either.

   ⚑ flag

   Mercury Books—none0/10

   Evidence confirms Mercury Books generates P&L, cash flow, and balance sheet reports and mentions 'bill pay' as a data source, but there is no mention of an accounts payable aging report or vendor-balance tracking feature anywhere in the evidence pack. missing for 10: AP aging report, vendor balance report/ledger, point-in-time vendor balance lookups.

   • [claimed-docs] “Generate P&L, cash flow, and balance sheet reports from today’s numbers, not last quarter’s.”
   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”
   • [claimed-docs] “Mercury Books is "Double-entry accounting that pulls directly from your Mercury data", generating "P&L, cash flow, and balance sheet reports…”

   proof ↗⚑ flag

Close process

1. accountantLock closed periods so prior-period numbers cannot change without an explicit reopening

   weight 2 · round drawn
   QuickBooks Online—none0/10

   No evidence pack item mentions closing periods, closing dates, or locking prior-period transactions from edits — QuickBooks Online does have a known 'closing date' feature in general knowledge, but nothing in this evidence pack documents it, so per the rules absence of evidence must be judged 'none'.

   ⚑ flag

   Mercury Books—none0/10

   No evidence in the pack mentions period locking, closing periods, or preventing edits to prior-period transactions without explicit reopening; the evidence covers categorization, reconciliation, reports, and accountant invites but not period lock controls.

   ⚑ flag

2. accountantRun a month-end close against a checklist that tracks reconciliations, accruals, and review sign-offs

   weight 3 · round drawn
   QuickBooks Online—none0/10

   Evidence shows QuickBooks Online offers bank reconciliation tools, reconciliation reports, and accountant access, but there is no evidence of a dedicated month-end close checklist that tracks reconciliations, accruals, and review sign-offs as an integrated workflow. Community evidence even notes QBO lacks feature parity with desktop, and no close-management or sign-off workflow is documented.

   • [claimed-docs] “Reconcile bank statements in minutes with QuickBooks.”
   • [claimed-docs] “When you finish reconciling accounts, QuickBooks automatically generates a reconciliation report.”
   • [claimed-docs] “There are several reports – such as the The Reconciliation Discrepancy Report, the Missing Checks Report, and the Transaction Detail Report …”
   • [claimed-docs] “Give your accountant direct access to your books so she can find the reports and information she needs when questions arise.”
   • [community] “"Quickbooks online also had some significant quirkyness... QuickBooks online is not feature complete when compared to QuickBooks desktop - h…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Evidence shows continuous automated reconciliation, accrual/cash accounting choice, and accountant collaboration via comments/tagging, but there is no mention of an actual month-end close checklist artifact, accrual entry tracking, or formal review sign-off workflow that an accountant could run through and mark complete. missing for 10: a defined close checklist feature, accrual scheduling/tracking, sign-off/approval workflow tied to close tasks.

   • [claimed-docs] “Reconciliation and categorization are automatic and continuous: "Data across banking, cards, invoicing, and more are categorized automatical…”
   • [claimed-docs] “Accountant collaboration without seat caps: "You can invite your bookkeeper or accountant directly to your Mercury account with permissions …”
   • [claimed-docs] “Mercury Books is "Double-entry accounting that pulls directly from your Mercury data", generating "P&L, cash flow, and balance sheet reports…”
   • [claimed-docs] “The banking side feeds clean data to any ledger: "Transactions on Mercury are now automatically assigned GL codes based on your categorizati…”

   proof ↗⚑ flag

Collaboration

1. founderInvite my external accountant or bookkeeper with role-scoped access to review and adjust the books

   weight 3 · round to Mercury Books
   QuickBooks Online~partialclaimed6/10

   QuickBooks explicitly markets giving accountants direct access to books and custom role-based access controls (up to 25 users on Advanced), which directly supports inviting an external accountant with scoped permissions. However, evidence lacks specifics on how granular the role-scoping is for an accountant-specific invite (e.g., accountant-only view vs. full custom roles) or independent confirmation of this workflow in practice. Missing for 10: detailed documentation of accountant-specific invite flow and role granularity, and independent/hands-on corroboration of the accountant access experience.

   • [claimed-docs] “Give your accountant direct access to your books so she can find the reports and information she needs when questions arise.”
   • [claimed-docs] “Manage what others can see and set custom roles, workflows, and fields to find more efficiency.”
   • [claimed-docs] “Grow confidently with custom access for up to 25 users, Priority Circle expert support, and backup and restore to undo mistakes instantly an…”
   • [claimed-docs] “Move your whole firm to Intuit Accountant Suite—no data migration, no switching costs, no starting over.”

   proof ↗⚑ flag

   Mercury Books✓fullclaimed8/10

   Mercury Books explicitly supports inviting bookkeepers/accountants in-product with role-tailored permissions and no seat caps, allowing them to view transactions, categorizations, and comment/tag on entries. Missing for 10: no independent/hands-on corroboration of the granularity of role-scoping (e.g., specific permission levels) and no detail on whether accountants can directly adjust vs. only comment.

   • [claimed-docs] “Invite your bookkeeper in-product, with unlimited seats at no extra cost.”
   • [claimed-docs] “Accountant collaboration without seat caps: "You can invite your bookkeeper or accountant directly to your Mercury account with permissions …”
   • [claimed-docs] “The banking side feeds clean data to any ledger: "Transactions on Mercury are now automatically assigned GL codes based on your categorizati…”

   proof ↗⚑ flag

Data access

1. developerPull the full general ledger and trial balance through a documented API in open formats

   weight 3 · round to QuickBooks Online
   QuickBooks Online~partialprobed5/10

   QuickBooks Online exposes a REST API (V3) with SDKs (PHP, Node OAuth client) and an MCP server covering 29 entity types and 11 financial reports including Balance Sheet, P&L, and Cash Flow, which implies GL/trial-balance-like data can be retrieved programmatically. However, there is no direct evidence of a documented endpoint explicitly returning a full general ledger or trial balance report, nor confirmation of open/standard export formats (e.g., CSV/JSON schema for GL); OpenAPI/llms.txt probes returned 404s, reducing discoverability of a formal spec. missing for 10: explicit trial balance/GL report endpoint documentation, confirmed open-format (CSV/JSON) export schema, publicly accessible OpenAPI spec.

   • [github] “145 Total Tools - Complete coverage of QuickBooks Online API”
   • [github] “It includes full CRUD operations for 29 entity types and 11 financial reports, giving you comprehensive access to QuickBooks Online function…”
   • [github] “11 Financial Reports - Balance Sheet, P&L, Cash Flow, and more”
   • [github] “29 Entity Types - Full CRUD operations (Create, Read, Update, Delete, Search)”
   • [claimed-docs] “PHP client for connecting to the QuickBooks Online V3 REST API.”
   • [claimed-docs] “Create, Update, Read, and Delete Examples”
   • [probe] “PROBE llms.txt: HTTP 404 at https://developer.intuit.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developer.intuit.com/openapi.json, https://developer.intuit.com/swagger.json, https://develo…”
   • [probe] “official MCP server documented at https://developer.intuit.com/app/developer/qbo/docs/develop/mcp”

   proof ↗⚑ flag

   Mercury Books—none0/10

   The evidence explicitly states a full accounting API is only planned ('Soon, a full accounting API will make every core Books action available programmatically'), and direct probes for OpenAPI/llms.txt docs returned 404s, confirming no current documented API for pulling GL/trial balance data in open formats.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

Integrations

1. founderConnect my banking, payments, and payroll systems so their activity flows into the ledger automatically

   weight 2 · round drawn
   QuickBooks Online✓fullcommunity8/10

   QuickBooks Online documents direct bank/credit card/PayPal/Square connections with automatic transaction import and matching, plus payments and payroll AI automation (time/attendance data flowing into payroll), and an 800+ app integration ecosystem including PayPal/Square/Shopify connectors. Community evidence confirms rule-based auto-categorization works in practice, corroborating the automated ledger flow. Missing for 10: independent hands-on verification of payroll-to-ledger automation specifically and no direct evidence of setup friction/reliability for these bank feeds beyond general reliability complaints unrelated to this axis.

   • [claimed-docs] “Connect QuickBooks to your bank, credit cards, PayPal, Square, and more1 and we’ll import your transactions for you.”
   • [claimed-docs] “Reconcile bank statements in minutes with QuickBooks.”
   • [claimed-docs] “When customers pay through QuickBooks invoices, we’ll record and match it for you.”
   • [claimed-docs] “Import all your PayPal transactions into QuickBooks Online”
   • [claimed-docs] “PayPal Connector by QuickBooks”
   • [claimed-docs] “Square Connector by QuickBooks”
   • [claimed-docs] “QuickBooks integrates with over 800 popular business apps.”
   • [claimed-docs] “Payroll AI proactively collects time and attendance data from your employees, spots inconsistencies, and texts your admin updates—so you can…”
   • [community] “"For the obvious ones, I already have automatic rules build right into QuickBooks Online." - noting existing rule-based transaction categori…”

   proof ↗⚑ flag

   Mercury Books✓fullclaimed8/10

   Mercury Books explicitly supports linking external bank accounts, cards, and payroll platforms, plus named integrations with Stripe, PayPal, and Gusto, with activity flowing automatically into the ledger via continuous categorization and reconciliation. Mercury itself is candid that this is a strong starting point rather than full autopilot, which tempers but doesn't contradict the core claim. Missing for 10: independent/hands-on verification of these integrations working in practice, and a public API/OpenAPI spec was found to 404, indicating limited programmatic verification.

   • [claimed-docs] “Link external bank accounts, cards, payroll platforms, and more for the complete story of your business.”
   • [claimed-docs] “Third-party data flows in alongside Mercury's own: Books "connects to a growing set of third-party platforms, including Stripe, PayPal, and …”
   • [claimed-docs] “Reconciliation and categorization are automatic and continuous: "Data across banking, cards, invoicing, and more are categorized automatical…”
   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”
   • [claimed-docs] “Mercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can e…”
   • [claimed-docs] “Customers with enriched integrations to QuickBooks and NetSuite can now attach Classes to transactions on Mercury.”

   proof ↗⚑ flag

Migration

1. founderMigrate historical books from another accounting system without losing transaction detail

   weight 1 · round drawn
   QuickBooks Online—none0/10

   No evidence describes any migration/import tooling for bringing historical transaction-level data from another accounting system into QuickBooks Online; the only migration-adjacent item (quickbooks-docs-27) refers to moving firms between Intuit's own products, not importing from competitors, and community evidence even notes QBO lacks feature parity with desktop QuickBooks. Missing for 10: any documented data-migration/import wizard, third-party system conversion tool, or evidence that transaction-level detail is preserved when switching from another platform.

   • [claimed-docs] “Move your whole firm to Intuit Accountant Suite—no data migration, no switching costs, no starting over.”
   • [community] “"Quickbooks online also had some significant quirkyness... QuickBooks online is not feature complete when compared to QuickBooks desktop - h…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   No evidence describes an import/migration tool for bringing historical transaction-level data in from QuickBooks/NetSuite or other systems; in fact Mercury explicitly frames Books as a replacement rather than an integration/sync layer for prior accounting systems, and the cited third-party integrations (Stripe, PayPal, Gusto, bank feeds) are for ongoing data flow, not one-time historical migration.

   • [claimed-docs] “Does Mercury Books replace QuickBooks? Yes. Mercury Books is a complete accounting system — not an add-on or integration layer for another p…”
   • [claimed-docs] “Mercury Books is "Double-entry accounting that pulls directly from your Mercury data", generating "P&L, cash flow, and balance sheet reports…”
   • [claimed-docs] “Third-party data flows in alongside Mercury's own: Books "connects to a growing set of third-party platforms, including Stripe, PayPal, and …”

   proof ↗⚑ flag

Invoicing

1. founderCreate and send invoices with online payment options and see when they are viewed and paid

   weight 3 · round to QuickBooks Online
   QuickBooks Online✓fullclaimed9/10

   Docs directly cover invoice creation (templates/logo), online payment button on invoices, view/paid tracking, and automated reminders — matching every element of the story. Missing for 10: independent/hands-on corroboration beyond vendor docs.

   • [claimed-docs] “Your invoices reflect your business. With our free invoice templates, add your logo and colors and create tailored professional invoices wit…”
   • [claimed-docs] “Send your invoice, know exactly when it’s viewed, and get notified when it’s paid.”
   • [claimed-docs] “Enable online payments to add a button to invoices for your customers to pay instantly online.”
   • [claimed-docs] “Avoid late payments with automated payment reminders.”
   • [claimed-docs] “Get paid 4 days faster on average when you send invoice reminders with your Payments AI.”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Evidence only mentions 'invoicing' as one of many transaction types Mercury Books pulls in automatically (alongside banking, bill pay); there is no evidence of invoice creation/sending, online payment collection, or view/paid status tracking within Mercury Books itself.

   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”
   • [claimed-docs] “Third-party data flows in alongside Mercury's own: Books "connects to a growing set of third-party platforms, including Stripe, PayPal, and …”

   proof ↗⚑ flag

2. founderSet up recurring invoices and automatic payment reminders for overdue customers

   weight 2 · round to QuickBooks Online
   QuickBooks Online~partialclaimed6/10

   Automatic payment reminders for overdue customers are well documented (statement reminders, automated payment reminders, faster payment via reminders), but the evidence pack never explicitly describes a recurring/repeating invoice setup feature. Missing for 10: explicit documentation of recurring invoice scheduling/templates, and independent confirmation that reminders/recurring invoices work reliably in practice.

