Skip to main content
Glama
Kemosabe0x

Sequential Thinking MCP Server

by Kemosabe0x
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

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: Enhanced Sequential Thinking 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

ParametersJSON Schema
NameRequiredDescriptionDefault
thoughtYesYour current thinking step
branchIdNoBranch identifier
isRevisionNoWhether this revises previous thinking
thoughtNumberYesCurrent thought number (numeric value, e.g., 1, 2, 3)
totalThoughtsYesEstimated total thoughts needed (numeric value, e.g., 5, 10)
revisesThoughtNoWhich thought is being reconsidered
branchFromThoughtNoBranching point thought number
needsMoreThoughtsNoIf more thoughts are needed
nextThoughtNeededNoWhether another thought step is needed

Output Schema

ParametersJSON Schema
NameRequiredDescription
branchesYes
thoughtNumberYes
totalThoughtsYes
nextThoughtNeededYes
thoughtHistoryLengthYes

TDQS

A4.7/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds context about the tool's adaptive and reflective nature, such as questioning previous thoughts and generating hypotheses. It does not contradict annotations and enriches understanding.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but well-structured with sections, bullet points, and clear headings. It is front-loaded with purpose and use cases. However, it could be slightly more concise without losing essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity, the description covers all necessary aspects: purpose, when to use, key features, parameter explanations, and step-by-step guidance. The presence of an output schema further supports completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description adds significant meaning beyond the schema by explaining each parameter in context (e.g., what 'thought' can include like revisions or hypothesis generation). It provides usage examples and clarifies the role of each parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool is for dynamic and reflective problem-solving through thoughts. It lists specific use cases like breaking down complex problems and planning with room for revision, distinguishing it as a thinking tool even though no siblings exist.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a detailed 'When to use this tool' section and 'You should' steps, offering clear context and instructions for when to apply the tool. It does not explicitly state when not to use it, but the guidance is comprehensive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

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

  1. 1 tool updatev0.6.2
    • First observedsequentialthinking
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.4/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of confusion between tools. The tool's purpose is clear and distinct.

Naming Consistency5/5

With a single tool, naming consistency is inherently perfect. The name 'sequentialthinking' is descriptive and follows a clear pattern.

Tool Count3/5

A single tool is borderline for a server; while the tool is comprehensive, the server's scope would typically benefit from multiple focused tools.

Completeness5/5

The tool covers the full sequential thinking process with parameters for revision, branching, and verification, leaving no obvious gaps for its stated purpose.

Maintenance

ActivityStale
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches