# Fix list: Cal.com API v2 + MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/cal-com, the October 2026 research run, assessed 1 October 2026. Grade C, 57.5 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 Cal.com API v2 + 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. Payments & pricing, 30 out of 100, up to 8.8 more on the total Why it scored 30: No x402, MPP or L402 (0). Seat prices published ($12 and $28 a user a month billed yearly) but nothing per call or per booking (10). Free plan for one user with API access, no card (20). Browser signup, and OAuth clients need admin approval (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. ## 2. Agent ergonomics, 50 out of 100, up to 8.1 more on the total Why it scored 50: 63 tools on the hosted MCP (5), with a `toolsets` query parameter to load only the groups you need and catalogue meta-tools (find, describe and call an API operation) (+10). Cursor pagination with `limit`, and filters on status, attendee, event type, team and start, end, created and updated times (20). Error envelope without documented codes (8). No idempotency key on bookings found, and we couldn't read the hosted tools for readOnlyHint or destructiveHint (0). No official REST SDK in two languages (Atoms is React components), and every endpoint needs the right version header (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. ## 3. Reliability, 60 out of 100, up to 8 more on the total Why it scored 60: OpenStatus page at status.cal.com with App, Website and API components and an events log back to February 2024 (20). In the last 90 days, a major API outage on 31 August (1 hour 14 minutes of HTTP 500s on /v2/slots and /v2/bookings in US East), a 1 hour 19 minute degradation of App and API on 15 September, and a partial outage of the Atoms endpoint on 21 July (10). 120 requests a minute per key or OAuth token, raisable to 200 and then to 800 on request (15). No 429 behaviour, rate-limit headers or retry guidance in the docs or the OpenAPI spec (0). Enterprise lists "SLA guarantees" with no published figure (5). API v2 is 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. ## 4. Security & auth, 56 out of 100, up to 7.7 more on the total Why it scored 56: OAuth with per-resource READ and WRITE scopes at user, team and organisation level, 30-minute access tokens, PKCE, and client secret rotation with two active secrets. OAuth clients are reviewed before use. API keys have test and live prefixes but no scopes (28). Read-only OAuth scopes and MCP toolsets narrow access, but nothing asks for confirmation before `delete_event_type`, `cancel_booking` or `delete_org_membership` (10). Bookings carry attendee-written names and notes into the model, with no injection guidance found (0). No operator request log found (0). ISO 27001, SOC 2 Type II and HIPAA claimed, an annual third-party penetration test, a Bugcrowd disclosure programme and a valid security.txt, though it points to the repository that now hosts the Cal.diy fork (18). 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. ## 5. Maintenance & community, 50 out of 100, up to 4.4 more on the total Why it scored 50: v6.9 changelog post on 15 September 2026 (30). Only one dated changelog post found between June and September, so partial credit (5). Public blog changelog and support, no public issue tracker for the closed product (10). No current official REST SDKs, and the npm MCP package has sat at 0.0.6 since 22 May 2025 (5). The cal-mcp repository's test workflow has its test step commented out (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. Schema & documentation, 76 out of 100, up to 3.9 more on the total Why it scored 76: OpenAPI 3.0 document for API v2 (25). llms.txt and Markdown copies of reference pages (10). Reference pages explain each endpoint and parameter, but the hosted MCP's tool descriptions aren't public since the code went closed (12). Typed parameters with ranges, such as `limit` 1 to 100 with a default of 50 and enumerated booking statuses (12). Examples on reference pages. The response envelope has `status` success or error, but we found no error catalogue (8). Date-based `cal-api-version` per endpoint (2026-05-01 for bookings, 2024-09-04 for slots), and release notes come as blog posts rather than an API changelog (9). 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. ## 7. Transparency & trust, 81 out of 100, up to 1.7 more on the total Made of editorial 61, provenance 100. Why it scored 81: Closed source since 14 April 2026, with terms that carry a 2021 effective date and name UK law for a San Francisco company. The security page still describes a self-hosted open-source option, which now means the Cal.diy community fork (12). Privacy policy (20 August 2026) says nothing is used to train models, account data is kept while active with a 30-day export window after closure, and logs exclude personal data. DPA in the compliance portal (22). Platform deprecation dated 15 December 2025 and date-pinned API versions (14). Subprocessors are listed in the trust centre per the privacy policy, which we didn't open, and data sits in the US with EU residency on request (13). 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 the hosted MCP tools carry readOnlyHint or destructiveHint, since the source isn't public - Which OAuth scopes the hosted MCP requests - unchecked: the subprocessor list in the trust centre - Whether changelog posts between v6.9 and earlier releases exist outside the blog index we saw - Enterprise SLA figure ## Weaknesses - API outage of 1 hour 14 minutes on 31 August 2026, with HTTP 500s on slots and bookings - 120 requests a minute by default and no documented 429 or retry behaviour - Closed source since April 2026, and the npm MCP package hasn't changed since May 2025 - No idempotency key on booking creation - Plain API keys can't be scoped ## 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. - Send `cal-api-version: 2026-05-01` on bookings and `2024-09-04` on slots, since each endpoint pins its own version - Append `?toolsets=bookings,availability` to the hosted MCP URL to skip the other 50-odd tools - Page bookings with `pagination.nextCursor`, not offsets - Check for an existing booking before retrying a create, since there's no idempotency key - Use `cal_` test keys while building so bookings don't reach real calendars ## What the review panel asked for - Idempotency key on bookings - Documented 429 handling - scoped API keys - publish MCP annotations ## 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.