   • [claimed-docs] “Avoid late payments with automated payment reminders.”
   • [claimed-docs] “In just a few clicks you can send statement reminders to customers that are late paying you.”
   • [claimed-docs] “Get paid 4 days faster on average when you send invoice reminders with your Payments AI.”
   • [claimed-docs] “QuickBooks helps you manage accounts receivable by tracking invoices, payments, and identifying your delinquent accounts.”
   • [claimed-docs] “QuickBooks makes it easy to run the A/R aging report to see which customers are late with their payments”

   proof ↗⚑ flag

   Mercury Books—none0/10

   The evidence pack mentions invoicing only as one data stream feeding into books (transactions across 'banking, invoicing, bill pay'), but there is no mention of recurring invoice scheduling or automated overdue payment reminders anywhere in the docs. This is a fair capability for a full accounting system to offer, so absence of evidence is 'none' rather than 'na'.

   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”
   • [claimed-docs] “Link external bank accounts, cards, payroll platforms, and more for the complete story of your business.”

   proof ↗⚑ flag

Receivables

1. accountantTrack accounts receivable with aging reports and per-customer balances

   weight 2 · round to QuickBooks Online
   QuickBooks Online✓fullclaimed8/10

   QuickBooks docs explicitly describe A/R aging reports ('run the A/R aging report to see which customers are late with their payments') and per-customer tracking of invoices, payments, and delinquent accounts, plus statement reminders for late-paying customers. Missing for 10: independent/hands-on corroboration of the aging report's accuracy or depth, and no sample screenshot/detail on per-customer balance breakdown beyond marketing copy.

   • [claimed-docs] “QuickBooks makes it easy to run the A/R aging report to see which customers are late with their payments”
   • [claimed-docs] “QuickBooks helps you manage accounts receivable by tracking invoices, payments, and identifying your delinquent accounts.”
   • [claimed-docs] “In just a few clicks you can send statement reminders to customers that are late paying you.”
   • [claimed-docs] “Enable online payments to add a button to invoices for your customers to pay instantly online.”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Mercury Books documents P&L, cash flow, and balance sheet reports and mentions invoicing as one of the pulled-in transaction types, but no evidence describes accounts-receivable aging reports or per-customer balance tracking specifically. missing for 10: AR aging report feature, per-customer balance view, any invoicing/AR-specific reporting documentation.

   • [claimed-docs] “Generate P&L, cash flow, and balance sheet reports from today’s numbers, not last quarter’s.”
   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”
   • [claimed-docs] “Mercury Books is "Double-entry accounting that pulls directly from your Mercury data", generating "P&L, cash flow, and balance sheet reports…”

   proof ↗⚑ flag

Ai ledger

1. ai-native userHave an agent draft and post journal entries via the API and leave them in a review queue for my accountant

   weight 3 · round to QuickBooks Online
   QuickBooks Online~partialclaimed4/10

   QuickBooks does expose journal-entry CRUD via its official API/MCP server (29 entity types with full CRUD and write-safety toggles like QUICKBOOKS_DISABLE_WRITE), so an agent could draft and post entries programmatically, and accountants can be given direct book access. However, there is no evidence of a dedicated 'review queue' or draft/pending-approval state for journal entries awaiting accountant sign-off before posting. Missing for 10: documented draft/pending status for journal entries, an approval workflow tying agent-created entries to accountant review, and any UI/API concept of a review queue.

   • [github] “It includes full CRUD operations for 29 entity types and 11 financial reports, giving you comprehensive access to QuickBooks Online function…”
   • [github] “29 Entity Types - Full CRUD operations (Create, Read, Update, Delete, Search)”
   • [claimed-docs] “Intuit's official QuickBooks Online MCP server README documents the same sandbox/production environment split for agent integrations: "Sandb…”
   • [claimed-docs] “Give your accountant direct access to your books so she can find the reports and information she needs when questions arise.”

   proof ↗⚑ flag

   Mercury Books—none0/10

   The only mention of a programmatic API and MCP layer for agents is explicitly framed as a future roadmap item ('Soon, a full accounting API... will let AI agents handle bookkeeping tasks end-to-end'), not a shipped capability, and probes confirm no live OpenAPI/MCP endpoints exist today (404s on all candidate paths). While Command can draft journal entries via chat and accountants can be invited to collaborate, there is no evidence of an API-driven posting workflow or a formal 'review queue' gating agent-drafted entries for accountant approval.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”
   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [claimed-docs] “Accountant collaboration without seat caps: "You can invite your bookkeeper or accountant directly to your Mercury account with permissions …”

   proof ↗⚑ flag

Chart of accounts

1. accountantCustomize the chart of accounts with account types, sub-accounts, and class or tag dimensions

   weight 3 · round to Mercury Books
   QuickBooks Online—none0/10

   The evidence pack contains no mention of chart of accounts, account types, sub-accounts, or class/tag tracking dimensions anywhere in the docs, GitHub, or community items. Without any documented evidence of this capability, it cannot be credited despite being a plausible axis for an accounting product.

