Close API + MCP by Close

# Fix list: Close API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/close, the October 2026 research run, assessed 1 October 2026. Grade B, 66.9 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 Close 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). Plan prices public, Solo $9 a seat a month yearly or $19 monthly up to Scale $139 or $149, with calls at about $0.02 a minute passed through at cost, but nothing per API call (10). 14-day trial with no card (20). A person signs up 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.

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

Why it scored 56: 121 MCP tools, 71 read, 16 safe-write and 34 destructive (5). Choosing a scope per connection cuts the list to 71 read tools or 87 with creates (5 more, 10 of 25). Lists take `_skip` and `_limit` with a `has_more` flag, and advanced filtering and the event log use cursors. No field selection found (16 of 20). Documented response codes, and 429s say how long to wait (13 of 20). No idempotency keys. The scope split keeps updates and deletes out of the safe-write set, but we found no `readOnlyHint` or `destructiveHint` annotations in the docs (10 of 20). The only official client is the Python `closeio` wrapper, last tagged v2.1 in July 2023 (7 of 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.

## 3. Security & auth, 66 out of 100, up to 6 more on the total

Why it scored 66: REST keys act as one user in one organisation over HTTP Basic and can be deleted. OAuth for apps has only `all.full_access` plus `offline_access`, with 1-hour access tokens and a revoke endpoint. The MCP server adds three scopes, `mcp.read`, `mcp.write_safe` and `mcp.write_destructive`, over OAuth with dynamic client registration or a key header (24 of 30). A read-only MCP connection is one header. Safe-write can create but not update or delete. Email tools only make drafts a person sends, and delete tools tell the model to act only on an explicit instruction (18 of 20). The MCP server reads emails, SMS and call transcripts written by outsiders, and we found no injection guidance. Draft-only email closes one exfiltration route (4 of 15). The event log API records changes and is on every plan (12 of 15). SOC 2 Type 2 on the security page. No security.txt (404), and no disclosure policy or bug bounty found (8 of 20).

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. Reliability, 81 out of 100, up to 3.8 more on the total

Why it scored 81: Status page at status.close.com with history back to February 2025 (20). Nothing logged since 3 July 2026. The last incident, background tasks delayed for about 2 hours on 29 June, falls just outside the 90 days (30). Limits are set per endpoint group, per key and per organisation (3 times the key limit), but the docs only give 20 a second as an example rather than a table (10 of 15). Every response carries a `RateLimit` header, and every 429 has both `RateLimit` and `retry-after`, with guidance to sleep for the reset value. No idempotency keys or safe-retry guidance for writes (11 of 15). No SLA found on the pricing page (0). REST and MCP carry no beta label (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.

## 5. Schema & documentation, 82 out of 100, up to 2.9 more on the total

Why it scored 82: OpenAPI spec published on 6 April 2026, still marked experimental and not covering every schema (20 of 25). llms.txt with about 450 links and Markdown copies of pages, including a changelog llms.txt (10). MCP tool descriptions say when not to call them. Delete tools read 'This action cannot be undone. ONLY call this if the user specifically instructed you to delete', and the email tool says it saves an unsent draft (16 of 20). Typed parameters in the reference, with free-form smart-view queries for search (11 of 15). Examples throughout and an HTTP response codes page (12 of 15). Dated changelog with deprecations marked (2026-03-06, 2026-07-21), on a single v1 path (13 of 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.

## 6. Transparency & trust, 69 out of 100, up to 2.7 more on the total

Made of editorial 47, provenance 90.

Why it scored 69: Closed service with terms and a privacy policy, run by Elastic Inc (15). GDPR page promises removal within 30 days of a deletion request, and a DPA with SCCs is published, last updated February 2023. Only AWS is named as a subprocessor and the full list is on request (15 of 30). Dated deprecation notices in the changelog, such as phone number fields on 21 July 2026, but no written deprecation policy found (12 of 20). No public subprocessor list or hosting region found (5 of 20).

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):

- security.txt: not found (0 of 10)

## 7. Maintenance & community, 79 out of 100, up to 1.8 more on the total

Why it scored 79: Newest changelog entry on 2026-09-10 (30). Three dated entries since 3 July 2026, on 16 July, 21 July and 10 September (20). Public changelog and support by email and phone. We didn't test support (10 of 15). In the official MCP registry as com.close/close-mcp, last version 1.0.1 published on 22 September 2025 (15). The Python client's last tag is v2.1 from July 2023, though its CI was updated in June 2026 (4 of 10).

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: whether the MCP tools carry readOnlyHint or destructiveHint annotations
- Published per-endpoint-group rate limit numbers, since the docs only give an example
- Which plan, if any, is needed for the MCP server, since the MCP docs don't say

## Weaknesses

- 121 MCP tools, and even the read scope loads 71
- OAuth for REST apps has a single full-access scope
- No public subprocessor list, no security.txt and no bug bounty found
- OpenAPI spec is marked experimental and incomplete
- No free plan, 14-day trial only

## 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.

- Connect with `Close-Scope: mcp.read` unless the job needs writes, and `mcp.write_safe` if it only creates
- Sleep for the `reset` value in the `RateLimit` header after a 429, which the docs say beats `retry-after`
- Use cursors through advanced filtering or the event log for large pulls, since `_skip` has a per-resource ceiling
- Search the lead before `create_lead`, because there's no idempotency key and a retry makes a duplicate
- Expect `create_draft_email` to leave a draft, and tell the user to send it from Close

## What the review panel asked for

- publish tool annotations
- finish the OpenAPI spec
- narrower REST OAuth scopes
- a disclosure policy

## 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.