Xero vs Mercury Books

Agent access

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

   weight 2 · round to Xero
   Xero~partialprobed5/10

   llms.txt returns a 404 (xero-probe-1), so there is no dedicated agent-oriented manifest file, but Xero does provide an official MCP server and AI toolkit documentation (developer.xero.com/documentation/tools/mcp-server, xero-docs-6, xero-docs-19) that an agent could be pointed at instead. This partially satisfies the intent of agent-discoverable docs but not via the standard llms.txt convention. missing for 10: a working llms.txt endpoint, evidence of agent-oriented markdown docs beyond MCP server README, independent confirmation an agent successfully consumes these docs.

   • [probe] “PROBE llms.txt: HTTP 404 at https://developer.xero.com/llms.txt”
   • [probe] “official MCP server documented at https://developer.xero.com/documentation/tools/mcp-server”
   • [claimed-docs] “Get Started with Xero's AI Toolkit including OpenAI Agents SDK, MCP Server, LangChain and prompt examples.”
   • [claimed-docs] “Contact management - Chart of Accounts management - Invoice creation and management - MCP protocol compliance”

   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 Xero
   Xero✓fullclaimed7/10

   Xero exposes a documented REST API with OpenAPI spec, official SDKs (xero-node), and a premium 'Custom Connections' option explicitly designed for machine-to-machine (M2M) integrations to a single org without interactive user auth — a direct enabler of headless/CI automation. Missing for 10: explicit CI/CD pipeline examples, documented service-account/headless auth walkthrough, and independent hands-on confirmation of running it unattended in automation pipelines.

   • [claimed-docs] “This includes Xero APIs, SDKs, code samples, documentation and more.”
   • [claimed-docs] “This repository holds the official Xero OpenAPI descriptions... An OpenAPI (Swagger) specification for the Xero API with OAuth 2.0 security …”
   • [github] “The xero-node SDK makes it easy for developers to access Xero's APIs in their JavaScript code, and build robust applications and software us…”
   • [github] “Custom Connections - a Xero premium option for building M2M integrations to a single org”
   • [github] “custom-connections-starter - Basic app showing Custom Connections - a Xero premium option for building M2M integrations to a single org”
   • [claimed-docs] “We are using OpenAPI generator along with these OAS yaml files to generate our new SDKs.”

   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
   Xero—none0/10

   Evidence only shows Xero publishing its own MCP server (and AI Toolkit) so external agents can call Xero's tools, not Xero acting as an MCP client that lets users plug arbitrary external MCP servers into it to extend its own tool use. No documentation of a client-side MCP integration point in Xero (e.g., JAX or other AI features consuming outside MCP servers) is present.

   • [claimed-docs] “This is a Model Context Protocol (MCP) server implementation for Xero. It provides a bridge between the MCP protocol and Xero's API, allowin…”
   • [claimed-docs] “Get Started with Xero's AI Toolkit including OpenAI Agents SDK, MCP Server, LangChain and prompt examples.”
   • [claimed-docs] “Contact management - Chart of Accounts management - Invoice creation and management - MCP protocol compliance”
   • [probe] “official MCP server documented at https://developer.xero.com/documentation/tools/mcp-server”

   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 Xero
   Xero✓fullprobed8/10

   Xero ships an official MCP server (xero-mcp-server) documented on developer.xero.com and GitHub, providing standardized MCP protocol access to accounting features like contacts, chart of accounts, and invoices, and Xero also promotes an 'AI Toolkit' including the MCP server, OpenAI Agents SDK and LangChain integration. Missing for 10: independent/hands-on third-party verification of the MCP server's reliability and breadth of tool coverage beyond vendor docs.

   • [claimed-docs] “This is a Model Context Protocol (MCP) server implementation for Xero. It provides a bridge between the MCP protocol and Xero's API, allowin…”
   • [claimed-docs] “This is a Model Context Protocol (MCP) server implementation for Xero. It provides a bridge between the MCP protocol and Xero's API”
   • [claimed-docs] “Contact management - Chart of Accounts management - Invoice creation and management - MCP protocol compliance”
   • [claimed-docs] “Get Started with Xero's AI Toolkit including OpenAI Agents SDK, MCP Server, LangChain and prompt examples.”
   • [probe] “official MCP server documented at https://developer.xero.com/documentation/tools/mcp-server”

   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
   Xero—none0/10

   Evidence shows Xero offers SDKs, an OpenAPI spec, and an MCP server, but there is no mention of an official CLI tool anywhere in the pack.

   ⚑ 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 Xero
   Xero✓fullclaimed9/10

   Xero has a well-documented public developer API with official OpenAPI spec, SDKs (xero-node), and a developer portal (developer.xero.com), enabling programmatic access; this is independently confirmed by the GitHub repos and OpenAPI descriptions. missing for 10: independent third-party hands-on verification of API robustness beyond vendor/SDK docs.

   • [claimed-docs] “This includes Xero APIs, SDKs, code samples, documentation and more.”
   • [claimed-docs] “This repository holds the official Xero OpenAPI descriptions.”
   • [github] “The xero-node SDK makes it easy for developers to access Xero's APIs in their JavaScript code, and build robust applications and software us…”
   • [claimed-docs] “This repository holds the official Xero OpenAPI descriptions... An OpenAPI (Swagger) specification for the Xero API with OAuth 2.0 security …”
   • [claimed-docs] “We are using OpenAPI generator along with these OAS yaml files to generate our new SDKs.”

   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 Xero
   Xero~partialclaimed4/10

   Xero's OpenAPI spec documents OAuth 2.0 security scopes, and Custom Connections offers M2M credentials scoped to a single org — both provide a technical basis for least-privilege API access, but none of the evidence specifically ties this to issuing scoped credentials for an AI agent (the MCP server docs describe protocol bridging, not credential scoping/permissions setup for agents). Missing for 10: explicit documentation of agent-specific scope selection, least-privilege credential issuance workflow for MCP/agent use, and independent confirmation of this being used for AI agents.

   • [claimed-docs] “This repository holds the official Xero OpenAPI descriptions... An OpenAPI (Swagger) specification for the Xero API with OAuth 2.0 security …”
   • [github] “Custom Connections - a Xero premium option for building M2M integrations to a single org”
   • [github] “custom-connections-starter - Basic app showing Custom Connections - a Xero premium option for building M2M integrations to a single org”
   • [claimed-docs] “This is a Model Context Protocol (MCP) server implementation for Xero. It provides a bridge between the MCP protocol and Xero's API, allowin…”
   • [claimed-docs] “Contact management - Chart of Accounts management - Invoice creation and management - MCP protocol compliance”

   proof ↗⚑ flag

   Mercury Books—none0/10

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

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

   proof ↗⚑ flag

8. ai-native userBuild against official SDKs

   weight 2 · round to Xero
   Xero✓fullprobed8/10

   Xero maintains official SDKs (xero-node) generated from official OpenAPI specs, plus a dedicated AI Toolkit with an official MCP server, OpenAI Agents SDK and LangChain integration, directly enabling AI-native development against Xero's API. missing for 10: independent/hands-on developer corroboration of SDK quality and no evidence of SDKs beyond JS/OpenAPI-generated languages being actively maintained.

   • [github] “The xero-node SDK makes it easy for developers to access Xero's APIs in their JavaScript code, and build robust applications and software us…”
   • [claimed-docs] “This repository holds the official Xero OpenAPI descriptions.”
   • [claimed-docs] “We are using OpenAPI generator along with these OAS yaml files to generate our new SDKs.”
   • [claimed-docs] “Get Started with Xero's AI Toolkit including OpenAI Agents SDK, MCP Server, LangChain and prompt examples.”
   • [claimed-docs] “This is a Model Context Protocol (MCP) server implementation for Xero. It provides a bridge between the MCP protocol and Xero's API, allowin…”
   • [probe] “official MCP server documented at https://developer.xero.com/documentation/tools/mcp-server”

   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
   Xero—none0/10

   The evidence pack covers Xero's API, SDKs, OpenAPI spec, and MCP server, but contains no mention of webhooks or event subscription capabilities anywhere.

   ⚑ flag

   Mercury Books—none0/10

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

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

   proof ↗⚑ flag

Agentic features

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

   weight 2 · round to Mercury Books
   Xero~partialclaimed6/10

   Xero offers JAX, an AI feature that reconciles transactions, categorizes/matches, and extracts bill details, plus dashboards for KPIs/ratios/benchmarking and 'instant answers about cash flow, profit trends and financial health' — these are AI-generated insights/suggestions drawn from user data inside the product. However, evidence is largely marketing copy without hands-on corroboration of insight quality or breadth (e.g., proactive suggestions beyond reconciliation/invoicing/bill entry). Missing for 10: independent/hands-on verification of AI insight accuracy, broader analytical insights (e.g., forecasting, anomaly detection) beyond reconciliation and bill scanning, and detail on how 'instant answers' works.

   • [claimed-docs] “JAX, your AI finance partner, reconciles your transactions for you. Connect your bank accounts to Xero. Let JAX categorize and match transac…”
   • [claimed-docs] “JAX, your AI finance partner, reconciles your transactions for you... Let JAX categorize and match transactions while you're busy with your …”
   • [claimed-docs] “Automate bill entry by uploading files directly to Xero or forwarding bills from your email. Xero's AI extracts the key details to create dr…”
   • [claimed-docs] “Get instant answers about your cash flow, profit trends and financial health.”
   • [claimed-docs] “Analyze KPIs and ratios”
   • [claimed-docs] “Customize performance dashboards ... Analyze KPIs and ratios”

   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 Mercury Books
   Xero~partialprobed4/10

   Xero provides APIs, SDKs, and an MCP server enabling third-party or AI agents to trigger accounting actions, and JAX offers some automated reconciliation/invoicing features, but there is no evidence of a native scheduler, workflow/automation builder, or persistent background job system that runs autonomously without an external trigger. missing for 10: documented autonomous scheduling/trigger mechanism, native workflow automation builder, evidence of unattended background execution beyond single AI-assisted actions like JAX.

   • [claimed-docs] “This is a Model Context Protocol (MCP) server implementation for Xero. It provides a bridge between the MCP protocol and Xero's API, allowin…”
   • [claimed-docs] “Get Started with Xero's AI Toolkit including OpenAI Agents SDK, MCP Server, LangChain and prompt examples.”
   • [claimed-docs] “JAX, your AI finance partner, reconciles your transactions for you. Connect your bank accounts to Xero. Let JAX categorize and match transac…”
   • [claimed-docs] “JAX is Xero's AI invoicing tool that lets you create, edit, and send invoices using plain-language commands.”
   • [probe] “official MCP server documented at https://developer.xero.com/documentation/tools/mcp-server”

   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 to Mercury Books
   Xero~partialclaimed6/10

   Xero has a built-in AI assistant called JAX that handles reconciliation, invoicing, and bill entry via plain-language commands, directly matching the story of delegating tasks to an in-product AI assistant. However, JAX's scope appears limited to a few specific workflows (reconciliation, invoicing, bill extraction) rather than a general-purpose task delegate, and there's no independent/hands-on corroboration beyond vendor marketing pages. Missing for 10: broader task coverage beyond reconciliation/invoicing/bills, independent user reviews confirming JAX's real-world reliability, and clarity on how conversational/agentic the delegation experience actually is.