   ⚑ flag

   Mercury Books~partialclaimed5/10

   Evidence shows GL code assignment, bulk categorization rules, and Class/tag attachment to transactions (via enriched QuickBooks/NetSuite integrations), plus Command's ability to help 'organize your chart of accounts' — indicating some COA customization exists. However there's no explicit documentation of defining account types or creating sub-accounts within the ledger structure itself. missing for 10: explicit account-type configuration, sub-account creation/hierarchy, and native (non-integration) class/tag dimension setup.

   • [claimed-docs] “Use Mercury Command to bulk assign GL codes, create categorization rules, and more”
   • [claimed-docs] “Customers with enriched integrations to QuickBooks and NetSuite can now attach Classes to transactions on Mercury.”
   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [claimed-docs] “The banking side feeds clean data to any ledger: "Transactions on Mercury are now automatically assigned GL codes based on your categorizati…”

   proof ↗⚑ flag

Journal entries

1. accountantPost manual journal entries with balanced debits, credits, and supporting memos

   weight 3 · round to Mercury Books
   QuickBooks Online—none0/10

   The evidence pack covers invoicing, reconciliation, A/R, integrations, and AI features but contains no mention of manual journal entries, debit/credit entry screens, or memo fields for adjusting entries. Since journal entries are a core, applicable ledger capability for accounting software, absence of any supporting evidence means this is 'none' rather than 'na'.

   ⚑ flag

   Mercury Books~partialclaimed5/10

   Books is confirmed as a double-entry accounting system with journal entries as a core capability ("writing journal entries" is explicitly listed as a task Command can help with), implying balanced debit/credit posting, but there's no direct documentation of a manual journal-entry UI, memo/note fields, or debit=credit validation for accountant-initiated entries — most journal entry evidence frames it as an AI-assisted/automated task rather than manual accountant entry. Missing for 10: explicit manual entry screen documentation, memo/attachment support on journal entries, and confirmation of balance validation.

   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [claimed-docs] “Mercury Books is "Double-entry accounting that pulls directly from your Mercury data", generating "P&L, cash flow, and balance sheet reports…”
   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”

   proof ↗⚑ flag

Ai audit

1. ai-native userHave an agent monitor the ledger and flag anomalies in spend or duplicate transactions before the close

   weight 3 · round to QuickBooks Online
   QuickBooks Online~partialclaimed5/10

   QuickBooks documents an 'Intuit Intelligence' chat AI that can 'help resolve anomalies' and generate reports, plus a Reconciliation Discrepancy Report for spotting book discrepancies, and ships an official MCP server exposing 145 tools/CRUD and 11 financial reports that an external agent could use to monitor the ledger. However, none of this evidence specifically describes automated, proactive flagging of spend anomalies or duplicate transactions ahead of month-end close, and there's no independent or hands-on confirmation of this working as an agentic monitoring workflow. Missing for 10: dedicated duplicate-transaction/anomaly detection feature documentation, evidence of pre-close automated alerting, and third-party validation of anomaly detection accuracy.

   • [claimed-docs] “Speed up business by telling Intuit Intelligence chat to create invoices, help resolve anomalies, run payroll, generate reports, estimate ta…”
   • [claimed-docs] “There are several reports – such as the The Reconciliation Discrepancy Report, the Missing Checks Report, and the Transaction Detail Report …”
   • [claimed-docs] “Your Payroll AI proactively collects time and attendance data from your employees and spots inconsistencies, allowing you to run payroll mor…”
   • [github] “145 Total Tools - Complete coverage of QuickBooks Online API”
   • [github] “It includes full CRUD operations for 29 entity types and 11 financial reports, giving you comprehensive access to QuickBooks Online function…”
   • [github] “11 Financial Reports - Balance Sheet, P&L, Cash Flow, and more”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Evidence shows Command can answer questions and bulk-categorize/reconcile transactions, and an MCP layer for agents is only promised as 'soon,' but nothing describes proactive anomaly detection, duplicate-transaction flagging, or pre-close audit alerts.

   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [claimed-docs] “Reconciliation and categorization are automatic and continuous: "Data across banking, cards, invoicing, and more are categorized automatical…”
   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [claimed-docs] “Mercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can e…”

   proof ↗⚑ flag

Audit trail

1. accountantSee a complete audit trail of who changed what and when across the entire ledger

   weight 3 · round drawn
   QuickBooks Online—none0/10

   The axis clearly applies to accounting software, but no evidence item mentions an audit trail, activity log, or change-history feature — closest matches (custom roles/permissions, backup & restore) address access control and data recovery, not a record of who changed what and when. Missing for 10: any documentation of an Audit Log/Audit Trail report, user-action history, or field-level change tracking across the ledger.

