Skip to main content
Glama
Sequential Thinking MCP Server

Sequential Thinking MCP Server

by coachgruden

Sequential Thinking MCP Server

This repository contains a Model Context Protocol (MCP) server that provides a sequentialthinking tool. The tool facilitates dynamic and reflective problem-solving through a chain of thoughts, allowing AI agents to break down complex problems, revise past thoughts, and explore branches of logic before arriving at a conclusion.

This project is configured to run in two modes:

  1. Stdio: Standard MCP transport for local IDE and CLI integrations.

  2. Server-Sent Events (SSE): Deployed as a secure, remote HTTP gateway on Google Cloud Run.

Local Development

Install dependencies and build the TypeScript code:

npm install
npm run build

To run the Stdio server locally:

node dist/index.js

Related MCP server: Visum Thinker MCP Server

Cloud Run Deployment (SSE Gateway)

This project can be easily cloned and deployed to any Google Cloud account or project. This allows anyone to host their own secure, remote Sequential Thinking MCP server.

Prerequisites

  1. Install the Google Cloud CLI (gcloud).

  2. Authenticate with your Google account:

    gcloud auth login
  3. Set your active Google Cloud Project (ensure billing is enabled):

    gcloud config set project YOUR_PROJECT_ID
  4. Enable the required APIs for your project:

    gcloud services enable run.googleapis.com cloudbuild.googleapis.com

Deploying

Once authenticated, you can deploy the service using the provided Makefile:

make deploy

What this does:

  • Packages the application and builds a Docker container using the provided Dockerfile.

  • Generates a secure, random MCP_API_KEY (if one is not already provided).

  • Deploys the container to Google Cloud Run (default region: us-central1).

  • Outputs the Service URL and your secure API key.

Client Configuration

Once deployed, you can configure your MCP client (Cursor, Hermes, Antigravity, Claude Desktop, etc.) to connect to the SSE gateway.

Provide your client with:

  • URL: <YOUR_CLOUD_RUN_URL>/sse

  • Headers: Authorization: Bearer <YOUR_MCP_API_KEY>

Available Tools

1 tool
sequentialthinkingSequential ThinkingA
Read-onlyIdempotent

A detailed tool for dynamic and reflective problem-solving through thoughts. This tool helps analyze problems through a flexible thinking process that can adapt and evolve. Each thought can build on, question, or revise previous insights as understanding deepens.

When to use this tool:

  • Breaking down complex problems into steps

  • Planning and design with room for revision

  • Analysis that might need course correction

  • Problems where the full scope might not be clear initially

  • Problems that require a multi-step solution

  • Tasks that need to maintain context over multiple steps

  • Situations where irrelevant information needs to be filtered out

Key features:

  • You can adjust total_thoughts up or down as you progress

  • You can question or revise previous thoughts

  • You can add more thoughts even after reaching what seemed like the end

  • You can express uncertainty and explore alternative approaches

  • Not every thought needs to build linearly - you can branch or backtrack

  • Generates a solution hypothesis

  • Verifies the hypothesis based on the Chain of Thought steps

  • Repeats the process until satisfied

  • Provides a correct answer

Parameters explained:

  • thought: Your current thinking step, which can include:

    • Regular analytical steps

    • Revisions of previous thoughts

    • Questions about previous decisions

    • Realizations about needing more analysis

    • Changes in approach

    • Hypothesis generation

    • Hypothesis verification

  • nextThoughtNeeded: True if you need more thinking, even if at what seemed like the end

  • thoughtNumber: Current number in sequence (can go beyond initial total if needed)

  • totalThoughts: Current estimate of thoughts needed (can be adjusted up/down)

  • isRevision: A boolean indicating if this thought revises previous thinking

  • revisesThought: If is_revision is true, which thought number is being reconsidered

  • branchFromThought: If branching, which thought number is the branching point

  • branchId: Identifier for the current branch (if any)

  • needsMoreThoughts: If reaching end but realizing more thoughts needed

You should:

  1. Start with an initial estimate of needed thoughts, but be ready to adjust

  2. Feel free to question or revise previous thoughts

  3. Don't hesitate to add more thoughts if needed, even at the "end"

  4. Express uncertainty when present

  5. Mark thoughts that revise previous thinking or branch into new paths

  6. Ignore information that is irrelevant to the current step

  7. Generate a solution hypothesis when appropriate

  8. Verify the hypothesis based on the Chain of Thought steps

  9. Repeat the process until satisfied with the solution

  10. Provide a single, ideally correct answer as the final output

  11. Only set nextThoughtNeeded to false when truly done and a satisfactory answer is reached

Inputs: thought (required), thoughtNumber (required), totalThoughts (required), branchId, +5 more. Returns: branches, thoughtNumber, totalThoughts, nextThoughtNeeded, +1 more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.6/5.0

    Scored across 1 tool

    Disambiguation5/5

    Only one tool exists, so there is no ambiguity. The tool's purpose is clearly defined and distinct.

    Naming Consistency5/5

    Single tool, so naming consistency is perfect. The name 'sequentialthinking' is descriptive and follows a single convention.

    Tool Count3/5

    A single tool for a server focused on complex sequential thinking feels thin. Even though the tool is comprehensive, the count is at the lower boundary of acceptability.

    Completeness4/5

    The tool covers many aspects of sequential thinking: problem analysis, revision, branching, hypothesis generation, and verification. Minor gaps might exist in explicit state management, but overall it is quite complete for its domain.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers