# Fix list: QuickBooks Online API + MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/quickbooks-online, the October 2026 research run, assessed 1 October 2026. Grade D, 49.3 out of 100. This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public. For a coding agent working on QuickBooks Online API + MCP: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published. ## 1. Reliability, 45 out of 100, up to 11 more on the total Why it scored 45: Statuspage at status.developer.intuit.com with separate QuickBooks Online API, sandbox, OAuth, webhooks and Payments components (20). Several majors since July. API timeouts with OAuth and sandbox failures for about 7.75 hours on 1 September, TaxCode and TaxRate calls failing with error 4001 for about 9.75 hours on 22 and 23 September, login, connection and API problems for about 2.25 hours on 8 July, and a wide Intuit outage on 26 July (0). The limits page is inside a JavaScript portal that returns only a loading message to a fetch, so we couldn't read the numbers (0, unchecked). Intuit's developer blog (31 August 2026) says to retry only 5xx and 429, honour Retry-After, back off at 1, 2 and 4 seconds, and send a RequestId on writes so a repeat returns the original response instead of posting twice. The official Node client retries 408, 429 and 5xx the same way (15). No SLA found, unchecked for the same reason (0). GA (10). The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability): Hosted APIs, MCP servers, models and platforms. - 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own). - 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so. - 15, rate limits documented with numbers. - 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved. - 10, an SLA published for any paid tier. - 10, the surface agents use is generally available, not beta or preview. Local packages, SDKs, frameworks and stdio MCP servers. - 20, installs from an official package with supported runtimes stated. - 25, a public CI and test suite, passing on the default branch. - 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered). - 15, semver discipline and breaking changes called out in a changelog. - 15, version 1.0 or later, or declared stable. Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors. ## 2. Security & auth, 38 out of 100, up to 10.9 more on the total Why it scored 38: OAuth 2.0 with OpenID Connect, one-hour access tokens and rotating refresh tokens of about 101 days. The accounting scope is a single grant over the whole ledger, with no read-only scope (22). No read-only mode in the API. The official MCP can drop create, update and delete tools by flag (8). Returns the company's records with customer and vendor text and no injection guidance (3). No API audit view found. QuickBooks' own audit log wasn't checked (0, unchecked). security.intuit.com returns only a loading message and www.intuit.com/.well-known/security.txt answers 400, so we couldn't confirm a disclosure policy, bounty or certifications (5, unchecked). The checklist (https://www.anchorterminal.com/benchmark/#checklist-security): - 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option. - 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions. - 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10. - 0 to 15, audit logs or per-call visibility for the operator. - 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public. Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing. ## 3. Schema & documentation, 43 out of 100, up to 9.3 more on the total Why it scored 43: No OpenAPI spec found. Intuit's Java SDK repository publishes the V3 payload schemas as XSD, about 20,000 lines with some 200 complex types and about 110 simple types, many of them enums, last updated on 17 July 2026. They type every entity but don't describe endpoints, so part credit (10 of 25). No llms.txt or Markdown docs, and every developer docs page returns "Compiling and pre-filling your Intuit info..." to a plain fetch (0). The official MCP server's descriptions are one line, such as "Create an invoice in QuickBooks Online." (6). The XSDs carry enums such as TaxExcluded, TaxInclusive and NotApplicable, the MCP's Zod schemas use min and positive, and the Java, .NET and PHP SDKs are typed (12). The OAuth client documents its error codes. The API's own error and example pages couldn't be read (5). Minor versions (the Java SDK targets 75), with dated change announcements on Intuit's developer blog, such as the Project Management APIs on 13 May, a refresh-token expiry field on 5 June and Affirm and PayPal payments on invoices on 10 August 2026. The release notes in the portal couldn't be read (10). The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema): APIs and MCP servers. - 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool). - 10, llms.txt or Markdown docs served for agents. - 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference. - 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs. - 0 to 15, examples and documented error responses. - 15, versioning and a public changelog. Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference. ## 4. Payments & pricing, 30 out of 100, up to 8.8 more on the total Why it scored 30: No x402, MPP or L402 (0). QuickBooks Online plans are priced publicly in local currency on quickbooks.intuit.com. Intuit's partner tiers (the status page names Builder partners and partner tier subscriptions on 10 July 2026) and any metering of API calls are inside the portal, so we scored plan-only (10). Free sandbox companies with a developer account, no card per the 30 September check (20). Browser signup, app registration and an OAuth consent in a browser (0). The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments): The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/). - 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which. - 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login. - 20, a free tier or trial that doesn't need a card. - 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API). Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied. Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol. ## 5. Agent ergonomics, 68 out of 100, up to 5.2 more on the total Why it scored 68: The query endpoint takes where clauses with STARTPOSITION and MAXRESULTS, so reads can be cut down server-side. The official MCP loads 145 tools, with DISABLE_WRITE, DISABLE_UPDATE and DISABLE_DELETE flags to drop whole groups (15). Query filtering and paging on every entity, plus reports with date parameters (18). Fault responses carry numbered codes such as 4001, though the catalogue sits in the unreadable portal (10). Intuit's developer blog documents RequestId as the idempotency mechanism (a repeat returns the original response), and the Java SDK sends one with each call. The MCP sets no readOnlyHint or destructiveHint (10). Official SDKs for Java, .NET and PHP and OAuth clients for Node and Python (15). The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics): - 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries). - 20, pagination, filtering and output-size controls. - 20, actionable, documented error responses, codes and messages an agent can recover from. - 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations. - 15, sensible defaults, few required parameters, and official SDKs in at least two languages. Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs. ## 6. Transparency & trust, 51 out of 100, up to 4.3 more on the total Made of editorial 22, provenance 80. Why it scored 51: Closed API. The linked terms are Intuit's general terms, since the developer terms sit in the portal. The MCP and OAuth clients are MIT and Apache-2.0 (12). Privacy statement updated 9 March 2026 per the 30 September check. Retention and the developer data terms couldn't be read (10). Minor-version deprecation rules are in the portal (0, unchecked). Subprocessors and data locations not found (0). The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency): - 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms. - 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors). - 0 to 20, a deprecation policy or notices with dates. - 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted). The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two. Provenance checks not met in full (half of this category, computed from checked facts): - Changelog: not found (0 of 10) - security.txt: could not be fetched (0 of 10) ## 7. Maintenance & community, 85 out of 100, up to 1.3 more on the total Why it scored 85: The .NET SDK's V14.7.1.6 was tagged on 17 September 2026 and is on NuGet, 15 days before the check (30). In the last 90 days, intuit-oauth 4.2.5 (15 July), PHP SDK v6.2.5 and v6.3.1 (15 and 17 July), Java SDK v6.5.5 (17 July) and v6.6.3 (3 August), and .NET V14.7.1.5 (16 July) and V14.7.1.6 (20). The official MCP repository merged five community pull requests on 15 September. Intuit's developer blog posts dated API changes. API release notes and the developer forum couldn't be read (12). Official SDKs in Java, .NET and PHP and OAuth clients for Node and Python, all released since July. The MCP isn't in the official registry (15). The MCP's CI builds, lints and tests on Ubuntu and Windows, with a dependency audit workflow (8). The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance): - 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older. - 20, at least three releases or dated changelog entries in the last 90 days. - 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15. - 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models). - 10, package health, current dependencies and CI. Models are read for deprecation notice periods and model churn rather than release counts. ## What we couldn't check What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it. - unchecked: rate limits, concurrency and batch limits (portal is JavaScript-only, and Intuit's 31 August retry post gives no numbers) - unchecked: partner tier prices and whether API reads are metered. The developer blog names a Silver tier that unlocks some APIs but gives no prices - unchecked: developer terms, minor-version deprecation policy and any SLA - unchecked: Intuit's disclosure policy, bug bounty and certifications. www.intuit.com/.well-known/security.txt timed out twice on 2 October after a 400 on 1 October, and no SECURITY.md in Intuit's QuickBooks repositories - Whether QuickBooks' audit log records API changes by app - The listing said there was no official MCP server. Intuit's own repository has one, so the patch adds it ## Weaknesses - Rate limits, developer terms, partner tiers and deprecation rules are behind a JavaScript portal that returns nothing to a plain fetch - No OpenAPI spec and no llms.txt. The only machine-readable schemas are XSDs in the Java SDK - One accounting scope covers the whole ledger, with no read-only grant - Four API-affecting outages between 8 July and 23 September 2026, two over seven hours - The official MCP isn't on npm or in the registry and sets no tool annotations ## What costs an agent a turn today The notes we give agents before they call it. Each one is a workaround an agent shouldn't need. - Store the realmId with the tokens. Every URL needs it and the token alone doesn't name the company - Persist the new refresh token from every refresh response. The previous one expires 24 hours later - Use the query endpoint with MAXRESULTS and STARTPOSITION for reads rather than fetching by id - Send a unique `requestid` query parameter on writes, so a retry returns the first response instead of posting twice - On 429, wait for Retry-After before retrying, and don't retry other 4xx errors ## What the review panel asked for - serve docs as plain HTML or Markdown - add annotations to MCP tools - read-only accounting scope - security.txt that answers ## When it's done Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.