   • [claimed-docs] “JAX, your AI finance partner, reconciles your transactions for you. Connect your bank accounts to Xero. Let JAX categorize and match transac…”
   • [claimed-docs] “JAX is Xero's AI invoicing tool that lets you create, edit, and send invoices using plain-language commands.”
   • [claimed-docs] “JAX, your AI finance partner, reconciles your transactions for you... Let JAX categorize and match transactions while you're busy with your …”
   • [claimed-docs] “Automate bill entry by uploading files directly to Xero or forwarding bills from your email. Xero's AI extracts the key details to create dr…”

   proof ↗⚑ flag

   Mercury Books✓fullclaimed7/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round to Mercury Books
   Xero~partialclaimed6/10

   Xero's JAX assistant lets users create/edit/send invoices and reconcile bank transactions using plain-language commands, directly supporting natural-language operation for end users (not just developers via MCP). However, this NL capability is documented only for invoicing and reconciliation, not the full product surface (e.g., bills, reports, contacts), and there's no independent/hands-on corroboration of JAX's reliability. Missing for 10: NL command support across broader workflows (reporting, bill pay, contact management), and independent verification of JAX's real-world accuracy.

   • [claimed-docs] “JAX is Xero's AI invoicing tool that lets you create, edit, and send invoices using plain-language commands.”
   • [claimed-docs] “JAX, your AI finance partner, reconciles your transactions for you. Connect your bank accounts to Xero. Let JAX categorize and match transac…”
   • [claimed-docs] “JAX, your AI finance partner, reconciles your transactions for you... Let JAX categorize and match transactions while you're busy with your …”

   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
   Xero—none0/10

   Evidence shows Xero has a developer portal with API docs, OpenAPI specs, and SDKs, but nothing indicates an interactive API reference with runnable/try-it-now examples (e.g., Swagger UI-style live console); the OpenAPI repo is just spec files for SDK generation. missing for 10: any mention of an interactive/try-it console, runnable code examples in-browser, or sandboxed API playground.

   • [claimed-docs] “This includes Xero APIs, SDKs, code samples, documentation and more.”
   • [claimed-docs] “This repository holds the official Xero OpenAPI descriptions.”
   • [claimed-docs] “This repository holds the official Xero OpenAPI descriptions... An OpenAPI (Swagger) specification for the Xero API with OAuth 2.0 security …”
   • [claimed-docs] “We are using OpenAPI generator along with these OAS yaml files to generate our new SDKs.”

   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 Xero
   Xero✓fullclaimed9/10

   Xero maintains an official GitHub repo of OpenAPI (Swagger) descriptions with OAuth 2.0 security schema, explicitly used to generate SDKs, giving a clear machine-readable API spec download. Missing for 10: independent third-party validation/hands-on confirmation of spec completeness or versioning practices.

   • [claimed-docs] “This repository holds the official Xero OpenAPI descriptions.”
   • [claimed-docs] “This repository holds the official Xero OpenAPI descriptions... An OpenAPI (Swagger) specification for the Xero API with OAuth 2.0 security …”
   • [claimed-docs] “We are using OpenAPI generator along with these OAS yaml files to generate our new SDKs.”

   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
   Xero—none0/10

   No evidence of a dedicated sandbox/demo company environment for testing against the Xero API without touching live production data; the developer docs, SDKs, and MCP server evidence describe general API access but never mention a sandbox, demo org, or test environment. Missing for 10: any mention of a sandbox/demo company, test credentials, or isolated non-production environment for API/agent testing.

   ⚑ 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 Xero
   Xero~partialclaimed3/10

   Xero publishes an official OpenAPI spec and developer portal (xero-docs-2, xero-docs-32) implying a versioned API surface, but no evidence describes a documented deprecation policy, version sunset timeline, or changelog for breaking changes. missing for 10: explicit deprecation/versioning policy docs, sunset timelines, changelog of API version history.

   • [claimed-docs] “This repository holds the official Xero OpenAPI descriptions.”
   • [claimed-docs] “This repository holds the official Xero OpenAPI descriptions... An OpenAPI (Swagger) specification for the Xero API with OAuth 2.0 security …”
   • [claimed-docs] “This includes Xero APIs, SDKs, code samples, documentation and more.”

   proof ↗⚑ flag

   Mercury Books—none0/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round to Mercury Books
   Xero~partialprobed5/10

   Xero documents native bulk-style workflows such as paying multiple bills at once and exporting a single payment file for many suppliers (xero-docs-25, xero-docs-30), and its REST API/SDK and MCP server expose programmatic access that could be scripted for batch operations (xero-gh-1, xero-docs-19). However there is no evidence of a dedicated bulk/batch API endpoint or MCP tool for bulk-updating invoices, contacts, or other records across many items at once. Missing for 10: explicit bulk/batch API or MCP tool documentation, evidence of bulk operations beyond bill payments (e.g., bulk invoicing, bulk contact updates), and independent confirmation of bulk operation reliability.

   • [claimed-docs] “Export a payment file from Xero and upload it directly to your online banking to pay multiple bills in one go. Each supplier receives a sing…”
   • [claimed-docs] “Pay multiple bills at once and automate reconciliation ensuring records are always up-to-date.”
   • [github] “The xero-node SDK makes it easy for developers to access Xero's APIs in their JavaScript code, and build robust applications and software us…”
   • [claimed-docs] “Contact management - Chart of Accounts management - Invoice creation and management - MCP protocol compliance”
   • [probe] “official MCP server documented at https://developer.xero.com/documentation/tools/mcp-server”

   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 Mercury Books
   Xero~partialprobed3/10

   Xero shows built-in automations (JAX auto-reconciliation matching, duplicate bill detection, automated bill data extraction) and exposes APIs/webhooks plus an MCP server that could be used by developers to build custom event-triggered actions, but there is no evidence of a native user-facing rules/trigger builder where an AI-native user defines arbitrary 'if event then action' rules. Missing for 10: a documented rules engine or webhook/trigger configuration UI, evidence of custom trigger-action mapping, and independent confirmation that such automation works end-to-end.

   • [claimed-docs] “JAX, your AI finance partner, reconciles your transactions for you. Connect your bank accounts to Xero. Let JAX categorize and match transac…”
   • [claimed-docs] “Automate bill entry by uploading files directly to Xero or forwarding bills from your email. Xero's AI extracts the key details to create dr…”
   • [claimed-docs] “Detect and flag duplicate bills automatically to minimize fraud and payment errors”
   • [claimed-docs] “This is a Model Context Protocol (MCP) server implementation for Xero. It provides a bridge between the MCP protocol and Xero's API, allowin…”
   • [probe] “official MCP server documented at https://developer.xero.com/documentation/tools/mcp-server”

   proof ↗⚑ flag

   Mercury Books~partialclaimed5/10

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

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

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   Xero—none0/10

   No evidence Xero supports scheduling recurring jobs/workflows for AI-native automation; the pack covers APIs, SDKs, MCP server, and accounting features but nothing about scheduled/recurring automation triggers or workflow scheduling.

   ⚑ 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
   Xero—none0/10

   No evidence anywhere in the pack of versioning, review, or rollback capabilities for automations/workflows in Xero; the evidence covers API/SDK access, MCP server, invoicing, reconciliation, and multi-currency features but nothing about automation version history or rollback.

   ⚑ flag

   Mercury Books—none0/10

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

   ⚑ flag

Ai reconciliation

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

   weight 3 · round drawn
   Xero~partialprobed5/10

   Xero's JAX assistant automates transaction categorization/matching for bank reconciliation, and the MCP server exposes accounting objects (invoices, chart of accounts, contacts) for programmatic/agent access, so the building blocks for an agent-driven reconciliation exist. However, there is no evidence of an agent performing a full month-end close workflow — no documented exception-flagging logic, no 'prepared for human review' close package, and no first-party or hands-on report of an agent doing this end-to-end. Missing for 10: exception flagging/anomaly detection features, month-end close packaging or review workflow, and evidence of an agent (vs. human using JAX UI) orchestrating the full process via MCP.

   • [claimed-docs] “JAX, your AI finance partner, reconciles your transactions for you. Connect your bank accounts to Xero. Let JAX categorize and match transac…”
   • [claimed-docs] “JAX, your AI finance partner, reconciles your transactions for you... Let JAX categorize and match transactions while you're busy with your …”
   • [claimed-docs] “Contact management - Chart of Accounts management - Invoice creation and management - MCP protocol compliance”
   • [probe] “official MCP server documented at https://developer.xero.com/documentation/tools/mcp-server”
   • [claimed-docs] “Get Started with Xero's AI Toolkit including OpenAI Agents SDK, MCP Server, LangChain and prompt examples.”

   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 to Mercury Books
   Xero✓fullclaimed7/10

   Xero explicitly markets bank feed connections with JAX auto-categorizing/matching transactions and integration directory entries (e.g., Mercury) show direct bank connections, supporting daily automatic import and reconciliation. Missing for 10: explicit documentation of daily-sync frequency/reliability, and independent hands-on verification of the bank-feed connection process beyond marketing copy.

   • [claimed-docs] “JAX, your AI finance partner, reconciles your transactions for you. Connect your bank accounts to Xero. Let JAX categorize and match transac…”
   • [claimed-docs] “JAX, your AI finance partner, reconciles your transactions for you... Let JAX categorize and match transactions while you're busy with your …”
   • [claimed-docs] “Connect Mercury with Xero”
   • [claimed-docs] “Automate bill entry by uploading files directly to Xero or forwarding bills from your email. Xero's AI extracts the key details to create dr…”

   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
   Xero~partialclaimed6/10

   Xero's AI feature JAX is explicitly described as categorizing and matching imported bank transactions during reconciliation, directly matching the story's core ask. However, evidence does not confirm that JAX learns from user corrections over time or how correction-based learning works. missing for 10: evidence of learning/adaptation from user corrections, independent/hands-on verification of categorization accuracy improving over time, detail on how suggestions are generated.

   • [claimed-docs] “JAX, your AI finance partner, reconciles your transactions for you. Connect your bank accounts to Xero. Let JAX categorize and match transac…”
   • [claimed-docs] “JAX, your AI finance partner, reconciles your transactions for you... Let JAX categorize and match transactions while you're busy with your …”

   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 Xero
   Xero~partialclaimed6/10

   Xero's marketing docs describe an AI reconciliation feature (JAX) that connects bank accounts and matches/categorizes transactions, and pay-bills docs mention duplicate detection, but the evidence never explicitly describes the classic bank rec workflow of surfacing matched/unmatched/duplicate transactions for review in the ledger-reconciliation screen itself. missing for 10: first-party documentation of the actual bank reconciliation UI showing matched/unmatched/duplicate transaction states, independent/hands-on verification of the reconciliation workflow, and detail on how duplicates are flagged during bank rec specifically (only bill-duplicate detection is cited).

   • [claimed-docs] “JAX, your AI finance partner, reconciles your transactions for you. Connect your bank accounts to Xero. Let JAX categorize and match transac…”
   • [claimed-docs] “JAX, your AI finance partner, reconciles your transactions for you... Let JAX categorize and match transactions while you're busy with your …”
   • [claimed-docs] “Detect and flag duplicate bills automatically to minimize fraud and payment errors”
   • [claimed-docs] “Pay multiple bills at once and automate reconciliation ensuring records are always up-to-date.”

   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 Xero
   Xero~partialclaimed6/10

   Xero documents automated bill capture (email/upload with AI extraction to draft bills), duplicate detection, and batch payment file export/upload plus reconciliation, covering most of the bills-AP workflow. However, evidence does not clearly describe a configurable multi-step approval routing workflow (e.g., approval thresholds, multiple approvers) beyond bills being 'ready for approval'. missing for 10: explicit approval-routing/workflow rules documentation, evidence of scheduled (future-dated) payment scheduling beyond batch export, independent/hands-on confirmation of the end-to-end flow.

   • [claimed-docs] “Automate bill entry by uploading files directly to Xero or forwarding bills from your email. Xero's AI extracts the key details to create dr…”
   • [claimed-docs] “Export a payment file from Xero and upload it directly to your online banking to pay multiple bills in one go. Each supplier receives a sing…”
   • [claimed-docs] “Pay multiple bills at once and automate reconciliation ensuring records are always up-to-date.”
   • [claimed-docs] “Detect and flag duplicate bills automatically to minimize fraud and payment errors”

   proof ↗⚑ flag

   Mercury Books~partialclaimed3/10

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

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

   proof ↗⚑ flag

Payables

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

   weight 2 · round drawn
   Xero—none0/10

   The evidence pack covers bill payment, duplicate detection, reconciliation, and invoicing features, but contains no mention of accounts payable aging reports or point-in-time vendor balance reporting.

   ⚑ 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
   Xero—none0/10

   No evidence in the pack mentions period locking, closing periods, or preventing edits to prior-period transactions; all evidence covers invoicing, payments, multi-currency, MCP/API tooling, and general reviews. missing for 10: any mention of period lock/close feature, permission controls for locked periods, or 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 drawn
   Xero—none0/10

   Evidence shows only basic bank transaction reconciliation via JAX AI, but no evidence of a structured month-end close checklist, accrual tracking, or review sign-off workflow that an accountant could run to manage close processes.

   • [claimed-docs] “JAX, your AI finance partner, reconciles your transactions for you. Connect your bank accounts to Xero. Let JAX categorize and match transac…”
   • [claimed-docs] “JAX, your AI finance partner, reconciles your transactions for you... Let JAX categorize and match transactions while you're busy with your …”

   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
   Xero—none0/10

   The evidence pack contains no mention of inviting an accountant/bookkeeper, user roles, or permission-scoped access to the books — it focuses on APIs, MCP servers, invoicing, reconciliation, and app marketplace integrations. Xero is well known to have this feature in reality, but per the rules only the evidence pack can be judged, and no citation here addresses accountant invites or role-based access.

   ⚑ 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 Xero
   Xero~partialclaimed6/10

   Xero has a documented OpenAPI-spec-based API and SDKs (xero-node) that expose accounting endpoints including reports like Trial Balance and general ledger data via the Accounting API, with an official OpenAPI description repo confirming open format specs. However, no evidence explicitly confirms a full 'general ledger' export endpoint or trial balance report details, and no independent developer corroboration of actually pulling GL/trial balance data is present. missing for 10: explicit documentation/evidence of a dedicated general ledger/trial balance endpoint, independent developer confirmation of successful GL/trial balance extraction, and detail on data completeness/limits of these reports via the API.

   • [claimed-docs] “This includes Xero APIs, SDKs, code samples, documentation and more.”
   • [claimed-docs] “This repository holds the official Xero OpenAPI descriptions.”
   • [claimed-docs] “This repository holds the official Xero OpenAPI descriptions... An OpenAPI (Swagger) specification for the Xero API with OAuth 2.0 security …”
   • [claimed-docs] “We are using OpenAPI generator along with these OAS yaml files to generate our new SDKs.”
   • [github] “The xero-node SDK makes it easy for developers to access Xero's APIs in their JavaScript code, and build robust applications and software us…”
   • [github] “The xero-node SDK makes it easy for developers to access Xero's APIs in their JavaScript code, and build robust applications”

   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
   Xero✓fullclaimed7/10

   Xero documents direct bank-feed reconciliation via JAX (xero-docs-20/27), native Stripe payment integration (xero-docs-23, xero-intdir-3), and payroll connectivity via the Gusto app in its App Store (xero-intdir-4), all designed to feed ledger data automatically. Missing for 10: independent/hands-on verification that these integrations reliably auto-sync in practice, and clearer detail on native payroll (vs. third-party Gusto) ledger posting.

   • [claimed-docs] “JAX, your AI finance partner, reconciles your transactions for you. Connect your bank accounts to Xero. Let JAX categorize and match transac…”
   • [claimed-docs] “JAX, your AI finance partner, reconciles your transactions for you... Let JAX categorize and match transactions while you're busy with your …”
   • [claimed-docs] “Use Stripe to accept online payments by credit and debit cards, digital wallets, Klarna, ACH Debit, and more”
   • [claimed-docs] “Stripe makes it easy to accept payments from debit cards, credit cards, Apple Pay, and Google Pay for online invoices sent from Xero—so you …”
   • [claimed-docs] “Behind every successful business is a thriving team. Hire, pay, insure, and support your employees with Gusto’s all-in-one people platform.”
   • [claimed-docs] “Connect Mercury with Xero”

   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 to Xero
   Xero~partialclaimed5/10

   Xero's app marketplace lists a third-party partner (Q2X) that explicitly handles QuickBooks-to-Xero migrations 'ensuring a smooth transition of your historical data,' and Xero even subsidizes 'simple conversions,' showing migration support exists. However this is a third-party service rather than a native first-party import tool, is scoped mainly to QuickBooks, and no evidence details preservation of full transaction-level granularity or migration from other accounting systems generally. Missing for 10: native first-party migration/import tooling, evidence covering non-QuickBooks source systems, and detail on transaction-level fidelity guarantees.

   • [claimed-docs] “The Q2X team ensures a seamless transition from QuickBooks to Xero. Our specialists will help set up a Xero account and handle the migration…”
   • [claimed-docs] “The Q2X team ensures a seamless transition from QuickBooks to Xero. Our specialists will help set up a Xero account and handle the migration…”

   proof ↗⚑ flag

   Mercury Books—none0/10

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

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

   proof ↗⚑ flag

Invoicing

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

   weight 3 · round to Xero
   Xero✓fullclaimed8/10

   Xero provides customizable invoice templates, a Pay Now button with Stripe online payments, and invoice tracking that alerts when a customer opens the invoice, directly covering creation, sending, online payment, and view/payment status tracking. Community feedback also corroborates value of invoicing/Stripe integration. Missing for 10: independent hands-on verification of read-receipt accuracy and paid-status timing beyond vendor docs.

   • [claimed-docs] “Use customizable invoice templates to create professional invoices fast – add your logo, payment terms, and branding.”
   • [claimed-docs] “Add your logo and payment terms to Xero's templates for professional invoices”
   • [claimed-docs] “Use Stripe to accept online payments by credit and debit cards, digital wallets, Klarna, ACH Debit, and more”
   • [claimed-docs] “Give customers a slick payment process with a Pay Now button on invoices – and encourage prompt payments”
   • [claimed-docs] “Invoice tracking lets you know the moment a customer opens your invoice, so you can follow up at exactly the right time.”
   • [claimed-docs] “I like Xero for its overall simplicity, especially compared to QuickBooks Online. I find the invoicing feature and Stripe integration in Xer…”
   • [claimed-docs] “Stripe makes it easy to accept payments from debit cards, credit cards, Apple Pay, and Google Pay for online invoices sent from Xero—so you …”

   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 drawn
   Xero—none0/10

   The evidence pack covers invoicing features like templates, Pay Now buttons, invoice tracking, and JAX AI invoicing, but contains no mention of recurring/repeating invoice scheduling or automated overdue payment reminders. Missing for 10: any documentation of recurring invoice setup, reminder scheduling rules, or overdue-customer notification workflows.

   ⚑ 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 Xero
   Xero~partialclaimed4/10

   Evidence shows Xero has invoicing, invoice tracking (open/paid status), and contact/customer management (xero-docs-29, xero-docs-19, xero-docs-13), which are prerequisites for AR tracking, but there is no explicit mention of an aging report or per-customer balance report in the pack. missing for 10: explicit aging report feature documentation, per-customer outstanding balance report, independent/hands-on confirmation of AR reporting.

   • [claimed-docs] “Invoice tracking lets you know the moment a customer opens your invoice, so you can follow up at exactly the right time.”
   • [claimed-docs] “Contact management - Chart of Accounts management - Invoice creation and management - MCP protocol compliance”
   • [claimed-docs] “Use customizable invoice templates to create professional invoices fast – add your logo, payment terms, and branding.”
   • [claimed-docs] “Add your logo and payment terms to Xero's templates for professional invoices”

   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 Xero
   Xero~partialprobed5/10

   Xero provides a full accounting API, SDKs, OpenAPI spec, and an official MCP server with Chart of Accounts and invoice management capabilities, which an agent could use to draft journal entries programmatically. However, there is no documented review-queue/approval workflow, draft-vs-post distinction for journal entries specifically, or accountant-facing review mechanism exposed via the API/MCP server. missing for 10: explicit journal entry draft/post API documentation, a review-queue or approval-hold feature for accountant sign-off, and evidence of an accountant-facing review UI tied to agent-created entries.

   • [claimed-docs] “This is a Model Context Protocol (MCP) server implementation for Xero. It provides a bridge between the MCP protocol and Xero's API, allowin…”
   • [claimed-docs] “Contact management - Chart of Accounts management - Invoice creation and management - MCP protocol compliance”
   • [claimed-docs] “This repository holds the official Xero OpenAPI descriptions... An OpenAPI (Swagger) specification for the Xero API with OAuth 2.0 security …”
   • [github] “The xero-node SDK makes it easy for developers to access Xero's APIs in their JavaScript code, and build robust applications and software us…”
   • [probe] “official MCP server documented at https://developer.xero.com/documentation/tools/mcp-server”

   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
   Xero~partialclaimed3/10

   The MCP server docs mention 'Chart of Accounts management' as a supported feature, indicating Xero exposes COA management capability, but there is no evidence detailing account types, sub-accounts, or class/tag (tracking category) dimensions. missing for 10: evidence of account type configuration, sub-account hierarchy support, and tracking category/tag/class dimension customization.

