Calendly API + MCP by Calendly

# Fix list: Calendly API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/calendly, the October 2026 research run, assessed 1 October 2026. Grade B, 68.4 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 Calendly 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. 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 public ($10 and $16 a seat a month, Enterprise from $15,000 a year) but nothing per call (10). Free plan with API read access and no card, though booking through the API needs a paid seat (20). A person signs up and consents in a browser, even though MCP clients register themselves (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, 61 out of 100, up to 6.3 more on the total

Why it scored 61: 36 MCP tools (5), with 5 back for two skill tools that load task guidance on demand and 2 for `count` on REST lists (12). `next_page` pagination and time and status filters on scheduled events (17). Error codes in the spec, and Free users get a clear 403 on booking (15). MCP tools carry readOnlyHint, destructiveHint and idempotentHint, but the REST booking call has no idempotency key (12). No official SDK, and the user URI from /users/me is needed before most calls (5).

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. Security & auth, 70 out of 100, up to 5.3 more on the total

Why it scored 70: OAuth 2.1 with PKCE and dynamic client registration on the MCP, and per-resource scopes such as `scheduled_events:read` and `availability:write` for new OAuth apps and new personal access tokens since March 2026. Tokens issued before scopes keep full access (28). Read scopes, `mcp:scheduling:read` and `mcp:scheduling:write` for the MCP, and destructiveHint on cancel, delete and revoke tools, but no confirmation step of its own (15). Invitee names and booking answers written by outsiders reach the model, with no injection guidance found (0). `activity_log:read` and audit logs on Enterprise (10). SOC 2 Type 2, ISO 27001, CSA STAR, an annual penetration test and a valid security.txt. No public bug bounty found (17).

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, 50 out of 100, up to 4.4 more on the total

Why it scored 50: Latest release note on 25 August 2026, 37 days before this check (20). Three dated entries since 3 July (9 July, 22 July, 25 August) (20). Public release notes and a developer support route, no public issue tracker (10). No official SDKs (0). No package to assess (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.

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

Why it scored 85: incident.io status page with separate Calendly API and Webhooks components, plus each calendar provider (20). The page shows 100% uptime for the API and Webhooks components and no incidents. We couldn't open a separate history page (/history returns 404), so this rests on the page's own uptime bars (30). 500 requests a minute per user on paid plans, 50 on Free, and booking capped at 10 a minute, 50 an hour and 100 a day below Enterprise (15). 429 with X-RateLimit-Limit, -Remaining and -Reset headers and exponential backoff advice, but no idempotency key or safe-retry guidance for booking writes (10). No SLA found on any plan (0). 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.

## 6. Schema & documentation, 86 out of 100, up to 2.3 more on the total

Why it scored 86: OpenAPI 3.1 for the scheduling API and a separate one for OAuth, in JSON and YAML (25). llms.txt with about 130 links and Markdown copies of every docs page (10). Reference pages and MCP tool docs mark plan requirements such as paid plan for booking and Teams for routing forms (14). Typed parameters in the spec (12). 400, 401, 403, 404, 409, 424 and 500 responses in the spec, but no 429 (12). Dated release notes, latest 25 August 2026. The API version only changes by migration, the last one being v1 to v2 (13).

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 service with customer terms and a separate developer policy (15). Privacy notice (3 July 2026) gives no retention periods, and the no-AI-training statement sits on the security page, not in the privacy notice (18). The v1 to v2 migration notice is dated 26 March 2025 and legacy token behaviour under scopes is written down (12). Sub-processor list linked from the privacy notice, which says data sits in the US or wherever providers operate. We didn't open the list (16).

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.

- Incident history beyond the status page's 100% component bars
- Whether any paid tier has an SLA
- Whether POST /invitees deduplicates a repeated request
- unchecked: sub-processor list and data locations

## Weaknesses

- Booking through the API needs a paid seat, and Free users get a 403
- Booking limited to 10 a minute, 50 an hour and 100 a day per user below Enterprise
- No idempotency key on POST /invitees
- No official SDK
- Tokens issued before scoped permissions keep full access

## 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.

- Resolve the user's URI with GET /users/me before listing event types or busy times
- Pass `start_time` in UTC and the invitee's `timezone` when calling POST /invitees
- List the invitee's scheduled events before retrying a booking, since there's no idempotency key
- Read `X-RateLimit-Reset` on 429 and wait that many seconds
- Use a client with dynamic client registration for mcp.calendly.com, since it has no static client ID

## What the review panel asked for

- Idempotency key on invitees
- Readable incident history
- expire pre-scope tokens
- audit log below Enterprise

## 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.