TheFork B2B API

# Fix list: TheFork B2B API

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/thefork, the October 2026 research run, assessed 14 October 2026. Grade E, 43.6 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 TheFork B2B 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. Reliability, 35 out of 100, up to 13 more on the total

Why it scored 35: Graded as a hosted API. status.thefork.io redirects to a private Rootly page behind a sign-in, so there is no public status page (0) and no readable history (5). The docs leave the rate limit to each contract. The Partners API terms set 200 calls a minute and 10,000 a day by default, which we take as published numbers for part of the line (8 of 15). 429 and 503 call for exponential backoff, and the llms.txt says to check the current state before retrying a POST or PATCH, but no idempotency key exists (12 of 15). No SLA, and the terms disclaim uptime (0). v1 is generally available (10). Total 35.

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. Payments & pricing, 5 out of 100, up to 11.9 more on the total

Why it scored 5: No x402, MPP or L402 (0). No API prices published (0). The API terms mention test data before launch, but no sandbox host or free tier is documented, and both follow approval (5 of 20). A person emails the integrations team and TheFork sends credentials (0). Total 5.

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. Security & auth, 42 out of 100, up to 10.1 more on the total

Why it scored 42: OAuth 2.0 client credentials with nine scopes in the schema, from full access down to read-only availability. The secret is delivered through a secure channel. No rotation procedure was found (25 of 30). Read-only scopes exist, and tfm-restaurant:unrestricted-reservations, which books outside published slots, is not granted by default (14 of 20). Responses carry review text and customer data written by people, and the best-practices page covers input sanitisation but not untrusted output (3). No audit log or per-call view found (0). www.thefork.com/.well-known/security.txt returns 404, the main site answered with a bot check, and no SOC 2, ISO 27001 or disclosure programme was found in the developer portal (0). Total 42.

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.

## 4. Maintenance & community, 15 out of 100, up to 7.4 more on the total

Why it scored 15: No changelog or dated release notes. The developer portal files, including the llms.txt, carry a Last-Modified date of 5 October 2026, which shows a recent docs deployment but not what changed, so it earns part of the line (10 of 30). No three dated changes in 90 days (0). An integrations email address, no public issue tracker or community channel (5 of 15). No official SDKs (0). No package to assess (0). Total 15.

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.

## 5. Agent ergonomics, 56 out of 100, up to 7.2 more on the total

Why it scored 56: List endpoints return UUIDs only and need one detail call per item, which keeps lists small but multiplies calls. No field selection (12 of 25). page and limit with totalCount or hasNext, and date filters on every list (16). Business codes in data.code (NO_AVAILABILITY, DOUBLE_BOOKING, PAYMENT_GUARANTEE_NOT_SUPPORTED), but gateway errors carry only a message and three formats must be parsed (15). No idempotency key. 409 DOUBLE_BOOKING and DOUBLE_CANCELLATION catch repeats, and the docs say to check state before retrying writes (8 of 20). No SDKs, five required customer fields, and restaurant UUIDs must come from TheFork because no endpoint lists them (5). Total 56.

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, 47 out of 100, up to 4.6 more on the total

Made of editorial 33, provenance 60.

Why it scored 47: Closed service. The Partners API terms are a public PDF naming La Fourchette SAS, though they describe an affiliate Partners API and defer to any core agreement (15 of 30). The terms cover data ownership and credential use. The privacy policy on www.thefork.com was behind a bot check, so retention and processing statements were unread (3 of 30). A written versioning policy with 6 months' support for the previous version, without dated notices (15 of 20). No subprocessor list or data locations found (0). Total 33.

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):

- Privacy policy: not found (0 of 10)
- Status page: not found (0 of 10)
- Changelog: not found (0 of 10)
- security.txt: not found (0 of 10)

## 7. Schema & documentation, 87 out of 100, up to 2.1 more on the total

Why it scored 87: OpenAPI 3.1.0 schema at api.thefork.io/manager/openapi.json, generated from the deployed code, with 19 operations and the scopes (25). A B2B llms.txt written for agents (10). Every operation has a description, and the llms.txt says when to use each and which pages to ignore, though per-endpoint when-not-to-use guidance is thin (16 of 20). 319 enums and required fields across the schema, with the E.164 phone pattern stated (14 of 15). 272 examples, error responses on every operation and three error formats explained (14 of 15). One version in the path with a written policy of 6 months' support after a breaking change, but no changelog (8 of 15). Total 87.

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.

## 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: www.thefork.com answered every request with a bot check (403), so its privacy policy, terms of use and any security or disclosure page were not read
- unchecked: TheFork's status history, which sits on a private Rootly status page
- Whether a sandbox exists for the B2B API. The terms mention test data, but no sandbox host is documented
- Whether the Partners API terms PDF, written for affiliate partners, is the licence for the B2B API. The portal footer links it as the terms of use
- Whether client secrets can be rotated on request

## Weaknesses

- Venue-side only. Credentials cover the restaurants that granted access, and no endpoint lists restaurants
- Credentials come from the integrations team by email after approval, with no self-serve route
- Timeslots that need a payment guarantee cannot be booked through the API
- The status page at status.thefork.io redirects to a private Rootly page that needs a sign-in
- No changelog, idempotency key or published production rate limit

## 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.

- Read hasPaymentGuaranteeRequirement in the timeslots response before booking, since the API cannot take a card
- Check the status field after creating a reservation and treat REQUESTED as unconfirmed
- Send the timeslot datetime unchanged as mealDate, because times are the restaurant's local time
- Check for an existing reservation before retrying a failed POST, as no idempotency key exists and 409 signals DOUBLE_BOOKING
- Cache the access token for its 8,600 seconds and do not request a new one while it is valid

## 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.