   • [claimed-docs] “Contact management - Chart of Accounts management - Invoice creation and management - MCP protocol compliance”

   proof ↗⚑ flag

   Mercury Books~partialclaimed5/10

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

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

   proof ↗⚑ flag

Journal entries

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

   weight 3 · round to Mercury Books
   Xero—none0/10

   The evidence pack covers invoicing, bill pay, reconciliation, multi-currency, and API/MCP tooling, but contains no mention of manual journal entries, debit/credit balancing, or journal memos anywhere in the docs, SDK, or MCP feature list. Missing for 10: any documentation of a manual journal entry feature, evidence of debit/credit balance validation, or memo/narration support on journals.

   • [claimed-docs] “Contact management - Chart of Accounts management - Invoice creation and management - MCP protocol compliance”
   • [claimed-docs] “This repository holds the official Xero OpenAPI descriptions... An OpenAPI (Swagger) specification for the Xero API with OAuth 2.0 security …”

   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 Xero
   Xero~partialprobed5/10

   Xero natively flags duplicate bills (xero-docs-31) and has JAX AI reconciling/categorizing transactions (xero-docs-20/27), and its official MCP server + APIs (xero-docs-3/14/19, xero-probe-2) let a developer build a custom agent to query ledger data for anomaly detection. However there's no evidence of a purpose-built 'monitor ledger for spend anomalies pre-close' agent or workflow — this would require custom development on top of the API/MCP server rather than an out-of-box capability. Missing for 10: a documented anomaly-detection/close-audit agent feature, evidence of spend-anomaly (not just duplicate-bill) flagging, and any close-process integration.

   • [claimed-docs] “Detect and flag duplicate bills automatically to minimize fraud and payment errors”
   • [claimed-docs] “JAX, your AI finance partner, reconciles your transactions for you. Connect your bank accounts to Xero. Let JAX categorize and match transac…”
   • [claimed-docs] “JAX, your AI finance partner, reconciles your transactions for you... Let JAX categorize and match transactions while you're busy with your …”
   • [claimed-docs] “This is a Model Context Protocol (MCP) server implementation for Xero. It provides a bridge between the MCP protocol and Xero's API, allowin…”
   • [claimed-docs] “Contact management - Chart of Accounts management - Invoice creation and management - MCP protocol compliance”
   • [probe] “official MCP server documented at https://developer.xero.com/documentation/tools/mcp-server”

   proof ↗⚑ flag

   Mercury Books—none0/10

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

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

   proof ↗⚑ flag

Audit trail

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

   weight 3 · round drawn
   Xero—none0/10

   No evidence in the pack references audit trails, change history, user activity logs, or ledger version tracking anywhere in Xero's documentation or community reports; the pack covers APIs, MCP servers, invoicing, reconciliation, and integrations but nothing about audit logging.

   ⚑ 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 Xero
   Xero~partialclaimed3/10

   The only relevant evidence is a marketing line claiming Xero can 'generate consolidated financial statements in multiple currencies,' which is ambiguous and likely refers to multi-currency transaction consolidation within a single entity rather than true multi-legal-entity consolidation (parent/subsidiary structures). No evidence describes managing separate legal entities, intercompany eliminations, or org-to-org consolidation tools. Missing for 10: explicit multi-entity/subsidiary management features, intercompany elimination support, and independent confirmation of cross-entity consolidated reporting.

   • [claimed-docs] “Generate consolidated financial statements in multiple currencies for a clear view of your financial position”
   • [claimed-docs] “Xero's multi-currency accounting software lets you do business in multiple currencies with ease. Get real-time foreign exchange rates, simpl…”
   • [claimed-docs] “Xero's multi-currency accounting software lets you do business in multiple currencies with ease.”

   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 Xero
   Xero~partialprobed6/10

   Xero has a comprehensive REST API with OpenAPI spec, SDKs, and an official MCP server exposing contacts, chart of accounts, and invoicing, indicating broad API coverage of core accounting workflows. However, there is no evidence confirming full parity with newer AI/UI-only features like JAX (AI invoicing/reconciliation assistant), KPI/benchmarking dashboards, or all pricing-plan features being exposed via API. missing for 10: confirmation that JAX AI features, performance dashboards/benchmarking, and all UI-exclusive workflows are accessible via API/MCP, independent verification of full UI-API parity.

   • [claimed-docs] “This includes Xero APIs, SDKs, code samples, documentation and more.”
   • [claimed-docs] “This repository holds the official Xero OpenAPI descriptions.”
   • [github] “The xero-node SDK makes it easy for developers to access Xero's APIs in their JavaScript code, and build robust applications and software us…”
   • [claimed-docs] “This is a Model Context Protocol (MCP) server implementation for Xero. It provides a bridge between the MCP protocol and Xero's API, allowin…”
   • [claimed-docs] “Contact management - Chart of Accounts management - Invoice creation and management - MCP protocol compliance”
   • [probe] “official MCP server documented at https://developer.xero.com/documentation/tools/mcp-server”
   • [claimed-docs] “This repository holds the official Xero OpenAPI descriptions... An OpenAPI (Swagger) specification for the Xero API with OAuth 2.0 security …”
   • [claimed-docs] “JAX, your AI finance partner, reconciles your transactions for you. Connect your bank accounts to Xero. Let JAX categorize and match transac…”
   • [claimed-docs] “JAX is Xero's AI invoicing tool that lets you create, edit, and send invoices using plain-language commands.”
   • [claimed-docs] “Analyze KPIs and ratios”

   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 Xero
   Xero~partialclaimed4/10

   Xero exposes API/OpenAPI access and third-party migration services (Q2X) that imply data can be extracted, but there is no documented native 'export all my data' bulk/open-format export feature or data-portability policy aimed at users leaving the platform. missing for 10: a first-party bulk data export tool/feature, documented open-format (CSV/JSON) full-account export, and any explicit data-portability/exit policy statement.

