Skip to content

How Mercury Books’s scores are calculated

The full audit trail, recomputed from the verdict data at build time through the same code that produced the leaderboard: verdict × quality × story weight per cell, cells sum to dimension scores, dimensions blend into the PA Score. Every number on the product page is reproducible from this page alone; for why the formula looks like this, see the methodology.

verdict factors: full ×1.0 · partial ×0.6 · disputed ×0.3 · none ×0.0 · n/a excluded from both sides · cell points = weight × quality × factor · cell max = weight × 10

PA Score12/100

Agent-ready 0.6 × 0.30 = 0.18

API quality 0.0 × 0.20 = 0.00

Openness 0.0 × 0.20 = 0.00

Built-in AI 61.1 × 0.15 = 9.16

Automation 20.3 × 0.15 = 3.04

(0.18 + 0.00 + 0.00 + 9.16 + 3.04) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 12.39 ÷ 1.00 = 12.4

Scores are stored to 1 decimal; the product page’s pills round to whole numbers for display. Each dimension below shows the stories, verdicts, and cited evidence behind its number.

Agent-ready0.6/100×0.30 of the PA blend

Outside-in: can YOUR agent reach and drive this product — API, MCP, CLI, headless runs, agent docs.

Point an agent at llms.txt or agent-oriented docsweight 2

2 (weight) × 2 (quality) × 0.3 (disputed) = 1.2 of 20 max

  • [claimed-docs] https://mercury.com/blog/introducing-mercury-booksSoon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkeeping tasks end-to-end.
  • [probe] https://support.mercury.com/llms.txtPROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt
  • [probe] https://support.mercury.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.mercury.com/api/openapi.json, https://support.mercury.com/.well-known/openapi.json)

Run the product headlessly / in CI for automationweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://mercury.com/blog/introducing-mercury-booksSoon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkeeping tasks end-to-end.
  • [probe] https://support.mercury.com/llms.txtPROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt
  • [probe] https://support.mercury.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.mercury.com/api/openapi.json, https://support.mercury.com/.well-known/openapi.json)

Plug MCP servers into this product so it can use their toolsweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [claimed-docs] https://mercury.com/blog/introducing-mercury-booksSoon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkeeping tasks end-to-end.
  • [probe] https://support.mercury.com/llms.txtPROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt
  • [probe] https://support.mercury.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.mercury.com/api/openapi.json, https://support.mercury.com/.well-known/openapi.json)

Connect an agent via an official MCP serverweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [claimed-docs] https://mercury.com/blog/introducing-mercury-booksSoon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkeeping tasks end-to-end.
  • [probe] https://support.mercury.com/llms.txtPROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt
  • [probe] https://support.mercury.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.mercury.com/api/openapi.json, https://support.mercury.com/.well-known/openapi.json)

Use an official CLIweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://mercury.com/blog/introducing-mercury-booksSoon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkeeping tasks end-to-end.
  • [probe] https://support.mercury.com/llms.txtPROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt
  • [probe] https://support.mercury.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.mercury.com/api/openapi.json, https://support.mercury.com/.well-known/openapi.json)

Drive the product through a documented public APIweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [claimed-docs] https://mercury.com/blog/introducing-mercury-booksSoon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkeeping tasks end-to-end.
  • [probe] https://support.mercury.com/llms.txtPROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt
  • [probe] https://support.mercury.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.mercury.com/api/openapi.json, https://support.mercury.com/.well-known/openapi.json)

Issue scoped/least-privilege API credentials for an agentweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://mercury.com/blog/introducing-mercury-booksSoon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkeeping tasks end-to-end.
  • [probe] https://support.mercury.com/llms.txtPROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt
  • [probe] https://support.mercury.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.mercury.com/api/openapi.json, https://support.mercury.com/.well-known/openapi.json)

Build against official SDKsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://mercury.com/blog/introducing-mercury-booksSoon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkeeping tasks end-to-end.
  • [probe] https://support.mercury.com/llms.txtPROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt
  • [probe] https://support.mercury.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.mercury.com/api/openapi.json, https://support.mercury.com/.well-known/openapi.json)

Subscribe to events via webhooksweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://mercury.com/blog/introducing-mercury-booksSoon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkeeping tasks end-to-end.
  • [probe] https://support.mercury.com/llms.txtPROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt
  • [probe] https://support.mercury.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.mercury.com/api/openapi.json, https://support.mercury.com/.well-known/openapi.json)

Agent-ready = 1.2 ÷ 210 × 100 = 0.6

API quality0.0/100×0.20 of the PA blend

The programmable surface once an agent is there — machine-readable spec, interactive docs, sandbox, versioning discipline.

