Sequential Thinking MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Sequential Thinking MCP Serverbreak down how to plan a cross-country road trip step by step"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Sequential Thinking MCP Server - LangGPT Demo
Note: This is a demonstration version by LangGPT, based on the original Sequential Thinking MCP Server from Anthropic's Model Context Protocol. This demo showcases how to extend and publish MCP servers for the Claude ecosystem.
An MCP server implementation that provides a tool for dynamic and reflective problem-solving through a structured thinking process. This server enables Claude to break down complex problems into manageable, trackable steps with support for revision and branching.
Features
Break down complex problems into manageable steps
Revise and refine thoughts as understanding deepens
Branch into alternative paths of reasoning
Adjust the total number of thoughts dynamically
Generate and verify solution hypotheses
Related MCP server: MCP Think Tool
Tool
sequential_thinking
Facilitates a detailed, step-by-step thinking process for problem-solving and analysis.
Inputs:
thought(string): The current thinking stepnextThoughtNeeded(boolean): Whether another thought step is neededthoughtNumber(integer): Current thought numbertotalThoughts(integer): Estimated total thoughts neededisRevision(boolean, optional): Whether this revises previous thinkingrevisesThought(integer, optional): Which thought is being reconsideredbranchFromThought(integer, optional): Branching point thought numberbranchId(string, optional): Branch identifierneedsMoreThoughts(boolean, optional): If more thoughts are needed
Usage
The Sequential Thinking tool is designed for:
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
Tasks that need to maintain context over multiple steps
Situations where irrelevant information needs to be filtered out
Quick Start
Installation via NPM (Recommended)
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"sequential-thinking": {
"command": "npx",
"args": ["-y", "@langgpt/sequential-thinking-mcp"]
}
}
}Installation via Docker
{
"mcpServers": {
"sequential-thinking": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"langgpt/sequential-thinking-mcp"
]
}
}
}After adding the configuration, restart Claude Desktop and try asking:
Please use the sequential thinking tool to analyze this complex problem step by step.Usage with VS Code
For quick installation, click one of the installation buttons below...
For manual installation, add the following JSON block to your User Settings (JSON) file in VS Code. You can do this by pressing Ctrl + Shift + P and typing Preferences: Open Settings (JSON).
Optionally, you can add it to a file called .vscode/mcp.json in your workspace. This will allow you to share the configuration with others.
Note that the
mcpkey is not needed in the.vscode/mcp.jsonfile.
For NPX installation:
{
"mcp": {
"servers": {
"sequential-thinking": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-sequential-thinking"
]
}
}
}
}For Docker installation:
{
"mcp": {
"servers": {
"sequential-thinking": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"mcp/sequentialthinking"
]
}
}
}
}Building
Docker:
docker build -t mcp/sequentialthinking -f src/sequentialthinking/Dockerfile .Local Development and Configuration
Prerequisites
Node.js (version 18 or higher)
npm (usually installed with Node.js)
Local Build Steps
Install dependencies
npm installBuild project
npm run buildThis compiles TypeScript code to the
dist/directory.Development mode
npm run watchThis starts watch mode for automatic recompilation.
Local Source Configuration for Claude Desktop
If you want to use this MCP server from local source code, follow these steps:
Ensure project is built
npm run buildLocate Claude Desktop config file
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
Add local configuration
{ "mcpServers": { "sequential-thinking": { "command": "node", "args": ["/your/absolute/path/to/project/dist/index.js"], "env": { "DISABLE_THOUGHT_LOGGING": "false" } } } }Important: Replace
/your/absolute/path/to/project/dist/index.jswith your actual project path!Restart Claude Desktop
After saving the config file, restart the Claude Desktop application.
Test the tool
Test in Claude with something like:
Please use the sequential thinking tool to analyze a complex problem
Tool Features
This sequential thinking tool enables Claude to:
Break down complex problems into manageable steps
Revise and refine thoughts as understanding deepens
Branch into alternative paths of reasoning
Adjust the total number of thoughts dynamically
Generate and verify solution hypotheses
Environment Variables
DISABLE_THOUGHT_LOGGING=true- Disable console output of thinking process
Publishing
This section provides guidance for developers who want to publish their own version of this MCP server.
