Notion MCP by Notion

# Fix list: Notion MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/notion-mcp, the October 2026 research run, assessed 1 October 2026. Grade C, 59 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 Notion 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). No separate MCP charge, and Notion's plan prices are public (10). Notion's Free plan needs no card, with some tools limited by plan (20). A person signs in through OAuth (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, 51 out of 100, up to 8 more on the total

Why it scored 51: 36 tools on the hosted server with no toolsets, read-only subset or dynamic loading (5). Search filters, data-source queries with filters and sorts, and truncation metadata on large pages in notion-fetch (16). Validation errors, rate-limit waits in the body and a documented 504 for slow writes give an agent something to act on (14). The open-source server marks tools readOnlyHint or destructiveHint from the HTTP method, but we couldn't confirm the hosted server does the same, and there are no idempotency keys (8). One URL and OAuth, with an official SDK in JavaScript only (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.

## 3. Security & auth, 60 out of 100, up to 7 more on the total

Why it scored 60: OAuth bounded by each user's Notion permissions, with MCP access tokens valid for about 8 hours since 14 July 2026, but no granular scopes for the MCP connection (22). No read-only mode on the hosted server. Workspace owners can allowlist and revoke connections, and the Admin API lists members' connections (8). Tools return page and comment text anyone in the workspace can write, and we found no prompt-injection guidance (3). Enterprise audit logs and SIEM events exist, with no per-call MCP log documented (10). A public HackerOne bug bounty, SOC 2 Type 2, ISO 27001, 27017, 27018 and 27701 and BSI C5 on the security page, no security.txt per the 26 September check (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. Reliability, 72 out of 100, up to 5.6 more on the total

Why it scored 72: Statuspage at notion-status.com with a Notion MCP component and an incident feed (20). In the last 90 days the feed lists "Notion is down" on 24 July 2026 with Notion MCP among 19 affected components, degraded pages and API errors on 11 July, MCP auth failures on 5 August and API 500s on 1 October. The feed doesn't give durations, so we counted 24 July as one major (10). Per-tool limits published, 20 calls per 10 seconds for notion-search and notion-query-data-sources since 28 September, with a per-connection 60-second window since 9 September (15). Since 24 September the wait time comes back in the response body, and the REST API documents 429 handling, but we found no safe-retry guidance for page writes, which return 504 on timeout (12). The security page states 99.9 per cent guaranteed uptime without saying the MCP server is covered (7). The core server is GA, and the Notion Agent session tools are a public beta since 20 August (8).

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, 71 out of 100, up to 4.7 more on the total

Why it scored 71: Tools carry JSON Schema by protocol, and the supported-tools page describes each one, but the hosted server's schemas aren't published outside a signed-in session (18). llms.txt at developers.notion.com and documentation resources at `notion://docs/*` URIs (10). The descriptions say what each tool does and which plan it needs, and `notion-get-tool-access` reports what's available, though few say when not to use a tool (12). Hosted input types not visible to us, and data-source queries take SQL strings (8). Validation errors and the 504 timeout are logged in the changelog, with few worked examples on the tools page (8). A dated changelog tagged [MCP], 20 MCP entries in the last 90 days, and the MCP protocol version is stated (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, 74 out of 100, up to 2.3 more on the total

Made of editorial 57, provenance 90.

Why it scored 74: The hosted server is closed under Notion's terms. The local server is MIT but unmaintained (15). The security page says AI subprocessors are barred from training on customer data and a trust centre holds the reports. We didn't check the DPA or retention periods in this run (20). Deprecations are dated in the changelog (notion-query-database-view on 29 September) and the local repository's README says it may be sunset, but notion-search changed behaviour on 2 September with no prior notice (12). Subprocessors sit in the trust centre, which we didn't read (10).

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, 81 out of 100, up to 1.7 more on the total

Why it scored 81: MCP changelog entry on 29 September 2026 (30). Twenty MCP entries in the last 90 days (20). The hosted server is supported through Notion support with an active public changelog, while the GitHub repository for the local server says issues and pull requests aren't monitored (10). Registered as com.notion/mcp in the official MCP registry (15). The local package @notionhq/notion-mcp-server 2.5.2 (20 September 2026) has CI on Node 20 and 22 and MCP SDK 1.29.0, but its README says it is no longer actively maintained (6).

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.

## Deductions

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

- 2026-09-02, notion-search became keyword-only and semantic search moved to a new notion-ai-search tool, with no advance notice in the changelog. Agents relying on semantic results from notion-search got different answers until a 10 September change routed content queries back to AI search (https://developers.notion.com/page/changelog)

## 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.

- Durations of the 24 July and 5 August 2026 incidents, which the feed doesn't state.
- Whether the hosted tools set readOnlyHint and destructiveHint like the open-source server does.
- Whether the 99.9 per cent uptime guarantee covers the MCP server and which plan it applies to.
- unchecked: Notion's DPA, retention periods and subprocessor list in the trust centre.

## Weaknesses

- 36 tools with no toolsets, read-only mode or granular OAuth scopes
- notion-search changed behaviour on 2 September 2026 with no advance notice
- The open-source local server is no longer maintained, per its README of 20 September 2026
- Notion AI and Custom Agent tools need paid add-ons, and the agent session tools are in public beta
- No prompt-injection guidance for tools that return user-written pages

## 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 `notion-ai-search` for meaning and `notion-search` for exact keywords, they diverged on 2 September 2026
- Call `notion-get-tool-access` first to see which tools the workspace's plan allows
- Keep search and data-source queries under 20 calls per 10 seconds and read the wait time from the response body
- Check the truncation metadata from `notion-fetch` before assuming you have the whole page
- Switch `notion-query-database-view` calls to `notion-query-data-sources`, deprecated on 29 September 2026

## What the review panel asked for

- One error reference
- Publish hosted schemas
- granular OAuth scopes
- read-only endpoint

## 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.