Zoho Books vs Mercury Books

Agent access

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

   weight 2 · round to Zoho Books
   Zoho Books~partialprobed5/10

   No llms.txt exists (confirmed 404) and the docs-in-markdown probe also 404s, so there's no dedicated agent-consumption doc format. However, Zoho does publish a downloadable OpenAPI spec (live-verified zip) and an explicit MCP integration page describing how to connect LLMs/agents to Zoho Books' APIs and actions, which serves a similar agent-onboarding purpose. Missing for 10: an actual llms.txt or markdown-native docs, and independent confirmation that agents can successfully parse/use the MCP or OpenAPI docs autonomously.

   • [probe] “PROBE llms.txt: HTTP 404 at https://www.zoho.com/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://www.zoho.com/books/api/v3/introduction/.md”
   • [claimed-docs] “A machine-readable spec is published from the docs: "Download Zoho Books OpenAPI Document" (books/api/v3/openapi-all.zip — a 340KB+ zip of t…”
   • [probe] “PROBE openapi (2026-09-16): the "Download Zoho Books OpenAPI Document" link documented on the API introduction page is live — HEAD https://w…”
   • [claimed-docs] “Zoho MCP covers Books: "Meet Zoho MCP (Model Context Protocol), which enables developers to instantly transform business apps into intellige…”

   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 Zoho Books
   Zoho Books~partialprobed6/10

   Zoho Books exposes a full REST API with OAuth2 tokens, documented rate limits, and a published OpenAPI spec, all of which support scripted/CI-driven automation without a UI, and MCP support adds agent-drivable actions. However, there is no evidence of a CLI, official SDK examples for CI pipelines, or headless/batch execution patterns beyond API calls, and OAuth token flow typically requires an initial interactive consent step not shown to be scriptable end-to-end. missing for 10: CLI tool, CI/headless-specific documentation or examples, fully non-interactive OAuth token provisioning, independent verification of automation in CI environments.

   • [claimed-docs] “Full API parity is the documented design goal: "The Zoho Books API allows you to perform all the operations that you do with our web client.…”
   • [claimed-docs] “A machine-readable spec is published from the docs: "Download Zoho Books OpenAPI Document" (books/api/v3/openapi-all.zip — a 340KB+ zip of t…”
   • [claimed-docs] “Authentication is OAuth 2.0 with documented steps — "Registering New Client", "Make the Authorization Request", "Generating Access and Refre…”
   • [claimed-docs] “Documented rate limits: "You can make 100 requests per minute per organization", per-plan daily call caps (the error payload for exceeding t…”
   • [probe] “PROBE openapi (2026-09-16): the "Download Zoho Books OpenAPI Document" link documented on the API introduction page is live — HEAD https://w…”
   • [claimed-docs] “Zoho MCP covers Books: "Meet Zoho MCP (Model Context Protocol), which enables developers to instantly transform business apps into intellige…”

   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
   Zoho Books—none0/10

   All MCP evidence describes Zoho positioning Books as an MCP *server* — external LLM agents (Claude, GPT) connect to Zoho's APIs and use Books' tools — the opposite direction from this story, which asks whether Zoho Books itself can act as an MCP client that plugs in and uses external MCP servers' tools. No evidence shows Books consuming outside MCP servers or its built-in Zia assistant connecting to third-party MCP tool providers.

   • [claimed-docs] “It connects LLMs like GPT or Claude to Zoho's APIs, data models, and actions, so agents gain the context, access, and control they need to t…”
   • [claimed-docs] “Zoho MCP covers Books: "Meet Zoho MCP (Model Context Protocol), which enables developers to instantly transform business apps into intellige…”
   • [claimed-docs] “Built-in AI plus agent hooks, in the vendor's own words: "Ask Zia in plain English", "Spot anomalies before they become problems", "Whether …”
   • [claimed-docs] “500+ integrations at your fingertips across Asana, Twilio, Zoho, and beyond.”

   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 Zoho Books
   Zoho Books✓fullclaimed8/10

   Zoho documents a Zoho MCP service (mcp.zoho.com) that explicitly connects LLMs like GPT/Claude to Zoho Books' APIs and actions, with customer quotes confirming real use for invoicing, bookkeeping, and reconciliation via Claude. This is an official first-party MCP server, not just client-side integration. Missing for 10: independent/hands-on verification of the MCP connection flow beyond vendor marketing quotes, and the hosted endpoint is sign-in-gated so behavior couldn't be directly probed.

   • [claimed-docs] “It connects LLMs like GPT or Claude to Zoho's APIs, data models, and actions, so agents gain the context, access, and control they need to t…”
   • [claimed-docs] “Generate invoices, track payments, log expenses, and create financial reports.”
   • [claimed-docs] “Zoho MCP covers Books: "Meet Zoho MCP (Model Context Protocol), which enables developers to instantly transform business apps into intellige…”
   • [claimed-docs] “Built-in AI plus agent hooks, in the vendor's own words: "Ask Zia in plain English", "Spot anomalies before they become problems", "Whether …”

   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
   Zoho Books—none0/10

   Evidence covers a REST API, OAuth, OpenAPI spec, and an MCP server offering, but there is no mention of an official command-line interface (CLI) tool for Zoho Books; probes for llms.txt and doc-md endpoints also failed. This is a fair axis for an API-driven SaaS product, but no CLI evidence exists.

   ⚑ 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 Zoho Books
   Zoho Books✓fullprobed9/10

   Zoho Books ships a comprehensive, well-documented public REST API with OAuth2 auth, rate limits, extensive endpoint coverage (contacts, banking, reconciliation, orgs), and a live-verified downloadable OpenAPI spec confirming machine-readability. This directly satisfies an AI-native user's need to drive the product programmatically via documented public API. Missing for 10: independent third-party developer corroboration beyond vendor docs, and the llms.txt/openapi.json well-known probes returned 404 (though the actual OpenAPI zip works).

   • [claimed-docs] “Full API parity is the documented design goal: "The Zoho Books API allows you to perform all the operations that you do with our web client.…”
   • [claimed-docs] “A machine-readable spec is published from the docs: "Download Zoho Books OpenAPI Document" (books/api/v3/openapi-all.zip — a 340KB+ zip of t…”
   • [claimed-docs] “Authentication is OAuth 2.0 with documented steps — "Registering New Client", "Make the Authorization Request", "Generating Access and Refre…”
   • [claimed-docs] “Documented rate limits: "You can make 100 requests per minute per organization", per-plan daily call caps (the error payload for exceeding t…”
   • [claimed-docs] “The banking API exposes agent-drivable reconciliation primitives: endpoints to "categorize an uncategorized transaction" (including as vendo…”
   • [probe] “PROBE openapi (2026-09-16): the "Download Zoho Books OpenAPI Document" link documented on the API introduction page is live — HEAD https://w…”
   • [claimed-docs] “Step3: Generating Access and Refresh Tokens”

   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 Zoho Books
   Zoho Books~partialclaimed5/10

   Zoho Books documents OAuth 2.0 with a scopes catalog gating access per module, which provides a mechanism for issuing credentials with limited access rather than full account access, and MCP integration references agent-driven access. However, there is no evidence of fine-grained, per-action or per-record least-privilege scoping (e.g., read-only vs. write, or resource-level restriction) beyond module-level scopes, nor documentation of agent-specific credential issuance/revocation workflows distinct from human OAuth clients. missing for 10: granular least-privilege scope examples beyond module-level, agent-specific credential lifecycle management (issuance/rotation/revocation tailored to AI agents), independent/hands-on verification that scoped tokens restrict agent actions as claimed.

   • [claimed-docs] “Authentication is OAuth 2.0 with documented steps — "Registering New Client", "Make the Authorization Request", "Generating Access and Refre…”
   • [claimed-docs] “Zoho MCP covers Books: "Meet Zoho MCP (Model Context Protocol), which enables developers to instantly transform business apps into intellige…”
   • [claimed-docs] “Step3: Generating Access and Refresh Tokens”

   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 drawn
   Zoho Books—none0/10

   The evidence pack documents a REST API, OAuth flow, rate limits, and a downloadable OpenAPI spec, but nowhere mentions official client SDKs (e.g., Python, Node, Java, PHP libraries) for Zoho Books; an OpenAPI zip is not itself an SDK. Missing for 10: any documentation of official language SDKs, package registry listings (npm/PyPI/Maven), or SDK usage guides.

   • [claimed-docs] “Full API parity is the documented design goal: "The Zoho Books API allows you to perform all the operations that you do with our web client.…”
   • [claimed-docs] “A machine-readable spec is published from the docs: "Download Zoho Books OpenAPI Document" (books/api/v3/openapi-all.zip — a 340KB+ zip of t…”
   • [claimed-docs] “Authentication is OAuth 2.0 with documented steps — "Registering New Client", "Make the Authorization Request", "Generating Access and Refre…”

   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
   Zoho Books—none0/10

   The evidence pack covers Zoho Books' REST API, OAuth, rate limits, OpenAPI spec, and MCP integration, but contains no mention of webhooks or event subscription mechanisms anywhere. Since webhook support is a plausible and common capability for an API-driven accounting platform, its complete absence from the evidence means the axis applies but is undocumented.

   ⚑ 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 drawn
   Zoho Books✓fullclaimed7/10

   Zoho Books ships built-in AI (Zia) that gives plain-English queries, anomaly detection, and auto-suggested next actions on financial data, plus MCP-based agent access letting LLMs reason over and act on Books data. Evidence is vendor-sourced with some third-party customer quotes but lacks independent hands-on verification of insight quality. Missing for 10: independent/hands-on evaluation of Zia's insight accuracy, and concrete examples of specific AI-generated suggestions beyond marketing copy.

   • [claimed-docs] “Built-in AI plus agent hooks, in the vendor's own words: "Ask Zia in plain English", "Spot anomalies before they become problems", "Whether …”
   • [claimed-docs] “Zoho MCP covers Books: "Meet Zoho MCP (Model Context Protocol), which enables developers to instantly transform business apps into intellige…”
   • [claimed-docs] “It connects LLMs like GPT or Claude to Zoho's APIs, data models, and actions, so agents gain the context, access, and control they need to t…”
   • [claimed-docs] “Generate invoices, track payments, log expenses, and create financial reports.”

   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 Zoho Books
   Zoho Books✓fullclaimed7/10

   Zoho Books documents native workflow automation (trigger workflows, bank rules, bulk categorization) and an MCP integration explicitly framed for 'fully autonomous agents [that] monitor, reason, and act without human input,' with customer quotes describing autonomous month-end closures and invoice handling via Claude/OpenClaw. This directly supports background, autonomous automation setups beyond simple manual triggers. missing for 10: independent/hands-on verification that MCP-driven agents persist and run unattended over time, and more detail on scheduling/triggers for background workflow execution beyond vendor marketing language.

   • [claimed-docs] “Zoho MCP covers Books: "Meet Zoho MCP (Model Context Protocol), which enables developers to instantly transform business apps into intellige…”
   • [claimed-docs] “Workflow automation is first-class: "Trigger workflow: Easily create and trigger unique business workflows to notify, update, or validate in…”
   • [claimed-docs] “The banking API exposes agent-drivable reconciliation primitives: endpoints to "categorize an uncategorized transaction" (including as vendo…”
   • [claimed-docs] “Built-in AI plus agent hooks, in the vendor's own words: "Ask Zia in plain English", "Spot anomalies before they become problems", "Whether …”

   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
   Zoho Books✓fullclaimed7/10

   Zoho Books documents a built-in AI assistant, Zia, that users can delegate tasks to in plain English — e.g. 'Ask Zia in plain English', sending bulk collection reminders, categorizing bank statements, and building workflow Blueprints automatically, all inside the product UI, distinct from the separate MCP-based external agent integration. This is first-party vendor documentation with concrete examples of task delegation. Missing for 10: independent or hands-on corroboration of Zia's task-delegation capability, and deeper documentation (e.g. feature list, screenshots) beyond a single marketing page's quotes.