Prerequisites
Node.js (version 18 or higher)
npm account for NPM publishing
Docker Hub account for Docker publishing (optional)
GitHub account for source code hosting
Prepare for Publishing
Update package.json
Modify the package configuration for your own project:
{ "name": "@langgpt/sequential-thinking-mcp", "version": "1.0.0", "description": "MCP server for sequential thinking and problem solving", "author": "LangGPT <contact@langgpt.dev>", "homepage": "https://github.com/langgpt/sequential-thinking-mcp", "bugs": "https://github.com/langgpt/sequential-thinking-mcp/issues", "repository": { "type": "git", "url": "git+https://github.com/langgpt/sequential-thinking-mcp.git" }, "keywords": [ "mcp", "model-context-protocol", "claude", "thinking", "ai-tools" ] }Ensure all files are ready
npm install npm run build
Publishing to NPM
Login to NPM
npm loginPublish the package
npm publish --access publicVersion management
# Update version and republish npm version patch # 1.0.0 -> 1.0.1 npm publish
Publishing to Docker Hub
Build Docker image
docker build -t langgpt/sequential-thinking-mcp .Test the image
docker run --rm -i langgpt/sequential-thinking-mcpPush to Docker Hub
docker login docker push langgpt/sequential-thinking-mcp # Also push with version tag docker tag langgpt/sequential-thinking-mcp langgpt/sequential-thinking-mcp:1.0.0 docker push langgpt/sequential-thinking-mcp:1.0.0
Publishing to GitHub
Initialize repository
git init git add . git commit -m "Initial commit: Sequential thinking MCP server"Push to GitHub
git remote add origin https://github.com/langgpt/sequential-thinking-mcp.git git push -u origin mainCreate GitHub Release
Go to your repository on GitHub
Click "Releases" → "Create a new release"
Add tag (e.g., v1.0.0) and release notes
Usage After Publishing
Once published, users can install and use your MCP server in the following ways:
NPM Installation
{
"mcpServers": {
"sequential-thinking": {
"command": "npx",
"args": ["-y", "@langgpt/sequential-thinking-mcp"]
}
}
}Docker Installation
{
"mcpServers": {
"sequential-thinking": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"langgpt/sequential-thinking-mcp"
]
}
}
}GitHub Installation
{
"mcpServers": {
"sequential-thinking": {
"command": "npx",
"args": [
"-y",
"https://github.com/langgpt/sequential-thinking-mcp#main"
]
}
}
}License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Available Tools
1 toolsequentialthinkingA
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
next_thought_needed: True if you need more thinking, even if at what seemed like the end
thought_number: Current number in sequence (can go beyond initial total if needed)
total_thoughts: Current estimate of thoughts needed (can be adjusted up/down)
is_revision: A boolean indicating if this thought revises previous thinking
revises_thought: If is_revision is true, which thought number is being reconsidered
branch_from_thought: If branching, which thought number is the branching point
branch_id: Identifier for the current branch (if any)
needs_more_thoughts: If reaching end but realizing more thoughts needed
You should:
Start with an initial estimate of needed thoughts, but be ready to adjust
Feel free to question or revise previous thoughts
Don't hesitate to add more thoughts if needed, even at the "end"
Express uncertainty when present
Mark thoughts that revise previous thinking or branch into new paths
Ignore information that is irrelevant to the current step
Generate a solution hypothesis when appropriate
Verify the hypothesis based on the Chain of Thought steps
Repeat the process until satisfied with the solution
Provide a single, ideally correct answer as the final output
Only set next_thought_needed to false when truly done and a satisfactory answer is reached
| Name | Required | Description | Default |
|---|---|---|---|
| thought | Yes | Your current thinking step | |
| nextThoughtNeeded | Yes | Whether another thought step is needed | |
| thoughtNumber | Yes | Current thought number | |
| totalThoughts | Yes | Estimated total thoughts needed | |
| isRevision | No | Whether this revises previous thinking | |
| revisesThought | No | Which thought is being reconsidered | |
| branchFromThought | No | Branching point thought number | |
| branchId | No | Branch identifier | |
| needsMoreThoughts | No | If more thoughts are needed |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description fully carries the burden of behavioral disclosure. It details the iterative process including revision, branching, hypothesis generation, verification, and repetition. It explains that thoughts can build, question, or revise previous insights. This level of detail fully informs the agent of the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections (When to use, Key features, Parameters explained, You should). It is front-loaded with the tool's purpose. However, it is somewhat verbose, particularly the 'You should' list which repeats earlier points (e.g., generating and verifying hypothesis). Trimming redundant points could improve conciseness without losing value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (9 parameters, no output schema, no annotations), the description covers most aspects: purpose, usage guidelines, parameter details, and behavioral process. The only gap is that it does not mention the return value format or output structure. Since there is no output schema, the description could have briefly described what the tool returns (e.g., final answer or thought log) to be fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Although schema coverage is 100%, the description adds substantial meaning beyond the schema. For example, the 'thought' parameter is described as including regular analytical steps, revisions, questions, etc. The 'next_thought_needed' and 'total_thoughts' parameters are explained with usage context. This extra information greatly helps the agent understand how to use each parameter effectively.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'dynamic and reflective problem-solving through thoughts.' It specifies that it helps analyze problems through a flexible thinking process. Since there are no sibling tools, differentiation is not needed. The verb 'helps analyze' and the resource 'problems' make it specific and actionable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides a dedicated 'When to use this tool' section listing scenarios like breaking down complex problems, planning with revision, and analysis needing course correction. It offers clear context but does not explicitly state when to avoid using the tool or mention alternatives. With no sibling tools, the lack of exclusions is acceptable, but the guidance could be more 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 tool update
- First observed
sequentialthinking
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion or overlap with other tools. The tool has a single, clearly defined purpose for sequential thinking and problem-solving, so disambiguation is perfect.
Since there is only one tool, naming consistency is inherently perfect. The tool name 'sequentialthinking' follows a consistent pattern with itself, and there are no other tools to cause inconsistency.
A single tool is too few for a server named 'Sequential Thinking MCP Server', which suggests a broader scope for problem-solving support. While the tool is detailed, the server feels thin and could benefit from additional tools to cover related aspects like summarization, validation, or different thinking modes.
The tool surface is severely incomplete for the implied domain of sequential thinking and problem-solving. There are obvious gaps, such as lack of tools for managing thought history, exporting results, integrating with other systems, or providing alternative thinking frameworks, limiting the server's utility.
Maintenance
Related MCP Connectors
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
MCP server for generating rough-draft project plans from natural-language prompts.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
Related MCP Servers
- AlicenseAqualityAmaintenanceThis server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.552 PyPI952MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that implements the 'think' tool, providing Claude with a dedicated space for structured thinking during complex problem-solving tasks to improve reasoning capabilities.130MIT
- AlicenseAqualityDmaintenanceA MCP server that implements sequential thinking protocols, provides structured problem-solving methods, decomposes complex problems into manageable steps, and supports iterative optimization and alternative reasoning paths.12Apache 2.0
- AlicenseCqualityDmaintenanceAn MCP server that enables persistent memory, structured thinking sessions, and project-based knowledge management for Claude. It includes specialized coding tools for package discovery and reinvention prevention by validating code against existing libraries and APIs.173MIT