n8n API + MCP by n8n

# Fix list: n8n API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/n8n, the October 2026 research run, assessed 1 October 2026. Grade D, 53.3 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 n8n 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. Reliability, 40 out of 100, up to 12 more on the total

Why it scored 40: Status page at status.n8n.cloud, an UptimeRobot page (20). Its incident history loads with JavaScript and came back empty for our reader, and the Statuspage JSON path is blocked by robots.txt, so we couldn't read the last 90 days (5, and this is our limit, not proof of a clean record). No request-per-minute limit for the API in the docs or the OpenAPI file. Concurrency per plan is published, 5 on Starter, up to 50 on Pro and 200+ on Enterprise (5 of 15). No 429, Retry-After or backoff guidance for the API found (0). Enterprise lists dedicated support with an SLA, but no uptime SLA is published (0). The REST API and the instance MCP server are generally available. Only the Agents tools are marked preview (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.

## 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). Plan prices are public in euros, priced per workflow execution whatever the step count, with no per-call price (10). Cloud trial of 1,000 executions with no card, though the API is off during it, and the self-hosted Community Edition is free with the API on (20). A person has to sign up or install an instance and create a key in the UI (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. Security & auth, 70 out of 100, up to 5.3 more on the total

Why it scored 70: REST keys go in `X-N8N-API-KEY`, carry an expiry and can be deleted, but scopes are Enterprise only. The MCP server takes OAuth with per-client revocation and about 17 grantable scopes, or a personal token (25). Workflows are exposed to MCP one at a time and an OAuth grant can be read-only, but nothing asks for confirmation before a destructive tool runs (14). Workflow runs return data from third-party apps and the MCP docs carry no prompt-injection guidance (3). Execution history per run, plus a security audit endpoint in the public API. We found no audit trail for MCP actions in the docs (10). Valid security.txt expiring 31 December 2027, a vulnerability disclosure policy, a trust centre with SOC reports, and advisories published on GitHub with CVEs. No bug bounty found (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.

## 4. Agent ergonomics, 75 out of 100, up to 4.1 more on the total

Why it scored 75: 54 MCP tools per the docs (58 names in the scope map on master), so 5, plus 10 back because OAuth scopes such as `workflow:read` and `execution:read` only register the tools they cover, and builder tools sit behind a flag (15). Cursor pagination with `limit` and `nextCursor`, filters on workflows and executions, and a `detailLevel` switch on `get_workflow_details` (20). Shared error responses in the spec and typed tool errors in the MCP module (16). `readOnlyHint` and `destructiveHint` set on the MCP tools, with `execute_workflow`, `update_workflow` and the delete tools marked destructive. No idempotency keys on API writes (16). Few required parameters, but no official REST SDK in any language (8).

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.

## 5. Maintenance & community, 80 out of 100, up to 1.8 more on the total

Why it scored 80: n8n@2.42.2 tagged on 1 October 2026 (30). 134 tags in the last 90 days across the 2.x and 1.x lines (20). 406 open issues, and the ten newest, opened 17 to 19 September, all carry triage labels and most a team assignment (20). No official REST SDK and the MCP server isn't in the official registry (0). CI on master with build, lint, unit tests, SBOM generation and security workflows (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.

## 6. Transparency & trust, 82 out of 100, up to 1.6 more on the total

Made of editorial 68, provenance 96.

Why it scored 82: Sustainable Use License, source-available with clear terms but not an OSI licence (20). Privacy policy, DPA, a trust centre, Cloud data stored in Frankfurt per the pricing page, and execution log retention stated per plan. No subprocessor list on the legal hub page (22). BREAKING-CHANGES.md lists each breaking version with what to do, and the 1.x line still gets patches alongside 2.x (15). Self-hosted telemetry is on by default in the source (`N8N_DIAGNOSTICS_ENABLED` defaults to true) with an environment opt-out. Cloud data location stated (11).

