Sequential Thinking (MCP reference server) by MCP project (reference servers)

# Fix list: Sequential Thinking (MCP reference server)

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/sequential-thinking-reference-server, the October 2026 research run, assessed 1 October 2026. Grade B, 62.7 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 Sequential Thinking (MCP reference server): 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, 52 out of 100, up to 9.6 more on the total

Why it scored 52: Scored as a local stdio package. Official npm package and the mcp/sequentialthinking Docker image on Node 22, but no engines field or supported runtimes stated (15 of 20). The monorepo's TypeScript workflow runs the server's 17 tests on every push and pull request. We couldn't see whether the default branch passes, so 20 of 25. We couldn't read the issue list. The history shows `nextThoughtNeeded` restored to the required array on 28 August 2026, and the published 2026.8.31 doesn't declare zod as a dependency, fixed on main on 3 September and not yet released (12 of 25). Date versions with no per-package changelog (5 of 15). The repository README and SECURITY.md call these reference implementations, 'not production-ready solutions' (0 of 15).

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. Security & auth, 64 out of 100, up to 6.3 more on the total

Why it scored 64: No credentials to hold or leak, so the middle band (20). No side effects beyond an in-memory history and stderr output (18 of 20). Returns only what the model sent, no outside content (10). Each thought is printed to stderr by default, which gives the operator a trace but also writes the model's reasoning into host logs until `DISABLE_THOUGHT_LOGGING=true` (10 of 15). SECURITY.md says the repository isn't eligible for vulnerability reports. No advisories for this server. Six advisories for the git server in the same repository were published, and security.txt on modelcontextprotocol.io was valid per the 26 September check (6 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.

## 3. Maintenance & community, 39 out of 100, up to 5.3 more on the total

Why it scored 39: 2026.8.31 on npm, published 31 August, 31 days before the run date (20). Only 2026.7.4 and 2026.8.31 were published for this package since 3 July, two of the monorepo's four dated releases (0). Fixes for this server merged in March, August and September 2026. We couldn't read reply times on issues (12 of 25). Not in the official MCP registry, though package.json carries the mcpName io.github.modelcontextprotocol/server-sequential-thinking (0). CI on push and Dependabot groups, but the published package is missing its zod declaration (7 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.

## 4. Payments & pricing, 60 out of 100, up to 5 more on the total

Why it scored 60: Free, self-hosted, nothing to buy, so 20 + 20 + 20. No payment protocol (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.

## 5. Schema & documentation, 73 out of 100, up to 4.4 more on the total

Why it scored 73: One tool with a zod input schema and an output schema (25). README in Markdown on GitHub, no llms.txt (5 of 10). The description lists when to use the tool in seven bullets but never when not to, runs about 2,800 characters, and its parameter section uses snake_case names (`total_thoughts`, `is_revision`) that don't match the camelCase inputs (14 of 20). Integers with a minimum of 1, required fields marked, and booleans that accept 'true' or 'false' strings (13 of 15). README example prompts since April 2026. Errors come back as `{error, status: failed}` with isError set, undocumented (8 of 15). Dated monorepo releases with notes, no changelog for this package (8 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. Agent ergonomics, 73 out of 100, up to 4.4 more on the total

Why it scored 73: One tool, but its description costs about 700 tokens (20 of 25). The response is a fixed five-field JSON object, so there's nothing to page or trim (15 of 20). Validation errors name the bad field, but the server keeps one thought history per process, so a second problem in the same session inherits the first one's thought count and branches (12 of 20). readOnlyHint true, destructiveHint false, idempotentHint true and openWorldHint false. Idempotent is generous for a call that appends to history (18 of 20). Four required arguments on every call, and every thought is a round trip (8 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.

## 7. Transparency & trust, 74 out of 100, up to 2.3 more on the total

Made of editorial 73, provenance 74.

Why it scored 74: MIT for older contributions and Apache-2.0 for new ones, both OSI licences, with npm saying `SEE LICENSE IN LICENSE` (28 of 30). No network calls and nothing stored beyond the process's memory. There's no written statement, but lib.ts is under 3 KB and shows it (20 of 30). No deprecation policy, and the README tells users to look for a `sequential_thinking` tool while the server registers `sequentialthinking` (5 of 20). No telemetry in the code (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):

- Domain age: modelcontextprotocol.io, registered 2024-11-18 (1 year) (3 of 15)
- Status page: not found (0 of 10)

## 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.

- Open issues and reply times for this server; GitHub's issue search wasn't readable to us.
- Whether the default branch CI passes.
- Why 2026.6.3, 2026.6.16, 2026.7.10 and 2026.8.18 didn't publish a new version of this package.

## Weaknesses

- Every thought is a tool call, so turns and tokens add up without creating anything outside the model
- Only 2026.7.4 and 2026.8.31 were published in 2026, and the latest doesn't declare its zod dependency
- History is shared across the whole process, so separate problems in one session run together
- README says `sequential_thinking` but the registered name is `sequentialthinking`
- The maintainers call it a reference implementation, not production-ready

## 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.

- Call it as `sequentialthinking`, not `sequential_thinking`
- Set `totalThoughts` low and raise it only when a revision needs room
- Restart the server between unrelated problems, or ignore `thoughtHistoryLength` and `branches` from earlier work
- Skip it when the host model already has extended thinking

## What the review panel asked for

- Cut the description
- Match parameter names
- a when-not-to list
- per-session history reset

## 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.