FreeAgent API by FreeAgent

# Fix list: FreeAgent API

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/freeagent, the October 2026 research run, assessed 1 October 2026. Grade C, 57.6 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 FreeAgent API: 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. Security & auth, 44 out of 100, up to 9.8 more on the total

Why it scored 44: OAuth 2.0 authorisation code, one-hour access tokens, refresh tokens that rotate on each refresh, and a client secret rotation guide. No scopes, so a token can do whatever the authorising user can (22). No read-only mode. Invoices are drafts until a transition endpoint marks them sent, which works as a confirmation step (5). Returns the business's own records plus bank descriptions and contact text from third parties, with no injection guidance (3). No per-app audit log or API activity view found (0). Valid security.txt to April 2027, a disclosure policy with discretionary rewards and Cyber Essentials Plus. No ISO 27001 or SOC 2 found (14).

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.

## 2. Payments & pricing, 30 out of 100, up to 8.8 more on the total

Why it scored 30: No x402, MPP or L402 (0). The API is free under section 4.1 of the terms with 30 days' notice before any fee, and a live company needs a subscription with public prices (£33 a month for a limited company, half for the first six months). We scored it as plan-only pricing (10). Free sandbox account at signup.sandbox.freeagent.com and a 30-day product trial (20). Browser signup and a developer app registration (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.

## 3. Schema & documentation, 50 out of 100, up to 8.1 more on the total

Why it scored 50: No OpenAPI or other machine-readable spec (0). No llms.txt or Markdown docs. The HTML is server-rendered and reads cleanly to a plain fetch, which the checklist doesn't score (0). Each resource page explains purpose and workflow, such as invoices created as drafts and moved by transition endpoints (14). Attribute tables give types, required markers and enums such as invoice status values (12). JSON and XML request and response examples on every page, but no error body format or error catalogue (9). Dated API changelog and a versioning guide (15).

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. Agent ergonomics, 55 out of 100, up to 7.3 more on the total

Why it scored 55: Responses sized by per_page (default 25, maximum 100), view filters such as open, overdue and last_N_months, and nested items off unless asked. No field selection (15). Link headers for prev, next, first and last, X-Total-Count, updated_since and sort (20). Only the 429 path is documented, not the error bodies an agent has to recover from (8). No idempotency keys or safe-retry guidance. Invoices start as drafts, which makes a duplicate visible before it goes out (5). Defaults are sensible, but there's no official SDK in any language (7).

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.

## 5. Maintenance & community, 60 out of 100, up to 3.5 more on the total

Why it scored 60: Last dated API change on 1 September 2026, bank transaction explanation attachments (30). Four dated entries since 3 July (3 July, 17 August, 20 August, 1 September) (20). Closed service with a public changelog and a developer discussion group at api-discuss.freeagent.com that isn't official support (10). No official SDKs and no MCP server (0). No packages to judge (0).

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.

## 6. Reliability, 85 out of 100, up to 3 more on the total

Why it scored 85: Statuspage at status.freeagent.com with history back to September 2024 (20). Nothing since the scheduled database maintenance on 17 June, so the 90 days to 1 October are clean (30). 120 requests a minute and 3,600 an hour per user, plus 15 token refreshes a minute (15). 429 with Retry-After 60, and an X-RateLimit-Test header that drops the sandbox to 5 a minute so a client can rehearse the back-off. No guidance on retrying writes (10). No SLA found (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.

## 7. Transparency & trust, 78 out of 100, up to 1.9 more on the total

Made of editorial 55, provenance 100.

Why it scored 78: Closed service with API terms v2.1 dated 28 February 2025, under Scots law, naming FreeAgent Central Limited, SC316774 (15). A privacy hub with a general notice, a customer DPA, a subprocessor list and a GDPR page, and API terms that bar clients from keeping data longer than the feature needs. The landing page gives no retention periods (20). Dated changelog and a versioning guide, and the terms promise email notice of material changes but set no deprecation period (8). Subprocessor list published. We didn't read the locations (12).

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.

## 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.

- Whether a user can see or revoke an app's access from inside FreeAgent, and whether API calls are logged anywhere the user can see
- Retention periods and data locations in the general privacy notice and subprocessor list
- The error body format for 4xx responses other than 429
- Whether the community MCP server io.github.OxygenBubbles/freeagent-mcp-server is still maintained (not rechecked)

## Weaknesses

- No OAuth scopes, so a token can do anything the authorising user can
- No OpenAPI spec, SDK, llms.txt or official MCP server
- Error responses aren't documented beyond the 429
- UK only, so VAT, MTD and HMRC filings are the tax model
- API terms bar migrating data to a competitor and using the API for benchmarking or comparison

## 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 new refresh token from every refresh response. The old one stops working
- Create the invoice, then PUT /v2/invoices/:id/transitions/mark_as_sent. A draft isn't visible to the customer
- Record a customer payment by explaining the bank transaction against the invoice. There's no invoice payments endpoint
- Send X-RateLimit-Test: true in the sandbox to see the 429 and Retry-After path before production does it to you
- Use view= and updated_since= on list calls and per_page up to 100 to stay under 120 requests a minute

## What the review panel asked for

- publish an OpenAPI spec
- document 4xx error bodies
- read-only OAuth scopes
- per-app activity log

## 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.