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: n8n.io, registered 2018-12-01 (7 years) (11 of 15)

## 7. Schema & documentation, 92 out of 100, up to 1.3 more on the total

Why it scored 92: OpenAPI 3.0 file for the public API in the repository (version 1.1.1, 208 operations), and every MCP tool declares a zod input schema and an output schema (25). llms.txt per the 30 September check, and the docs serve Markdown copies of each page (10). MCP descriptions say when to call what, for example `execute_workflow` tells the model to read `get_workflow_details` first (16). Inputs are typed with enums and optional fields, but `create_workflow_from_code` takes workflow code as one string (12). 791 examples in the API spec and shared error responses for 400, 401, 403, 404, 409, 422, 500 and 503 (14). Versioned at /api/v1, weekly release notes and a BREAKING-CHANGES file with upgrade steps per version (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.

## Deductions

Each comes off the total. A fixed and documented problem counts for less at the next check.

- CVE-2025-68613 (GHSA-v98v-ff95-f3cp), code execution through workflow expressions for any authenticated user, published to NVD on 19 December 2025 (GitHub's advisory is dated 22 December) and added to CISA's Known Exploited Vulnerabilities catalogue on 11 March 2026 as exploited in the wild. Patched and documented (https://github.com/advisories/GHSA-v98v-ff95-f3cp, https://services.nvd.nist.gov/rest/json/cves/2.0?cveId=CVE-2025-68613, https://services.nvd.nist.gov/rest/json/cves/2.0?keywordSearch=n8n&hasKev).
- CVE-2026-21858 (GHSA-v4pr-fm98-w9pg), unauthenticated file access through improper webhook handling, rated critical, published 7 January 2026, and CVE-2026-27493 (GHSA-75g8-rv7v-32f7), unauthenticated expression evaluation through the Form node, published 25 February 2026. Both patched (https://github.com/advisories?query=n8n+severity%3Acritical).
- 24 critical advisories for the n8n package published between 8 December 2025 and 14 May 2026, counted on 2 October 2026 with the GitHub Advisory Database query cited here, most of them sandbox escapes or remote code execution, and high-severity batches still landing on 22 July, 10 September and 16 September 2026, including credential decryption without an ownership check (GHSA-9rhv-fhr8-7q5r). All handled in public with fixes, which is why this isn't the full -15 (https://github.com/advisories?query=type%3Areviewed+ecosystem%3Anpm+affects%3An8n+severity%3Acritical+published%3A2025-12-01..2026-05-31, https://github.com/n8n-io/n8n/security/advisories).

## 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: the incident history on status.n8n.cloud, which didn't render for our reader
- Whether n8n Cloud instances were ever exposed to the exploited CVE-2025-68613 before patching
- Whether failed executions count towards the plan allowance
- Whether the public API returns 429 under load and with what headers

## Weaknesses

- 24 critical advisories from December 2025 to May 2026, and CVE-2025-68613 was exploited in the wild
- No published API rate limit, 429 guidance or uptime SLA
- API key scopes only on Enterprise, and no API during the Cloud trial
- Sustainable Use License, not OSI open source, and self-hosted telemetry on by default
- 54 MCP tools in the full set, heavy for a context window unless the grant is narrowed

## 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.

- Check the instance version before trusting it. Anything older than the September 2026 patch releases carries published high-severity flaws
- Ask for only the OAuth scopes the job needs. `workflow:read` plus `workflow:execute` keeps the builder and delete tools out of the tool list
- Call `get_workflow_details` with `detailLevel` set to execution before `execute_workflow`, which returns an execution ID and doesn't wait
- Follow `nextCursor` until it's null when paging workflows or executions
- On Cloud trial accounts `/api/v1` won't answer. Use the MCP server or a paid plan

## What the review panel asked for

- dated 1.x support window
- REST scopes below Enterprise
- audit trail for MCP

## 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.