Official reference MCP server that gives Claude a structured sequential thinking tool for breaking complex problems into ordered, revisable thought steps, all processed locally with no external calls.
by Model Context Protocol · submitted by glorydavid03023·added 2026-06-03·
Provides a structured reasoning scaffold only; it does not access the network, read or write files, run shell commands, or use credentials., Runs locally as an stdio process, so its effect is limited to organizing the model's reasoning steps during a session.
Privacy notes
The thought steps it structures stay within the local MCP session and are not sent to any external service by this server.
Author
Model Context Protocol
Submitted by
glorydavid03023
Claim status
unclaimed
Last verified
2026-06-03
Decision playbook
Review trust signals before you adopt
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
Compare context
Selected
0
Current score
78
Baseline
—
Delta
No baseline selected
No major trust-signal divergence detected in the current selection.
Source and provenance checks
Complete
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Done
Source provenance statusRequired
Marked as source-backed.
Done
Metadata reviewed
Registry metadata indicates a reviewed listing.
Done
Safety and privacy checks
Complete
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Done
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Done
Trust level risk gateRequired
Trust level does not block evaluation.
Done
Package and install checks
Needs review
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Done
Package verification flag
No package verification flag provided.
Pending
Checksum metadata
No checksum provided for downloaded artifact.
Pending
Compare-driven decision checks
Needs review
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
Current risk score 16/100. Use staged verification before broader rollout.
Risk 16
Pre-adoption checks
Validate source and review signals before any execution.
Confirm source provenanceRequired
Source URL/provenance metadata is present.
Done
Confirm metadata review state
Listing has review metadata.
Done
Verify install payload
Install/config payload exists and can be inspected.
Done
Security checks
Confirm safety, privacy, and package integrity signals.
Review safety notesRequired
Safety notes are present.
Done
Review privacy notesRequired
Privacy notes are present.
Done
Verify package integrity metadata
No package verification/checksum metadata.
Pending
Rollout
Adopt in controlled steps based on the selected plan.
Run in isolated sandbox firstRequired
Use a constrained sandbox and observe behavior across multiple tasks.
Pending
Roll out graduallyRequired
Roll out to a small cohort before wider usage.
Pending
Set monitoring and fallback
Define rollback path and monitor errors after adoption.
Pending
Evidence readiness
Evidence readiness matrix · balanced
Required evidence gates are covered (5/6 signals complete).
Risk 15
Source provenance
Present
Source repository/provenance is listed.
Required in this preset
Metadata review
Present
Review metadata is present.
Required in this preset
Safety notes
Present
Safety notes are present.
Required in this preset
Privacy notes
Present
Privacy notes are present.
Optional in this preset
Package integrity
Missing
Package integrity metadata is missing.
Optional in this preset
Install payload
Present
Install payload is available.
Required in this preset
Required evidence gates are covered for this preset.
Decision timeline
Decision timeline · balanced
5/6 steps complete with no blocking gaps for this preset.
Risk 14
triage
Confirm source provenanceRequired
Source/provenance metadata is available.
Done
triage
Check metadata review statusRequired
Review metadata is available.
Done
verify
Review safety notesRequired
Safety notes are available.
Done
verify
Review privacy notes
Privacy notes are available.
Done
verify
Validate package integrity metadata
Package integrity metadata is missing.
Pending
rollout
Verify install payload and commandsRequired
Install payload is available.
Done
No required blockers for this timeline preset.
Prerequisite readiness
Prerequisite readiness
2 prerequisites to line up before setup.
0/2 ready
Install & runtime1Network & hosting12 minutes
Safety & privacy surface
Safety & privacy surface
2 safety and 1 privacy notes across 1 risk area. Review closely: credentials & tokens.
1 area
SafetyCredentials & tokensProvides a structured reasoning scaffold only; it does not access the network, read or write files, run shell commands, or use credentials.
SafetyCredentials & tokensRuns locally as an stdio process, so its effect is limited to organizing the model's reasoning steps during a session.
PrivacyCredentials & tokensThe thought steps it structures stay within the local MCP session and are not sent to any external service by this server.
Safety notes
Provides a structured reasoning scaffold only; it does not access the network, read or write files, run shell commands, or use credentials.
Runs locally as an stdio process, so its effect is limited to organizing the model's reasoning steps during a session.
Privacy notes
The thought steps it structures stay within the local MCP session and are not sent to any external service by this server.
Prerequisites
Node.js 18+ and npx available (verify with: npx --version)
Sequential Thinking is one of the official Model Context Protocol reference servers. It gives Claude a dedicated tool for working through a problem in explicit, ordered steps: laying out a thought, revising an earlier one, branching to explore alternatives, and tracking how many steps remain. Rather than asking the model to reason in a single pass, the server provides a structured scaffold that encourages deliberate, reviewable problem-solving. It performs no external actions, so it is a safe, low-overhead way to improve how Claude approaches complex or multi-step tasks.
Features
A structured thinking tool that organizes reasoning into ordered, numbered steps.
Support for revising earlier thoughts as understanding improves.
The ability to branch and explore alternative lines of reasoning.
Explicit tracking of progress, including how many steps are expected.
Runs locally as a standard stdio MCP server with no network, file, or credential access.
Maintained as part of the official Model Context Protocol reference servers.
Use Cases
Work through complex, multi-step problems more deliberately.
Plan an implementation before writing code by laying out ordered steps.
Explore alternative approaches by branching reasoning paths.
Revisit and revise an earlier assumption mid-analysis.
Add a lightweight, safe reasoning aid to a Claude workflow.
Installation
Claude Code
Make sure Node.js 18+ is installed (verify with npx --version).
Run: claude mcp add sequential-thinking -- npx -y @modelcontextprotocol/server-sequential-thinking
Verify the server is registered: claude mcp list
Ask Claude to work through a multi-step problem to see the structured steps.
Claude Desktop
Open your Claude Desktop configuration file.
Add the Sequential Thinking server to the mcpServers section using the configuration below.
Restart Claude Desktop.
Confirm the server appears and ask Claude to reason through a problem step by step.
Ask Claude to think through the approach in ordered steps.
"Use sequential thinking to plan how to refactor this module before writing any code."
Work through a tricky problem
Encourage deliberate, step-by-step analysis.
"Reason through this scheduling problem step by step, revising earlier steps if needed."
Explore alternatives
Branch the reasoning to compare options.
"Use sequential thinking to compare two approaches to caching and explain the trade-offs."
Security
The server is a reasoning scaffold only. It does not access the network, read or write files, execute shell commands, or use credentials.
It runs locally as an stdio process, so its impact is limited to structuring the model's reasoning during the session.
The thought steps it organizes stay within the local MCP session and are not transmitted anywhere by this server.
As with any MCP server, install it from the official package source shown above.
Troubleshooting
npx cannot resolve the package
Verify Node.js 18+ and npx are installed (npx --version). Networks that block the npm registry will prevent npx -y @modelcontextprotocol/server-sequential-thinking from resolving.
Server not listed in Claude Code
Re-run claude mcp add sequential-thinking -- npx -y @modelcontextprotocol/server-sequential-thinking, then claude mcp list. Confirm it was added to the scope (project versus user) you are running in.
Claude does not use the thinking tool
Add an explicit instruction such as "use sequential thinking" to the prompt. The model decides when to call the tool, so a nudge helps on tasks where it would otherwise answer in a single pass.
Steps seem to stop early
The tool tracks an expected number of steps but can extend or revise them. Ask Claude to continue reasoning or to add steps if the analysis feels incomplete.
Show that Sequential Thinking MCP Server for Claude is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/sequential-thinking-mcp-server)
How it compares
Sequential Thinking MCP Server for Claude side by side with 2 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
1 trust signal differ across this comparison (Submitter).
Official reference MCP server that gives Claude a structured sequential thinking tool for breaking complex problems into ordered, revisable thought steps, all processed locally with no external calls.
Official reference MCP server that gives Claude persistent memory through a local knowledge graph of entities, relations, and observations, stored in a file on your own machine.
Maintenance-mode MCP server that adds metacognitive oversight tools for challenging an agent's plan, recording recurring mistakes, and applying session rules before complex or high-risk work continues.
✓Provides a structured reasoning scaffold only; it does not access the network, read or write files, run shell commands, or use credentials.
Runs locally as an stdio process, so its effect is limited to organizing the model's reasoning steps during a session.
✓Persists remembered information to a local file on disk (its location can be set with MEMORY_FILE_PATH); manage and review that file as it accumulates data.
Runs locally as an stdio process and makes no external network calls; the knowledge graph stays on your machine.
✓Vibe Check MCP is in final maintenance mode according to the project README, so check the repository and package state before adopting it broadly.
The server is an advisory oversight layer; it can challenge assumptions but cannot guarantee safe, correct, or complete decisions.
The `vibe_check` tool sends the goal, plan, optional user prompt, progress, uncertainties, and task context to a configured LLM provider for critique.
The `vibe_learn` tool can record mistakes, preferences, successes, categories, and solutions for later reflection.
Constitution tools can help apply session rules, but they do not enforce external system permissions or prevent client-side actions by themselves.
Privacy notes
✓The thought steps it structures stay within the local MCP session and are not sent to any external service by this server.
✓Details Claude chooses to remember are written to and read from the local memory file, so it can retain personal or project information across sessions.
Review or clear the memory file if it should not retain sensitive data, and use MEMORY_FILE_PATH to control where it is stored.
✓Agent plans, prompts, progress, uncertainties, session identifiers, mistakes, and learned preferences can reveal confidential project details.
Provider API keys are loaded from environment variables and should be scoped, stored, and rotated according to local policy.
Depending on provider selection, request metadata and prompt content may be processed by Gemini, OpenAI, OpenRouter, Anthropic, or compatible endpoints.
Avoid sending secrets, private code, customer data, or regulated information in `vibe_check` or `vibe_learn` inputs unless approved for the selected provider.
Prerequisites
Node.js 18+ and npx available (verify with: npx --version)
Claude Code or Claude Desktop with MCP support
Node.js 18+ and npx available (verify with: npx --version)
Claude Code or Claude Desktop with MCP support
A writable location for the memory file, optionally set with the MEMORY_FILE_PATH environment variable
Node.js 20 or newer and npx available to the MCP client runtime.
At least one supported LLM provider credential, such as Gemini, OpenAI, OpenRouter, or Anthropic.
Review of the project's maintenance notice before relying on it for long-lived workflows.
Clear policy for what agent plans, prompts, progress notes, and session context may be sent to a second model provider.
Install
claude mcp add sequential-thinking -- npx -y @modelcontextprotocol/server-sequential-thinking
claude mcp add memory -- npx -y @modelcontextprotocol/server-memory