   • [claimed-docs] “This repository holds the official Xero OpenAPI descriptions.”
   • [claimed-docs] “This repository holds the official Xero OpenAPI descriptions... An OpenAPI (Swagger) specification for the Xero API with OAuth 2.0 security …”
   • [claimed-docs] “We are using OpenAPI generator along with these OAS yaml files to generate our new SDKs.”
   • [claimed-docs] “The Q2X team ensures a seamless transition from QuickBooks to Xero. Our specialists will help set up a Xero account and handle the migration…”

   proof ↗⚑ flag

   Mercury Books—none0/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Xero—none0/10

   No evidence in the pack mentions data residency, regional data storage options, or location choice for Xero data; all evidence covers APIs, SDKs, MCP server, invoicing, and other unrelated features. missing for 10: any mention of data residency/region selection, storage location controls, or compliance documentation addressing where customer data is stored.

   ⚑ 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
   Xero—none0/10

   No evidence pack item mentions AI-training data opt-out, data usage policies for model training, or any privacy controls addressing this specific concern; all evidence covers product features, SDKs, and MCP integration rather than data-training privacy controls.

   ⚑ 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
   Xero—none0/10

   No evidence in the pack addresses data retention or deletion controls for AI-native usage (e.g., API-level data purge, retention policies for MCP/agent access, or user-controlled deletion settings); coverage is limited to product features and integrations unrelated to retention/deletion. missing for 10: retention policy documentation, deletion/export APIs, MCP/agent-specific data lifecycle controls.

   ⚑ 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
   Xero—none0/10

   No evidence in the pack addresses telemetry, usage tracking, or an opt-out mechanism for AI/agent interactions with Xero; all evidence covers unrelated product features (invoicing, MCP server, integrations).

   ⚑ 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 Xero
   Xero~partialprobed6/10

   Xero has a documented official MCP server exposing accounting data (contacts, chart of accounts, invoices) plus a full API/SDK/OpenAPI spec, which could let an agent pull live ledger data to answer affordability-type questions, and Xero markets 'JAX' and 'instant answers about cash flow' features. However, there's no evidence of a natural-language reasoning layer that combines live ledger pulls with a financial-affordability judgment ('can we afford X') — the MCP server's documented capabilities are CRUD-style (contacts, invoices, chart of accounts) not analytical queries, and no hands-on example shows this exact grounded Q&A flow working. missing for 10: evidence of the MCP/API surfacing cash-flow or budget-analysis endpoints usable for affordability reasoning, and a concrete example/transcript of an agent answering such a question grounded in live data.

   • [claimed-docs] “This is a Model Context Protocol (MCP) server implementation for Xero. It provides a bridge between the MCP protocol and Xero's API, allowin…”
   • [claimed-docs] “Contact management - Chart of Accounts management - Invoice creation and management - MCP protocol compliance”
   • [claimed-docs] “Get Started with Xero's AI Toolkit including OpenAI Agents SDK, MCP Server, LangChain and prompt examples.”
   • [probe] “official MCP server documented at https://developer.xero.com/documentation/tools/mcp-server”
   • [claimed-docs] “Get instant answers about your cash flow, profit trends and financial health.”
   • [claimed-docs] “This repository holds the official Xero OpenAPI descriptions... An OpenAPI (Swagger) specification for the Xero API with OAuth 2.0 security …”

   proof ↗⚑ flag

   Mercury Books—none0/10

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

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

   proof ↗⚑ flag

Custom reports

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

   weight 2 · round drawn
   Xero—none0/10

   No evidence in the pack addresses custom report building, or filtering/grouping by class, location, or tracking-category/tag dimensions; the pack covers invoicing, payments, multi-currency, AI tools, and API/MCP integrations but nothing about the reporting/tracking-category feature set. Missing for 10: any mention of custom report builder, tracking categories (class/location), tag dimensions, or report filtering/grouping capabilities.

   ⚑ 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
   Xero~partialclaimed6/10

   Xero's marketing pages reference core financial reporting capability ("Get instant answers about your cash flow, profit trends and financial health", "Generate consolidated financial statements", "Analyze KPIs and ratios", customizable dashboards), consistent with an accounting platform producing P&L, balance sheet and cash-flow reports. However, the evidence pack lacks explicit documentation naming these three statements, period-selection controls, or independent corroboration of accuracy/on-demand generation. Missing for 10: explicit product docs naming P&L/balance sheet/cash-flow statement generation, evidence of date-range/period flexibility, and independent user validation of report accuracy.

   • [claimed-docs] “Get instant answers about your cash flow, profit trends and financial health.”
   • [claimed-docs] “Generate consolidated financial statements in multiple currencies for a clear view of your financial position”
   • [claimed-docs] “Analyze KPIs and ratios”
   • [claimed-docs] “Customize performance dashboards ... Analyze KPIs and ratios”

   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