Linear MCP by Linear

# Fix list: Linear MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/linear-mcp, the October 2026 research run, assessed 1 October 2026. Grade C, 54 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 Linear 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. Agent ergonomics, 38 out of 100, up to 10.1 more on the total

Why it scored 38: Tool count not published and not countable without a workspace sign-in, so we scored context cost as unknown (5), plus a read-only endpoint that exposes only read tools (7). Pagination and filters likely exist on list tools but we couldn't see them (8). No documented error responses for MCP calls (3). The read-only endpoint is safe by construction, and we couldn't check readOnlyHint or destructiveHint (8). One URL with OAuth or a Bearer key, and an official SDK in TypeScript only (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.

## 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). No separate MCP charge, and Linear's plan prices are public (10). Linear's Free plan needs no card and the MCP docs state no plan restriction (20). A person signs in through OAuth or creates an API key in the app (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. Reliability, 60 out of 100, up to 8 more on the total

Why it scored 60: incident.io status page at linearstatus.com with US and EU components for the app, API and integrations and an RSS history, but no MCP component (15). Minor incidents only in the last 90 days, slow loading on 16 July, the docs site on 12 August, Codex sessions on 14 August and agent automation delays on 19 August 2026 (20). The GraphQL API publishes limits, 2,500 requests an hour per user on an API key and 5,000 on OAuth, but the MCP docs don't say whether these apply (10). A rate-limited call comes back as HTTP 400 with code RATELIMITED and reset headers, with no Retry-After or backoff guidance (5). No SLA found (0). The MCP server has been out of beta since its May 2025 launch and the docs carry no preview 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.

## 4. Schema & documentation, 51 out of 100, up to 8 more on the total

Why it scored 51: Tools carry JSON Schema by protocol, but Linear doesn't publish the tool list or schemas and we couldn't read them without signing in to a workspace (15). llms.txt with links to .md pages, including the MCP page (10). Descriptions not readable from public sources (5). Input typing not verifiable (5). The docs have a troubleshooting section for auth and transport but no tool examples or error responses (4). Registry versions (1.0.1 on 4 August 2026) and MCP changes logged in the main product changelog, with no version on the tool surface itself (12).

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.

## 5. Security & auth, 71 out of 100, up to 5.1 more on the total

Why it scored 71: OAuth 2.1 with dynamic client registration and a `read` scope that, in Linear's words, means the token can't reach write APIs, or API keys that can be created with Read permission only, sent in the `Authorization` header (30). A read-only endpoint plus read-only keys and scopes, but no confirmation step for writes on the full endpoint (16). Tools return issue and comment text written by anyone in the workspace, and we found no prompt-injection guidance (3). Workspace audit logs cover the last 3 months and admins can see active MCP connections, but we found no per-call MCP log (8). SOC 2 Type II and ISO 27001:2022 on the security page, security.txt valid per the 26 September check, no bug bounty 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.

## 6. Maintenance & community, 57 out of 100, up to 3.8 more on the total

Why it scored 57: Last MCP change in the changelog on 13 August 2026 (enterprise-managed authorisation through Okta), 49 days before the run date (20). Two MCP-related dated entries in the last 90 days, the registry update of 4 August and the 13 August entry, with the 2 July batch of new tools just outside the window (7). Closed service with a public changelog and in-app support, no public issue tracker for the MCP server (10). Registered as app.linear/linear 1.0.1 in the official MCP registry (15). No package to install, and we didn't check the TypeScript SDK's health in this run (5).

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.

## 7. Transparency & trust, 73 out of 100, up to 2.4 more on the total

Made of editorial 50, provenance 96.

Why it scored 73: Closed service under Linear's terms (15). The privacy policy of 17 March 2025 says the services are hosted in the United States, while the security page says a workspace can choose EU or US storage, and retention is "as long as you have an open account" (15). The SSE endpoint is called a deprecated fallback with no end date (8). A DPA at linear.app/dpa and EU or US hosting stated, subprocessor list not checked in this run (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.

Provenance checks not met in full (half of this category, computed from checked facts):

- Domain age: linear.app, registered 2018-05-09 (8 years) (11 of 15)

## 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.

- The tool list, tool count and input schemas, which Linear doesn't publish and we couldn't read without a workspace sign-in.
- Whether MCP calls share the GraphQL API rate limits and what the MCP server returns when limited.
- Whether workspace audit logs record individual MCP tool calls.
- Whether the SSE endpoint has a shutdown date.
- unchecked: the Linear subprocessor list and DPA contents.

## Weaknesses

- No published tool list, schemas or MCP error responses
- No MCP component on linearstatus.com
- Rate limits are documented for the GraphQL API only, and a limit returns HTTP 400 rather than 429
- The privacy policy (March 2025) says US hosting while the security page lets a workspace choose EU or US
- SSE endpoint deprecated with no end date

## 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.

- Use `https://mcp.linear.app/mcp/readonly` for triage and reporting, it only exposes read tools
- Headless runs take `Authorization: Bearer <API key>`, and a key created with Read permission can't write
- Treat an HTTP 400 with RATELIMITED as a rate limit and wait for the X-RateLimit-Requests-Reset time
- Call `list_teams` first, since team visibility and retired teams come back in its output

## What the review panel asked for

- Publish the tool list and schemas
- Document MCP errors
- published tool annotations
- per-call MCP audit

## 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.