mcp-sequentialthinking-tools — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Track tool schema and client compatibility as the reasoning helper changes

Reviewed Oct 5, 2026 · Documentation review; complete setup workflow not independently tested

Best fit

Inspectable planning scratchpad with branching, revisions and tool-name validation.

What we know

Lightweight local reasoning scratchpad that stores sequential thoughts, history and branches and validates recommended tool names against a supplied list.

Maintenance / activity evidence

Observed Sep 25, 2026 (UTC)Merge pull request 94 from spences10/renovate/pnpm-12.x

Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: high.

Activity source · commits ↗Activity source · releases ↗

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Local scratchpad/history only. Writes: Store thought records; Clear histories.
Authentication not yet verified.
Sensitive access: Reasoning notes and tool descriptions

Low operational authority, but histories can contain sensitive context.

Security source · repository notice ↗

Full authority, access and evidence limits are available in Review context and Access & risk.

Popularity

590 repository stars

Stars observed Sep 25, 2026.

Do not overwrite existing reviewed stars/download metrics with nulls from this enrichment batch.

All limitations / Review context

Does the current package preserve the documented sequential-thinking contract?

The bounded assessment reviewed the official README, repository notices, security policy path, and security page for known material public-tracking blockers. No such blocker was identified. This is a public-tracking assessment, not an installation safety certification.

Low operational authority, but histories can contain sensitive context.
Local scratchpad/history only.
Thought text is stored by the server; injection-like strings are defensively scanned/redacted.
Reviewed write actions: Store thought records; Clear histories
Sensitive access: Reasoning notes and tool descriptions
Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
A project-specific SECURITY.md policy was not available at the fetched official path; the review remains limited to published repository notices.
No installation, runtime, client matrix, or complete tool-contract audit was performed in this review.
The fetched official SECURITY.md path returned HTTP 404; it was not treated as positive evidence.
It does not discover or choose tools.
Adds overhead on trivial tasks.
The publisher warns not to store secrets in thought text.

Original activity observations

2026-09-25T20:38:35Z: Merge pull request 94 from spences10/renovate/pnpm-12.x

Technical identity

github.com/spences10/mcp-sequentialthinking-tools

Exact implementation source: https://github.com/spences10/mcp-sequentialthinking-tools ↗
Reviewed resource type: MCP Server
Repository identity: spences10/mcp-sequentialthinking-tools
Package identity: npm:mcp-sequentialthinking-tools

Evidence & Sources

Evidence basis: Recorded source evidence
Setup runtime verification: Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed Oct 5, 2026 · Latest source observation Oct 7, 2026

GitHub repository ↗
spences10/mcp-sequentialthinking-tools
Recorded repository material and project history.

Setup · Watchlist

Install & Agents

Publisher instructions.

Source evidence observed Oct 14, 2026.

Additional setup details required — see the specific gaps below.

Install / connect
Publisher instructions
Sequential Thinking Tools is a stdio MCP server providing reasoning tools.
publisher setup entry · Publisher instructions · Review before use
```
npx -y mcp-sequentialthinking-tools
```
Configure / authenticate
MCP100 setup guide
Register npx -y mcp-sequentialthinking-tools in the chosen client mcpServers JSON. MAX_HISTORY_SIZE is optional in publisher example.
Check connection
Suggested check
List MCP tools and run a small synthetic reasoning step.
Remove / uninstall / revoke
MCP100 setup guide
Remove the MCP client entry named `sequentialthinking` (or its actual registered name), e.g. `claude mcp remove sequentialthinking`; stop any separately running node process and retain project files. Client remove command is an MCP100 composed example: replace the registration name with your actual installed name.
Client unregistration, program uninstall, persistent-data deletion, and credential revocation must be treated separately.
Remove client registration · Claude Code only · MCP100 composed guide
claude mcp remove sequentialthinking

Official Documentation & Sources

What it does

Lightweight local reasoning scratchpad that stores sequential thoughts, history and branches and validates recommended tool names against a supplied list.

Capability: AI & Reasoning
Resource type: MCP Server
Best fit: Inspectable planning scratchpad with branching, revisions and tool-name validation.

Representative uses

Record a sequence of reasoning notes
Revise/branch a plan
Inspect or clear session history
Validate planned tool names

Limitations

It does not discover or choose tools.
Adds overhead on trivial tasks.
The publisher warns not to store secrets in thought text.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: Not documented in the reviewed sources
Permissions: Local scratchpad/history only.
Data handling: Thought text is stored by the server; injection-like strings are defensively scanned/redacted.
Cost: free
Risk and cautions: Low operational authority, but histories can contain sensitive context.

Access scope and cautions

Write actions: Store thought records Clear histories
Sensitive access: Reasoning notes and tool descriptions
Risk level: low

FAQ

Based on reviewed evidence as of 2026-10-07. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The reviewed tasks include: Record a sequence of reasoning notes; Revise/branch a plan; Inspect or clear session history; Validate planned tool names.

What setup information is documented?

Recorded installation/entrypoint step: npx -y mcp-sequentialthinking-tools. Recorded transport: stdio. Recorded environment-variable notes: MAX_HISTORY_SIZE (optional). No configuration values are supplied here. Prerequisites: Node.js >=22. These are the documented setup details, not a claim that installation or client compatibility was independently tested.

Can it modify data or perform write operations?

Documented write actions include: Store thought records; Clear histories. Recorded permission boundary: Local scratchpad/history only.

What data-handling boundary should I consider?

Thought text is stored by the server; injection-like strings are defensively scanned/redacted. Recorded sensitive-access context: Reasoning notes and tool descriptions.

What limitations and risks should I check before use?

Low operational authority, but histories can contain sensitive context. It does not discover or choose tools. Adds overhead on trivial tasks. The publisher warns not to store secrets in thought text. A project-specific SECURITY.md policy was not available at the fetched official path; the review remains limited to published repository notices.

Is this an official MCP?

Scott Spence is listed as Community implementation in MCP100’s current evidence.