   • [claimed-docs] “Built-in AI plus agent hooks, in the vendor's own words: "Ask Zia in plain English", "Spot anomalies before they become problems", "Whether …”

   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 Zoho Books
   Zoho Books✓fullclaimed8/10

   Zoho Books ships an official MCP server connecting LLMs like GPT/Claude to its APIs so agents can act on natural instructions, plus built-in Zia AI for 'plain English' commands, with customer testimonials describing invoice/bill/bookkeeping tasks done via simple AI-driven instructions. Missing for 10: independent (non-vendor-quoted) hands-on verification of the MCP server's reliability and breadth of natural-language command coverage beyond the cited testimonials.

   • [claimed-docs] “Zoho MCP covers Books: "Meet Zoho MCP (Model Context Protocol), which enables developers to instantly transform business apps into intellige…”
   • [claimed-docs] “Built-in AI plus agent hooks, in the vendor's own words: "Ask Zia in plain English", "Spot anomalies before they become problems", "Whether …”
   • [claimed-docs] “It connects LLMs like GPT or Claude to Zoho's APIs, data models, and actions, so agents gain the context, access, and control they need to t…”
   • [claimed-docs] “Generate invoices, track payments, log expenses, and create financial reports.”

   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
   Zoho Books—none0/10

   Evidence shows static API docs, OAuth guides, and a downloadable OpenAPI zip, but nothing indicates an interactive reference with runnable/try-it-now examples; probes for machine-readable/live docs endpoints (llms.txt, docs.md, openapi.json paths) returned 404s, and there's no mention of a sandbox or 'try it' console.

   • [claimed-docs] “A machine-readable spec is published from the docs: "Download Zoho Books OpenAPI Document" (books/api/v3/openapi-all.zip — a 340KB+ zip of t…”
   • [probe] “PROBE openapi (2026-09-16): the "Download Zoho Books OpenAPI Document" link documented on the API introduction page is live — HEAD https://w…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://www.zoho.com/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://www.zoho.com/books/api/v3/introduction/.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.zoho.com/openapi.json, https://www.zoho.com/swagger.json, https://www.zoho.com/api/opena…”

   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 to Zoho Books
   Zoho Books✓fullprobed9/10

   Zoho Books publishes a downloadable OpenAPI document, live-verified via HEAD request returning HTTP 200 with a 349KB zip of the full API corpus, directly linked from the official API docs. missing for 10: no independent third-party confirmation of spec completeness/validity beyond the vendor-hosted file check.

   • [claimed-docs] “A machine-readable spec is published from the docs: "Download Zoho Books OpenAPI Document" (books/api/v3/openapi-all.zip — a 340KB+ zip of t…”
   • [probe] “PROBE openapi (2026-09-16): the "Download Zoho Books OpenAPI Document" link documented on the API introduction page is live — HEAD https://w…”
   • [claimed-docs] “Full API parity is the documented design goal: "The Zoho Books API allows you to perform all the operations that you do with our web client.…”

   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 drawn
   Zoho Books—none0/10

   No evidence of a sandbox/test environment, demo org, or non-production API mode for AI agents to safely test against; the only isolation-like feature mentioned is a free plan with real financial thresholds, not a sandbox. There is also no mention of a 'test mode' flag or separate sandbox API endpoint distinct from the production organization_id-based API.

   ⚑ 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 to Zoho Books
   Zoho Books~partialprobed4/10

   Zoho Books documents a versioned API (v3), OAuth 2.0 auth, rate limits, and a downloadable OpenAPI spec, but there is no evidence of a documented version-deprecation policy, sunset timeline, or changelog governing how v3 will be retired or migrated. missing for 10: explicit deprecation/sunset policy, versioning changelog, migration guides between API versions, and any stated support-lifecycle commitments.

   • [claimed-docs] “Full API parity is the documented design goal: "The Zoho Books API allows you to perform all the operations that you do with our web client.…”
   • [claimed-docs] “A machine-readable spec is published from the docs: "Download Zoho Books OpenAPI Document" (books/api/v3/openapi-all.zip — a 340KB+ zip of t…”
   • [claimed-docs] “Documented rate limits: "You can make 100 requests per minute per organization", per-plan daily call caps (the error payload for exceeding t…”
   • [claimed-docs] “Authentication is OAuth 2.0 with documented steps — "Registering New Client", "Make the Authorization Request", "Generating Access and Refre…”
   • [probe] “PROBE openapi (2026-09-16): the "Download Zoho Books OpenAPI Document" link documented on the API introduction page is live — HEAD https://w…”

   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 Zoho Books
   Zoho Books✓fullclaimed8/10

   Zoho Books API documents explicit bulk endpoints (assign owner to multiple contacts, mark multiple contacts for 1099, bulk update/delete bank rules) and MCP integration lets AI agents drive these actions via natural instructions, with customer testimonials describing bulk workflows (month-end closures, bulk reminders) done via AI. Missing for 10: no independent hands-on verification of bulk operation limits/scale via MCP, and no explicit bulk invoice/expense creation endpoints documented.

   • [claimed-docs] “Assign an Owner to Multiple Contacts”
   • [claimed-docs] “Mark Multiple Contacts for 1099 Tracking”
   • [claimed-docs] “The banking API exposes agent-drivable reconciliation primitives: endpoints to "categorize an uncategorized transaction" (including as vendo…”
   • [claimed-docs] “Zoho MCP covers Books: "Meet Zoho MCP (Model Context Protocol), which enables developers to instantly transform business apps into intellige…”
   • [claimed-docs] “Built-in AI plus agent hooks, in the vendor's own words: "Ask Zia in plain English", "Spot anomalies before they become problems", "Whether …”

   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 to Zoho Books
   Zoho Books✓fullclaimed7/10

   Zoho Books documents genuine event/condition-based automation: 'Trigger workflow' rules to notify/update/validate on events, Bank Rules API for auto-categorizing transactions, and Zia AI turning data into automatic next steps (bulk reminders, categorization, Blueprints). MCP integration also lets AI agents trigger actions from natural instructions, corroborated by customer quotes. Missing for 10: independent hands-on verification of rule complexity/reliability, and detailed docs on the full workflow-rule builder (trigger types, conditions, action chaining) beyond marketing copy.

   • [claimed-docs] “Workflow automation is first-class: "Trigger workflow: Easily create and trigger unique business workflows to notify, update, or validate in…”
   • [claimed-docs] “The banking API exposes agent-drivable reconciliation primitives: endpoints to "categorize an uncategorized transaction" (including as vendo…”
   • [claimed-docs] “Built-in AI plus agent hooks, in the vendor's own words: "Ask Zia in plain English", "Spot anomalies before they become problems", "Whether …”
   • [claimed-docs] “Zoho MCP covers Books: "Meet Zoho MCP (Model Context Protocol), which enables developers to instantly transform business apps into intellige…”

   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 to Zoho Books
   Zoho Books~partialclaimed4/10

   Zoho Books documents workflow automation ('Trigger workflow', Blueprints, AI-driven bulk reminders/categorization) and MCP-based agent actions, suggesting automation depth, but no evidence explicitly describes scheduling recurring jobs, cron-like triggers, or persistent recurring workflows for AI agents. Missing for 10: explicit recurring/scheduled job API or documentation, evidence of interval-based triggers, and independent confirmation that AI agents can set up recurring automations.

   • [claimed-docs] “Workflow automation is first-class: "Trigger workflow: Easily create and trigger unique business workflows to notify, update, or validate in…”
   • [claimed-docs] “Built-in AI plus agent hooks, in the vendor's own words: "Ask Zia in plain English", "Spot anomalies before they become problems", "Whether …”
   • [claimed-docs] “Zoho MCP covers Books: "Meet Zoho MCP (Model Context Protocol), which enables developers to instantly transform business apps into intellige…”

   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
   Zoho Books—none0/10

   Evidence shows workflow automation, AI/MCP integration, and audit trail for financial records, but there is no mention of versioning, reviewing, or rolling back automations/workflow definitions themselves. Missing for 10: automation version history, diff/review UI for workflow changes, rollback mechanism for automations.

   ⚑ 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 to Zoho Books
   Zoho Books~partialclaimed7/10

   Zoho Books exposes concrete reconciliation primitives (bank transaction categorization, bank reconciliation creation/listing, bank rules with match filters) plus Zia AI anomaly detection ('Spot anomalies before they become problems') and MCP access letting LLM agents act on Books data, with a customer testimonial claiming 'Month-end closures... reduced from hours to minutes' via Claude integration. However, there is no documented end-to-end orchestrated workflow that explicitly matches transactions, compiles an exception list, and stages a close for human sign-off as a single agent-driven process. Missing for 10: a documented structured exception-flagging/close-summary output, an explicit human-review handoff step, and independent (non-vendor-testimonial) verification of full month-end automation.

   • [claimed-docs] “The banking API exposes agent-drivable reconciliation primitives: endpoints to "categorize an uncategorized transaction" (including as vendo…”
   • [claimed-docs] “"Zoho Books enhances banking efficiency by enabling your business to connect with bank and credit card accounts. Automatically import transa…”
   • [claimed-docs] “Zoho MCP covers Books: "Meet Zoho MCP (Model Context Protocol), which enables developers to instantly transform business apps into intellige…”
   • [claimed-docs] “Built-in AI plus agent hooks, in the vendor's own words: "Ask Zia in plain English", "Spot anomalies before they become problems", "Whether …”
   • [claimed-docs] “Accountant collaboration: "Invite your accountant in Zoho Books to access real-time data. From handling journal entries and base currency ad…”

   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
   Zoho Books✓fullclaimed8/10

   Zoho Books explicitly documents connecting bank/credit-card accounts with automatic daily transaction import, categorization, and reconciliation workflows, backed by a full Bank Accounts/Bank Rules API for automation. Missing for 10: independent/hands-on user corroboration of daily-import reliability and any bank-feed coverage/outage caveats.

   • [claimed-docs] “"Zoho Books enhances banking efficiency by enabling your business to connect with bank and credit card accounts. Automatically import transa…”
   • [claimed-docs] “The banking API exposes agent-drivable reconciliation primitives: endpoints to "categorize an uncategorized transaction" (including as vendo…”

   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
   Zoho Books~partialclaimed5/10

   Zoho Books documents automatic bank feed import with categorization (Zia AI "categorizing bank statements") and an API/UI for categorizing transactions plus configurable Bank Rules for matching, but there is no evidence that suggestions adapt or improve specifically from user corrections (an explicit learning/feedback loop). Missing for 10: documented ML feedback loop showing suggestions improve after corrections, independent/hands-on confirmation of this adaptive behavior.

   • [claimed-docs] “"Zoho Books enhances banking efficiency by enabling your business to connect with bank and credit card accounts. Automatically import transa…”
   • [claimed-docs] “The banking API exposes agent-drivable reconciliation primitives: endpoints to "categorize an uncategorized transaction" (including as vendo…”
   • [claimed-docs] “Built-in AI plus agent hooks, in the vendor's own words: "Ask Zia in plain English", "Spot anomalies before they become problems", "Whether …”

   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 Zoho Books
   Zoho Books~partialclaimed6/10

   Zoho Books documents bank feeds, transaction categorization, bank reconciliation creation/listing, bank statement summaries, and bank rules for matching, which together support surfacing matched/unmatched items during reconciliation; accountant collaboration is also documented. However, there is no explicit description of a duplicate-transaction detection/review UI or a dedicated reconciliation screen showing matched vs unmatched vs duplicate buckets. missing for 10: explicit documentation or hands-on evidence of duplicate-transaction flagging, a unified reconciliation review screen showing matched/unmatched/duplicate side-by-side, and independent (non-vendor) confirmation of the reconciliation workflow.

   • [claimed-docs] “The banking API exposes agent-drivable reconciliation primitives: endpoints to "categorize an uncategorized transaction" (including as vendo…”
   • [claimed-docs] “"Zoho Books enhances banking efficiency by enabling your business to connect with bank and credit card accounts. Automatically import transa…”
   • [claimed-docs] “Accountant collaboration: "Invite your accountant in Zoho Books to access real-time data. From handling journal entries and base currency ad…”

   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
   Zoho Books—none0/10

   The evidence pack shows generic Zoho Books workflow automation (trigger workflows, notifications), bank transaction categorization as 'vendor payment', and vague MCP-agent quotes about 'managing bills,' but nothing documents a specific bill-capture → approval-routing → payment-scheduling pipeline for accounts payable. Missing for 10: vendor bill entry/OCR capture docs, an approval-routing/Blueprint workflow specific to bills, and a scheduled/batch bill payment feature.

   • [claimed-docs] “Workflow automation is first-class: "Trigger workflow: Easily create and trigger unique business workflows to notify, update, or validate in…”
   • [claimed-docs] “The banking API exposes agent-drivable reconciliation primitives: endpoints to "categorize an uncategorized transaction" (including as vendo…”
   • [claimed-docs] “Zoho MCP covers Books: "Meet Zoho MCP (Model Context Protocol), which enables developers to instantly transform business apps into intellige…”

   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 to Zoho Books
   Zoho Books~partialclaimed3/10

   Evidence shows generic 'custom reports' and accountant collaboration for 'generating reports', plus vendor-related bank transaction categorization, but nothing explicitly documents an accounts-payable aging report or vendor balance report as of a specific date. Missing for 10: explicit AP aging report documentation, vendor balance report screenshots/specs, point-in-time reporting capability evidence.

   • [claimed-docs] “Accountant collaboration: "Invite your accountant in Zoho Books to access real-time data. From handling journal entries and base currency ad…”
   • [claimed-docs] “The banking API exposes agent-drivable reconciliation primitives: endpoints to "categorize an uncategorized transaction" (including as vendo…”
   • [claimed-docs] “Workflow automation is first-class: "Trigger workflow: Easily create and trigger unique business workflows to notify, update, or validate in…”

   proof ↗⚑ 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
   Zoho Books—none0/10

   No evidence of a period-locking/closing-books feature or explicit reopening workflow anywhere in the pack; mentions of month-end closing refer to reconciliation speed, not locking prior-period transactions from edits. missing for 10: documentation of a 'close books' or 'lock period' setting, permission controls around it, and an explicit reopening workflow.

   ⚑ 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 to Zoho Books
   Zoho Books~partialclaimed4/10

   Zoho Books documents strong reconciliation tooling (bank reconciliation API, auto-categorization, bank rules) and accountant collaboration access, plus a workflow-trigger engine and audit trail, and even a customer quote referencing faster 'month-end closures.' However, there is no evidence of a dedicated close checklist feature that explicitly tracks accrual entries or formal review/sign-off steps as a structured workflow. missing for 10: a named month-end close checklist UI, accrual-tracking/journal automation tied to close, and a documented sign-off/approval mechanism for reviewers.

   • [claimed-docs] “"Zoho Books enhances banking efficiency by enabling your business to connect with bank and credit card accounts. Automatically import transa…”
   • [claimed-docs] “The banking API exposes agent-drivable reconciliation primitives: endpoints to "categorize an uncategorized transaction" (including as vendo…”
   • [claimed-docs] “Accountant collaboration: "Invite your accountant in Zoho Books to access real-time data. From handling journal entries and base currency ad…”
   • [claimed-docs] “Workflow automation is first-class: "Trigger workflow: Easily create and trigger unique business workflows to notify, update, or validate in…”
   • [claimed-docs] “Zoho MCP covers Books: "Meet Zoho MCP (Model Context Protocol), which enables developers to instantly transform business apps into intellige…”

   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
   Zoho Books~partialclaimed7/10

   Zoho Books explicitly documents an accountant-invite feature: "Invite your accountant in Zoho Books to access real-time data... accountants can effortlessly manage your books from anywhere," covering journal entries, currency adjustments, reconciliation, and reports. However, the evidence does not detail granular role-scoping (custom permission levels, view-only vs edit controls) for that invited user. Missing for 10: explicit documentation of configurable role/permission scopes for accountant invites, and independent/hands-on confirmation of the invite flow in practice.

   • [claimed-docs] “Accountant collaboration: "Invite your accountant in Zoho Books to access real-time data. From handling journal entries and base currency ad…”

   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 Zoho Books
   Zoho Books~partialprobed4/10

   Zoho Books publishes a full REST API with an OpenAPI spec download and OAuth-based access, and states the API's goal is 'all the operations you do with our web client,' implying report access, but no evidence cites specific 'General Ledger' or 'Trial Balance' report endpoints or confirms these are exportable in open formats (JSON/CSV) via API. missing for 10: explicit GL/trial-balance report endpoint documentation, confirmed open-format export options, and independent verification of report API usage.

   • [claimed-docs] “Full API parity is the documented design goal: "The Zoho Books API allows you to perform all the operations that you do with our web client.…”
   • [claimed-docs] “A machine-readable spec is published from the docs: "Download Zoho Books OpenAPI Document" (books/api/v3/openapi-all.zip — a 340KB+ zip of t…”
   • [claimed-docs] “Accountant collaboration: "Invite your accountant in Zoho Books to access real-time data. From handling journal entries and base currency ad…”
   • [probe] “PROBE openapi (2026-09-16): the "Download Zoho Books OpenAPI Document" link documented on the API introduction page is live — HEAD https://w…”

   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 to Mercury Books
   Zoho Books~partialclaimed6/10

   Bank feed automation is well documented (auto-import, categorization, reconciliation APIs) and general integration breadth (500+ apps, MCP) is claimed, but there is no explicit evidence of dedicated payments-gateway or payroll-system integrations feeding the ledger. Missing for 10: explicit payroll system connectors (e.g., Zoho Payroll or Gusto), explicit payment processor integrations (Stripe/PayPal) beyond generic '500+ integrations' claim, and independent confirmation these flows work end-to-end.

   • [claimed-docs] “"Zoho Books enhances banking efficiency by enabling your business to connect with bank and credit card accounts. Automatically import transa…”
   • [claimed-docs] “The banking API exposes agent-drivable reconciliation primitives: endpoints to "categorize an uncategorized transaction" (including as vendo…”
   • [claimed-docs] “500+ integrations at your fingertips across Asana, Twilio, Zoho, and beyond.”
   • [claimed-docs] “Zoho MCP covers Books: "Meet Zoho MCP (Model Context Protocol), which enables developers to instantly transform business apps into intellige…”

   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
   Zoho Books—none0/10

   The evidence pack shows general API/contact/organization creation endpoints, OAuth, banking reconciliation, and MCP/AI agent capabilities, but nothing addresses importing historical transactions, opening balances, or bulk migration from another accounting system (e.g., QuickBooks/Xero import tools, CSV bulk import, or a dedicated migration service) while preserving transaction-level detail.

   ⚑ 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 Zoho Books
   Zoho Books~partialclaimed4/10

   Evidence confirms Zoho Books can 'generate invoices' and 'track payments' (via MCP/Zia docs), implying some invoicing and payment-tracking capability, but there is no explicit documentation of online payment gateway options embedded in invoices or of invoice 'viewed' status tracking. missing for 10: dedicated docs on online payment gateway/checkout options on invoices, evidence of 'viewed' status/read-receipt tracking, and any independent/hands-on confirmation of the payment/view workflow.

   • [claimed-docs] “Generate invoices, track payments, log expenses, and create financial reports.”
   • [claimed-docs] “Built-in AI plus agent hooks, in the vendor's own words: "Ask Zia in plain English", "Spot anomalies before they become problems", "Whether …”

   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 Zoho Books
   Zoho Books~partialclaimed5/10

   Evidence documents automated collection reminders ("sending bulk collection reminders") and workflow triggers that can notify customers, plus AI/MCP hooks for invoice tracking, but no citation explicitly describes a recurring-invoice scheduling feature. Missing for 10: explicit documentation of setting up recurring/repeating invoices, and independent/hands-on confirmation of the reminder automation working end-to-end.

   • [claimed-docs] “Built-in AI plus agent hooks, in the vendor's own words: "Ask Zia in plain English", "Spot anomalies before they become problems", "Whether …”
   • [claimed-docs] “Workflow automation is first-class: "Trigger workflow: Easily create and trigger unique business workflows to notify, update, or validate in…”
   • [claimed-docs] “Generate invoices, track payments, log expenses, and create financial reports.”

   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 Zoho Books
   Zoho Books~partialclaimed3/10

   Evidence confirms Zoho Books has contact/customer management and a customizable reporting engine ('generating reports... changing date range, adding columns, filters') that accountants can use, implying AR-related reporting capability, but no citation explicitly names an accounts-receivable aging report or per-customer balance view. missing for 10: explicit AR aging report documentation, explicit per-customer balance/statement feature, independent confirmation of these standard reports.

   • [claimed-docs] “Accountant collaboration: "Invite your accountant in Zoho Books to access real-time data. From handling journal entries and base currency ad…”
   • [claimed-docs] “Create a Contact”
   • [claimed-docs] “Workflow automation is first-class: "Trigger workflow: Easily create and trigger unique business workflows to notify, update, or validate in…”

   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 Zoho Books
   Zoho Books~partialclaimed5/10

   Zoho Books has a documented Journal Entries-capable API, OAuth-based agent access, and MCP integration for agent-driven bookkeeping actions, plus accountant collaboration features, which together make agent-drafted journal entries plausible. However, there is no evidence of a dedicated 'draft/review queue' status or approval workflow for journal entries specifically, nor confirmation that journal entries can be created in a pending/unposted state for accountant review via API. missing for 10: explicit journal entry draft/pending status API field, a documented review-queue or approval workflow feature, and a hands-on example of an agent posting a journal entry that awaits accountant sign-off.

   • [claimed-docs] “Zoho MCP covers Books: "Meet Zoho MCP (Model Context Protocol), which enables developers to instantly transform business apps into intellige…”
   • [claimed-docs] “Accountant collaboration: "Invite your accountant in Zoho Books to access real-time data. From handling journal entries and base currency ad…”
   • [claimed-docs] “Full API parity is the documented design goal: "The Zoho Books API allows you to perform all the operations that you do with our web client.…”
   • [claimed-docs] “Authentication is OAuth 2.0 with documented steps — "Registering New Client", "Make the Authorization Request", "Generating Access and Refre…”
   • [claimed-docs] “Workflow automation is first-class: "Trigger workflow: Easily create and trigger unique business workflows to notify, update, or validate in…”

   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
   Zoho Books—none0/10

   The evidence pack contains no mention of chart of accounts customization, account types, sub-accounts, or class/tag dimensions—only unrelated docs on contacts, bank reconciliation, MCP, OAuth, and pricing. This is a core accounting feature that clearly applies to a bookkeeping product like Zoho Books, but no supporting evidence is provided.

   ⚑ 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 drawn
   Zoho Books~partialclaimed5/10

   Zoho Books documents accountant access to 'journal entries and base currency adjustments' via the accountant collaboration feature, confirming journal entry posting exists as a core feature, but there is no direct evidence of the journal entry UI/API showing debit/credit balancing enforcement or memo/attachment support. Missing for 10: explicit documentation of journal entry creation flow, balance validation, memo/notes fields, and attachment support for journal entries.

   • [claimed-docs] “Accountant collaboration: "Invite your accountant in Zoho Books to access real-time data. From handling journal entries and base currency ad…”

   proof ↗⚑ 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 Zoho Books
   Zoho Books~partialclaimed6/10

   Zia AI is explicitly documented to 'Spot anomalies before they become problems' and Zoho MCP lets external agents (Claude, GPT) connect to Books data to 'monitor, reason, and act without human input,' with bank feed categorization and reconciliation APIs that an agent could use to review transactions before close. However, there is no explicit documentation of duplicate-transaction detection or a dedicated anomaly-flagging workflow across multiple entities/organizations, and evidence is vendor-marketing plus generic customer quotes rather than a demonstrated anomaly-detection feature spec. Missing for 10: explicit duplicate-transaction detection capability, documented multi-entity/cross-org anomaly rollup, and independent/hands-on verification of agent-driven anomaly flagging.

   • [claimed-docs] “Built-in AI plus agent hooks, in the vendor's own words: "Ask Zia in plain English", "Spot anomalies before they become problems", "Whether …”
   • [claimed-docs] “Zoho MCP covers Books: "Meet Zoho MCP (Model Context Protocol), which enables developers to instantly transform business apps into intellige…”
   • [claimed-docs] “The banking API exposes agent-drivable reconciliation primitives: endpoints to "categorize an uncategorized transaction" (including as vendo…”
   • [claimed-docs] “"Zoho Books enhances banking efficiency by enabling your business to connect with bank and credit card accounts. Automatically import transa…”

   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 to Zoho Books
   Zoho Books~partialclaimed3/10

   The features page briefly names an 'audit trail' as a Zoho Books capability, but the evidence pack gives no detail on what it captures (user, timestamp, field-level changes) or its coverage across the entire ledger/multi-entity setup — it's a single passing mention alongside unrelated features like custom reports. missing for 10: documentation of audit trail granularity (who/what/when), screenshots or hands-on verification, coverage confirmation across multiple organizations/entities, and independent corroboration.

   • [claimed-docs] “Accountant collaboration: "Invite your accountant in Zoho Books to access real-time data. From handling journal entries and base currency ad…”

   proof ↗⚑ 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 to Zoho Books
   Zoho Books~partialclaimed3/10

   Zoho Books supports creating multiple organizations and copying settings between them (zoho-books-docs-6, zoho-books-docs-7), which enables managing multiple legal entities separately, but there is no evidence of a consolidated financial reporting feature across organizations/entities. Missing for 10: documented consolidation/roll-up reporting across multiple organizations, inter-entity eliminations, or a unified consolidated financial statement feature.

   • [claimed-docs] “Create an organization”
   • [claimed-docs] “Copy settings to an organization”
   • [claimed-docs] “Accountant collaboration: "Invite your accountant in Zoho Books to access real-time data. From handling journal entries and base currency ad…”

   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 Zoho Books
   Zoho Books~partialprobed7/10

   Zoho explicitly states API parity as a design goal ('perform all the operations that you do with our web client'), backs it with a large, verified OpenAPI spec covering contacts, banking, reconciliation, rules, orgs, and 1099 workflows, plus documented OAuth scopes gating module access. However, there is no independent/hands-on verification confirming true 1:1 parity (e.g., UI-only settings, some organization-level admin actions), and the llms.txt/well-known OpenAPI discovery probes 404, showing openness/discoverability gaps for AI-native tooling. Missing for 10: independent confirmation of full UI-API parity with no exceptions, and standard machine-discoverable API metadata (llms.txt, well-known openapi.json) actually resolving.

   • [claimed-docs] “Full API parity is the documented design goal: "The Zoho Books API allows you to perform all the operations that you do with our web client.…”
   • [claimed-docs] “A machine-readable spec is published from the docs: "Download Zoho Books OpenAPI Document" (books/api/v3/openapi-all.zip — a 340KB+ zip of t…”
   • [claimed-docs] “The banking API exposes agent-drivable reconciliation primitives: endpoints to "categorize an uncategorized transaction" (including as vendo…”
   • [claimed-docs] “Authentication is OAuth 2.0 with documented steps — "Registering New Client", "Make the Authorization Request", "Generating Access and Refre…”
   • [probe] “PROBE openapi (2026-09-16): the "Download Zoho Books OpenAPI Document" link documented on the API introduction page is live — HEAD https://w…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://www.zoho.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.zoho.com/openapi.json, https://www.zoho.com/swagger.json, https://www.zoho.com/api/opena…”

   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 Zoho Books
   Zoho Books~partialprobed4/10

   Zoho Books never documents a dedicated 'export all data' or backup feature, but its REST API offers near-full parity with the web client ("perform all the operations that you do with our web client") plus a published OpenAPI spec, meaning a technical/AI-native user could programmatically pull out contacts, transactions, invoices, etc. in JSON via authenticated calls — a workaround path to open-format export rather than a first-class export/leave feature. Missing for 10: an explicit bulk-export or full-account-backup capability, documented standard export formats (CSV/Excel/JSON dump), and any migration/portability tooling or independent confirmation that a full data export actually works end-to-end.