Explore an interactive API reference with runnable examplesweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://mercury.com/blog/introducing-mercury-booksSoon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkeeping tasks end-to-end.
  • [probe] https://support.mercury.com/llms.txtPROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt
  • [probe] https://support.mercury.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.mercury.com/api/openapi.json, https://support.mercury.com/.well-known/openapi.json)

Download a machine-readable API spec (OpenAPI or equivalent)weight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://support.mercury.com/llms.txtPROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt
  • [probe] https://support.mercury.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.mercury.com/api/openapi.json, https://support.mercury.com/.well-known/openapi.json)
  • [claimed-docs] https://mercury.com/blog/introducing-mercury-booksSoon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkeeping tasks end-to-end.

Test against a sandbox environment without touching production dataweight 1

1 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 10 max

  • [claimed-docs] https://mercury.com/blog/introducing-mercury-booksSoon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkeeping tasks end-to-end.
  • [probe] https://support.mercury.com/llms.txtPROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt
  • [probe] https://support.mercury.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.mercury.com/api/openapi.json, https://support.mercury.com/.well-known/openapi.json)

Rely on versioned APIs with a documented deprecation policyweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://mercury.com/blog/introducing-mercury-booksSoon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkeeping tasks end-to-end.
  • [probe] https://support.mercury.com/llms.txtPROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt
  • [probe] https://support.mercury.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.mercury.com/api/openapi.json, https://support.mercury.com/.well-known/openapi.json)

API quality = 0.0 ÷ 70 × 100 = 0.0

Openness0.0/100×0.20 of the PA blend

Can you leave, inspect, or self-host — data export, open source, portability.

Do everything through the API that I can do in the UIweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://mercury.com/blog/introducing-mercury-booksSoon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkeeping tasks end-to-end.
  • [probe] https://support.mercury.com/llms.txtPROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt
  • [probe] https://support.mercury.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.mercury.com/api/openapi.json, https://support.mercury.com/.well-known/openapi.json)

Export all of my data in open formats and leaveweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [claimed-docs] https://mercury.com/booksDoes Mercury Books replace QuickBooks? Yes. Mercury Books is a complete accounting system — not an add-on or integration layer for another platform.
  • [probe] https://support.mercury.com/llms.txtPROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt
  • [probe] https://support.mercury.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.mercury.com/api/openapi.json, https://support.mercury.com/.well-known/openapi.json)

Read the product's source under an open licenseweight 2

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Self-host the core productweight 3

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Openness = 0.0 ÷ 50 × 100 = 0.0

Built-in AI61.1/100×0.15 of the PA blend

Inside-out: how agentic the product itself is for its users — built-in assistants, autonomous features.

Get AI-generated insights and suggestions from my data inside the productweight 2

2 (weight) × 7 (quality) × 1.0 (full) = 14.0 of 20 max

  • [claimed-docs] https://mercury.com/booksThe built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers grounded in your account data", and "Let Command clear the backlog — Offload work like writing journal entries, organizing your chart of accounts, categorization in bulk, and more."
  • [claimed-docs] https://mercury.com/blog/cleaner-books-without-the-busyworkThe banking side feeds clean data to any ledger: "Transactions on Mercury are now automatically assigned GL codes based on your categorization history and AI-driven suggestions", enriched integrations "sync attachments and notes for each transaction to your accounting software", and accountants can be invited so they "can look at transactions and categorizations and even tag you in comments on specific transactions".
  • [claimed-docs] https://mercury.com/blog/introducing-mercury-booksAsk Mercury Command a question about your books, or hand off a bookkeeping task to it directly, in plain language.
  • [claimed-docs] https://mercury.com/blog/bank-connected-bookkeepingMercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can eliminate a surprising amount of tedious financial admin, but there are still decisions software can't reliably make for you. So, think of it as giving whoever manages your books a much better starting point (and not as putting your books on autopilot)."

Set up automations that run autonomously in the backgroundweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [claimed-docs] https://mercury.com/booksReconciliation and categorization are automatic and continuous: "Data across banking, cards, invoicing, and more are categorized automatically as you run your business. Accounts reconcile in real time, always reflecting your company's reality, without manual work."
  • [claimed-docs] https://mercury.com/booksThe built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers grounded in your account data", and "Let Command clear the backlog — Offload work like writing journal entries, organizing your chart of accounts, categorization in bulk, and more."
  • [claimed-docs] https://mercury.com/accounting-integrationsUse Mercury Command to bulk assign GL codes, create categorization rules, and more
  • [claimed-docs] https://mercury.com/blog/bank-connected-bookkeepingMercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can eliminate a surprising amount of tedious financial admin, but there are still decisions software can't reliably make for you. So, think of it as giving whoever manages your books a much better starting point (and not as putting your books on autopilot)."
  • [claimed-docs] https://mercury.com/blog/introducing-mercury-booksSoon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkeeping tasks end-to-end.

Delegate tasks to a built-in AI assistant inside the productweight 3

3 (weight) × 7 (quality) × 1.0 (full) = 21.0 of 30 max

  • [claimed-docs] https://mercury.com/booksThe built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers grounded in your account data", and "Let Command clear the backlog — Offload work like writing journal entries, organizing your chart of accounts, categorization in bulk, and more."
  • [claimed-docs] https://mercury.com/blog/introducing-mercury-booksAsk Mercury Command a question about your books, or hand off a bookkeeping task to it directly, in plain language.
  • [claimed-docs] https://mercury.com/blog/introducing-mercury-booksFrom the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your business. Intelligence automatically categorizes and reconciles these entries in real time, erasing manual work before it lands on your to-do list... Your P&L, balance sheet, and cash flow statement are ready the moment you need them... AI built-in, not bolted on... Reconciliation is continuous and real time, ensuring nothing is ever missed."
  • [claimed-docs] https://mercury.com/blog/bank-connected-bookkeepingMercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can eliminate a surprising amount of tedious financial admin, but there are still decisions software can't reliably make for you. So, think of it as giving whoever manages your books a much better starting point (and not as putting your books on autopilot)."

Operate the product with natural-language commandsweight 2

2 (weight) × 7 (quality) × 1.0 (full) = 14.0 of 20 max

  • [claimed-docs] https://mercury.com/blog/introducing-mercury-booksAsk Mercury Command a question about your books, or hand off a bookkeeping task to it directly, in plain language.
  • [claimed-docs] https://mercury.com/booksThe built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers grounded in your account data", and "Let Command clear the backlog — Offload work like writing journal entries, organizing your chart of accounts, categorization in bulk, and more."
  • [claimed-docs] https://mercury.com/accounting-integrationsUse Mercury Command to bulk assign GL codes, create categorization rules, and more

Built-in AI = 55.0 ÷ 90 × 100 = 61.1

Automation20.3/100×0.15 of the PA blend

Depth of automation primitives — rules, scheduling, bulk operations, webhooks.

Perform bulk operations across many items at onceweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [claimed-docs] https://mercury.com/accounting-integrationsUse Mercury Command to bulk assign GL codes, create categorization rules, and more
  • [claimed-docs] https://mercury.com/booksThe built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers grounded in your account data", and "Let Command clear the backlog — Offload work like writing journal entries, organizing your chart of accounts, categorization in bulk, and more."
  • [claimed-docs] https://mercury.com/blog/introducing-mercury-booksSoon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkeeping tasks end-to-end.
  • [probe] https://support.mercury.com/llms.txtPROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt
  • [probe] https://support.mercury.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.mercury.com/api/openapi.json, https://support.mercury.com/.well-known/openapi.json)

Define rules that trigger actions automatically on eventsweight 3

3 (weight) × 5 (quality) × 0.6 (partial) = 9.0 of 30 max

  • [claimed-docs] https://mercury.com/accounting-integrationsUse Mercury Command to bulk assign GL codes, create categorization rules, and more
  • [claimed-docs] https://mercury.com/booksThe built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers grounded in your account data", and "Let Command clear the backlog — Offload work like writing journal entries, organizing your chart of accounts, categorization in bulk, and more."
  • [claimed-docs] https://mercury.com/blog/bank-connected-bookkeepingMercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can eliminate a surprising amount of tedious financial admin, but there are still decisions software can't reliably make for you. So, think of it as giving whoever manages your books a much better starting point (and not as putting your books on autopilot)."

Schedule recurring jobs or workflowsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://mercury.com/blog/introducing-mercury-booksSoon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkeeping tasks end-to-end.
  • [claimed-docs] https://mercury.com/booksThe built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers grounded in your account data", and "Let Command clear the backlog — Offload work like writing journal entries, organizing your chart of accounts, categorization in bulk, and more."
  • [probe] https://support.mercury.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.mercury.com/api/openapi.json, https://support.mercury.com/.well-known/openapi.json)

Version, review, and roll back my automationsweight 1

1 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 10 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Automation = 16.2 ÷ 80 × 100 = 20.3