   ⚑ flag

   Mercury Books—none0/10

   No evidence describes an audit trail, change log, user attribution, or history of edits across the ledger; the pack focuses on automation, categorization, reporting, and accountant seat invites, none of which document who-changed-what-when tracking. This is a plausible and expected feature for a full accounting system, so absence of evidence yields 'none' rather than 'na'.

   ⚑ flag

Multi entity

1. accountantManage multiple legal entities and produce consolidated financials across them

   weight 2 · round drawn
   QuickBooks Online—none0/10

   No evidence pack item mentions multi-entity management, inter-company eliminations, or consolidated financial reporting across separate legal entities; QuickBooks Online appears architected as single-company-per-subscription (Advanced tier only mentions up to 25 users, not multi-entity consolidation). Community notes even flag missing desktop features vs QBO, reinforcing the gap. missing for 10: any mention of multi-entity/subsidiary management, consolidated reporting across companies, or inter-entity eliminations.

   • [claimed-docs] “Grow confidently with custom access for up to 25 users, Priority Circle expert support, and backup and restore to undo mistakes instantly an…”
   • [claimed-docs] “Get 13-week cash flow and P&L forecasting powered by historical data. Compare forecast vs. actual data, share inputs in real time”
   • [community] “"Quickbooks online also had some significant quirkyness... QuickBooks online is not feature complete when compared to QuickBooks desktop - h…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   No evidence anywhere in the pack mentions multiple legal entities, inter-company eliminations, or consolidated financial statements across entities; all documentation describes a single-business books setup with one set of P&L/balance sheet/cash flow reports.

   ⚑ flag

1. ai-native userDo everything through the API that I can do in the UI

   weight 2 · round to QuickBooks Online
   QuickBooks Online~partialprobed6/10

   Intuit's official API/SDKs and the official QuickBooks Online MCP server (145 tools, full CRUD for 29 entity types, 11 financial reports) show broad, deliberate API coverage of core accounting objects, and sandbox/production + write-safety toggles indicate agent-friendly design (quickbooks-gh-3, quickbooks-gh-4, quickbooks-gh-6, quickbooks-supp-mcp-sandbox). However, there's no evidence that UI-specific features like GPS mileage capture, invoice template customization, bank-feed matching UX, or the Intuit Intelligence chat assistant itself are exposed via the API, and OpenAPI/llms.txt discovery probes 404'd, suggesting incomplete self-describing API docs. Missing for 10: confirmation that non-core UI features (mileage, invoice branding, AI chat actions) are API-reachable, and a first-party OpenAPI spec or llms.txt for full discoverability.

   • [github] “145 Total Tools - Complete coverage of QuickBooks Online API”
   • [github] “It includes full CRUD operations for 29 entity types and 11 financial reports, giving you comprehensive access to QuickBooks Online function…”
   • [github] “11 Financial Reports - Balance Sheet, P&L, Cash Flow, and more”
   • [github] “29 Entity Types - Full CRUD operations (Create, Read, Update, Delete, Search)”
   • [claimed-docs] “Intuit's official QuickBooks Online MCP server README documents the same sandbox/production environment split for agent integrations: "Sandb…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://developer.intuit.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developer.intuit.com/openapi.json, https://developer.intuit.com/swagger.json, https://develo…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Mercury's own docs say a full accounting API is coming 'soon' — it does not exist yet — and probes for llms.txt/openapi specs both return 404, confirming no current API parity with the UI.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

2. ai-native userExport all of my data in open formats and leave

   weight 3 · round to QuickBooks Online
   QuickBooks Online~partialprobed3/10

   There is no documented native 'export all data' feature in open formats (like a full CSV/Excel/QBO-file export) in the evidence pack, but the presence of REST APIs, SDKs, and an official MCP server with full CRUD access to 29 entity types and 11 financial reports (quickbooks-gh-3, quickbooks-gh-4, quickbooks-gh-5) suggests a technical path for an AI-native user to programmatically pull out their data via API. Missing for 10: an explicit bulk data export tool, documented file formats (CSV/JSON/XML) for full account export, and any first-party 'migrate out' or backup-to-open-standard feature.

   • [github] “145 Total Tools - Complete coverage of QuickBooks Online API”
   • [github] “It includes full CRUD operations for 29 entity types and 11 financial reports, giving you comprehensive access to QuickBooks Online function…”
   • [github] “11 Financial Reports - Balance Sheet, P&L, Cash Flow, and more”
   • [probe] “official MCP server documented at https://developer.intuit.com/app/developer/qbo/docs/develop/mcp”

   proof ↗⚑ flag

   Mercury Books—none0/10

   No evidence pack item mentions any data export feature, open format (CSV/OFX/JSON) download, or account-closure data portability path; the only related probes (llms.txt, openapi.json) return 404s, and Mercury explicitly positions Books as a replacement system rather than an interoperable one ('not an add-on or integration layer for another platform').

   • [claimed-docs] “Does Mercury Books replace QuickBooks? Yes. Mercury Books is a complete accounting system — not an add-on or integration layer for another p…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

1. ai-native userChoose where my data is stored (region/residency)

   weight 2 · round drawn
   QuickBooks Online—none0/10

   No evidence in the pack addresses data residency, regional data storage options, or data locality controls for QuickBooks Online; the evidence covers features like invoicing, reconciliation, integrations, and MCP tooling but nothing about where customer data is physically stored or user choice over data region.

   ⚑ flag

   Mercury Books—none0/10

   No evidence anywhere in the pack discusses data residency, region selection, or storage location controls for Mercury Books; the material covers accounting features, AI assistant capabilities, and integrations only.

   ⚑ flag

2. ai-native userPrevent my data from being used to train AI models

   weight 3 · round drawn
   QuickBooks Online—none0/10

   No evidence in the pack addresses AI training data opt-out or data-usage controls for AI model training; QuickBooks docs focus on bookkeeping, invoicing, integrations, and MCP/API tooling but never mention privacy controls over AI training use of customer data.

   ⚑ flag

   Mercury Books—none0/10

   The evidence pack contains no mention of data-training opt-outs, AI model training policies, or privacy controls specific to preventing customer data from being used to train AI models; Mercury Books' AI features (Command) are described functionally but with no privacy-posture documentation on this axis. Missing for 10: any privacy policy language, opt-out mechanism, or documentation addressing whether user financial data is used to train AI models.

   ⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round drawn
   QuickBooks Online—none0/10

   Evidence shows CRUD 'Delete' operations exist for business records via API/SDK and MCP write-toggles, but nothing addresses account-level data retention policies, AI training data deletion, or privacy-oriented data lifecycle controls that an AI-native user would need to manage. No documentation on retention periods, deletion of AI-processed data, or privacy dashboard controls is present.

   • [claimed-docs] “Create, Update, Read, and Delete Examples”
   • [github] “It includes full CRUD operations for 29 entity types and 11 financial reports, giving you comprehensive access to QuickBooks Online function…”
   • [github] “29 Entity Types - Full CRUD operations (Create, Read, Update, Delete, Search)”
   • [github] “restrict which tool categories are registered (default: all enabled)”

   proof ↗⚑ flag

   Mercury Books—none0/10

   The evidence pack contains no mention of data retention policies, deletion controls, export/purge mechanisms, or any privacy-posture settings a user could control; it focuses entirely on accounting features, AI assistant capabilities, and pricing. This is a fair axis for a financial SaaS product handling sensitive business data, but no supporting evidence exists.

   ⚑ flag

4. ai-native userOpt out of telemetry and usage tracking

   weight 2 · round drawn
   QuickBooks Online—none0/10

   No evidence in the pack addresses telemetry/usage-tracking opt-out settings for AI features or otherwise; QuickBooks documentation covers accounting features, integrations, and MCP server sandboxing, but nothing about a privacy/telemetry opt-out control.

   ⚑ flag

   Mercury Books—none0/10

   No evidence anywhere in the pack mentions telemetry, usage tracking, data collection settings, or opt-out controls; the material focuses entirely on accounting features, AI assistant capabilities, and pricing. This is a fair privacy-posture question for any SaaS product, so absence of evidence yields 'none' rather than 'na'.

   ⚑ flag

Ai insights

1. ai-native userAsk an agent "can we afford X?" and get an answer grounded in live ledger data pulled through the API

   weight 3 · round to QuickBooks Online
   QuickBooks Online~partialprobed6/10

   QuickBooks has an official MCP server exposing 145 tools with full CRUD across 29 entities and 11 financial reports (Balance Sheet, P&L, Cash Flow), which could ground an agent's answer to affordability questions in live ledger data, and Intuit Intelligence chat markets natural-language Q&A like 'What's driving my profit?'. However, there's no first-party documentation showing an agent actually reasoning through a cash-flow/affordability question end-to-end, and probes show no public OpenAPI/llms.txt discoverability layer, and no independent/hands-on evidence confirms real-time accuracy of agent-grounded answers. missing for 10: a documented example of an agent answering an affordability-style question using live API data, public OpenAPI/llms.txt for easy agent discovery, and independent verification that answers are accurately grounded rather than hallucinated.