   • [claimed-docs] “Full API parity is the documented design goal: "The Zoho Books API allows you to perform all the operations that you do with our web client.…”
   • [claimed-docs] “A machine-readable spec is published from the docs: "Download Zoho Books OpenAPI Document" (books/api/v3/openapi-all.zip — a 340KB+ zip of t…”
   • [probe] “PROBE openapi (2026-09-16): the "Download Zoho Books OpenAPI Document" link documented on the API introduction page is live — HEAD https://w…”
   • [claimed-docs] “Authentication is OAuth 2.0 with documented steps — "Registering New Client", "Make the Authorization Request", "Generating Access and Refre…”

   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 to Zoho Books
   Zoho Books~partialclaimed3/10

   The only relevant evidence is a brief mention that the API root documents "eight regional API domains," implying Zoho Books operates data centers in multiple regions — a proxy for data residency options — but there is no explicit documentation of a user-facing region/residency selection at signup or account level, nor any privacy-page confirmation of data locality guarantees. missing for 10: explicit account creation region-selection documentation, data residency/privacy policy statement, independent confirmation of regional data storage enforcement.

   • [claimed-docs] “Full API parity is the documented design goal: "The Zoho Books API allows you to perform all the operations that you do with our web client.…”

   proof ↗⚑ 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
   Zoho Books—none0/10

   No evidence in the pack addresses AI-training data usage policies, opt-outs, or data-privacy controls related to model training; the pack covers API docs, MCP integration, and features but nothing on training-data exclusion.

   ⚑ 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
   Zoho Books—none0/10

   The evidence pack covers API access, OAuth, MCP integration, and general accounting features, but contains no documentation of data retention policies, deletion controls, data export/purge APIs, or configurable retention periods for AI-native or any users. No mention of GDPR/CCPA deletion mechanisms, audit-trail retention settings, or account/data deletion workflows appears anywhere.

   ⚑ 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
   Zoho Books—none0/10

   No evidence in the pack addresses telemetry opt-out or usage tracking controls; the material covers API docs, OAuth, MCP integration, and accounting features but nothing about privacy settings or telemetry toggles.

   ⚑ 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 Zoho Books
   Zoho Books~partialclaimed6/10

   Zoho Books exposes live ledger data via a documented REST/OAuth API and OpenAPI spec, and Zoho MCP explicitly connects LLMs (GPT/Claude) to Books' data/actions with customer testimonials describing pulling reports and managing bookkeeping via natural-language agent instructions; Zia also markets 'pull reports just by asking'. However, there is no concrete evidence of an agent answering a specific affordability/cash-runway question grounded in live balances—no worked example, and MCP access is gated/unverified hands-on beyond vendor testimonials. Missing for 10: a demonstrated affordability-style query/answer flow, independent (non-vendor) confirmation of MCP grounding accuracy, and explicit cash-balance/afford-X reasoning support.

   • [claimed-docs] “It connects LLMs like GPT or Claude to Zoho's APIs, data models, and actions, so agents gain the context, access, and control they need to t…”
   • [claimed-docs] “Generate invoices, track payments, log expenses, and create financial reports.”
   • [claimed-docs] “Zoho MCP covers Books: "Meet Zoho MCP (Model Context Protocol), which enables developers to instantly transform business apps into intellige…”
   • [claimed-docs] “Built-in AI plus agent hooks, in the vendor's own words: "Ask Zia in plain English", "Spot anomalies before they become problems", "Whether …”
   • [claimed-docs] “Full API parity is the documented design goal: "The Zoho Books API allows you to perform all the operations that you do with our web client.…”
   • [claimed-docs] “A machine-readable spec is published from the docs: "Download Zoho Books OpenAPI Document" (books/api/v3/openapi-all.zip — a 340KB+ zip of t…”

   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 to Zoho Books
   Zoho Books~partialclaimed4/10

   Evidence confirms Zoho Books supports custom reports with filters, columns, and date ranges (zoho-books-supp-accountant), but no citation explicitly documents reporting dimensions like class, location, or tags for grouping/filtering—only generic 'custom fields' and 'custom reports' are mentioned. Missing for 10: explicit documentation of class/location/tag tracking categories and their use as report filter/group dimensions, plus any hands-on or independent confirmation of this specific capability.

   • [claimed-docs] “Accountant collaboration: "Invite your accountant in Zoho Books to access real-time data. From handling journal entries and base currency ad…”
   • [claimed-docs] “Workflow automation is first-class: "Trigger workflow: Easily create and trigger unique business workflows to notify, update, or validate in…”

   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
   Zoho Books~partialclaimed5/10

   Evidence confirms Zoho Books supports generating financial reports generally (custom reports with date-range/filter controls, MCP-enabled 'pull reports just by asking', accountant access to 'generating reports') but never explicitly names or documents P&L, balance sheet, or cash-flow statement generation specifically. Missing for 10: explicit documentation/screenshots of P&L, balance sheet, and cash-flow statement generation for arbitrary periods, and any independent/hands-on verification of their accuracy.

   • [claimed-docs] “Accountant collaboration: "Invite your accountant in Zoho Books to access real-time data. From handling journal entries and base currency ad…”
   • [claimed-docs] “Generate invoices, track payments, log expenses, and create financial reports.”
   • [claimed-docs] “Built-in AI plus agent hooks, in the vendor's own words: "Ask Zia in plain English", "Spot anomalies before they become problems", "Whether …”
   • [claimed-docs] “Workflow automation is first-class: "Trigger workflow: Easily create and trigger unique business workflows to notify, update, or validate in…”

   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