   • [github] “145 Total Tools - Complete coverage of QuickBooks Online API”
   • [github] “It includes full CRUD operations for 29 entity types and 11 financial reports, giving you comprehensive access to QuickBooks Online function…”
   • [github] “11 Financial Reports - Balance Sheet, P&L, Cash Flow, and more”
   • [github] “29 Entity Types - Full CRUD operations (Create, Read, Update, Delete, Search)”
   • [claimed-docs] “Ask anything—from “What’s driving my profit?” to “How are my invoices doing this month?”—and get instant, contextual answers in clear, conci…”
   • [claimed-docs] “Speed up business by telling Intuit Intelligence chat to create invoices, help resolve anomalies, run payroll, generate reports, estimate ta…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://developer.intuit.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developer.intuit.com/openapi.json, https://developer.intuit.com/swagger.json, https://develo…”
   • [probe] “official MCP server documented at https://developer.intuit.com/app/developer/qbo/docs/develop/mcp”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Mercury's own docs frame the accounting API and MCP layer for external agents as a future ('Soon') capability, not something shipped today, and direct probes for an OpenAPI spec or llms.txt on Mercury's docs return 404s, indicating no live API for third-party agents yet. The only grounded Q&A shown (Command) is an in-product assistant, not an externally callable API an outside agent could query.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”
   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”

   proof ↗⚑ flag

Custom reports

1. accountantBuild custom reports filtered and grouped by class, location, or tag dimensions

   weight 2 · round drawn
   QuickBooks Online—none0/10

   The evidence pack contains no mention of class, location, or tag tracking, nor of custom report building filtered/grouped by these dimensions — only generic mentions of custom roles/access, invoicing, and integrations. One community note even claims QBO lacks many reports found in desktop QuickBooks, but nothing confirms or denies this specific capability.

   • [claimed-docs] “Manage what others can see and set custom roles, workflows, and fields to find more efficiency.”
   • [community] “"Quickbooks online also had some significant quirkyness... QuickBooks online is not feature complete when compared to QuickBooks desktop - h…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Evidence shows Mercury Books generates standard P&L, cash flow, and balance sheet reports, and mentions attaching 'Classes' to transactions only for customers with enriched QuickBooks/NetSuite integrations — not a native custom report builder. No evidence of location or tag dimensions, or of building custom reports filtered/grouped by these dimensions within Books itself.

   • [claimed-docs] “Generate P&L, cash flow, and balance sheet reports from today’s numbers, not last quarter’s.”
   • [claimed-docs] “Customers with enriched integrations to QuickBooks and NetSuite can now attach Classes to transactions on Mercury.”

   proof ↗⚑ flag

Statements

1. founderGenerate an accurate P&L, balance sheet, and cash-flow statement for any period on demand

   weight 3 · round to Mercury Books
   QuickBooks Online✓fullcommunity7/10

   The official QuickBooks Online MCP server explicitly lists '11 Financial Reports - Balance Sheet, P&L, Cash Flow, and more' with full API coverage, and QBO Advanced marketing cites 13-week cash-flow/P&L forecasting and instant on-demand reporting via Intuit Intelligence chat. This confirms the three core statements are generatable on demand for any period. Missing for 10: a dedicated first-party reports-center walkthrough showing period selection UI, and independent hands-on verification of statement accuracy (community feedback notes QBO is 'not feature complete' vs desktop for some reports).

   • [github] “11 Financial Reports - Balance Sheet, P&L, Cash Flow, and more”
   • [claimed-docs] “Get 13-week cash flow and P&L forecasting powered by historical data. Compare forecast vs. actual data, share inputs in real time”
   • [claimed-docs] “Ask for the reports that matter most to your business—top expenses, sales trends, industry benchmarking—and get them instantly.”
   • [claimed-docs] “I chose QuickBooks Online Advanced, because I have the real-time data at my fingertips, and I'm able to easily forecast what the next three …”
   • [community] “"Quickbooks online also had some significant quirkyness... QuickBooks online is not feature complete when compared to QuickBooks desktop - h…”

   proof ↗⚑ flag

   Mercury Books✓fullclaimed8/10

   Mercury Books explicitly generates P&L, cash-flow, and balance-sheet reports on demand from real-time reconciled data, with cash/accrual choice, positioned as a full double-entry replacement for QuickBooks. This is a core advertised feature with detailed first-party docs, though there's no independent/hands-on corroboration of report accuracy and Mercury itself cautions that automation isn't fully hands-off. Missing for 10: independent verification of statement accuracy, and confirmation that reports are audit-grade/error-free in practice.

   • [claimed-docs] “Generate P&L, cash flow, and balance sheet reports from today’s numbers, not last quarter’s.”
   • [claimed-docs] “Mercury Books is "Double-entry accounting that pulls directly from your Mercury data", generating "P&L, cash flow, and balance sheet reports…”
   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”
   • [claimed-docs] “Reconciliation and categorization are automatic and continuous: "Data across banking, cards, invoicing, and more are categorized automatical…”
   • [claimed-docs] “Mercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can e…”

   proof ↗⚑ flag