Skip to main content
MCP Server
Sequential Thinking avatar

Sequential Thinking

by @modelcontextprotocol

Dynamic and reflective problem-solving through thought sequences

Share
720 stars TypeScript MIT Updated: 2025-05-11

Send to Your Agent

Copy this prompt and paste it into Claude, Cursor, or any MCP client to install instantly.

Install the Sequential Thinking MCP server for me.

Server: Sequential Thinking
Description: Dynamic and reflective problem-solving through thought sequences
Install command: npx -y @modelcontextprotocol/server-sequential-thinking

GitHub: https://github.com/modelcontextprotocol/servers/tree/main/src/sequentialthinking

Please install this MCP server and confirm when ready.

Paste into any AI agent with MCP support — works with Claude Desktop, Cursor, Cline, and more.

Quick Install

Config file: ~/Library/Application Support/Claude/claude_desktop_config.json

  1. Open Claude Desktop app
  2. Go to Settings → Developer → Edit Config
  3. Paste the config below into the file
  4. Restart Claude Desktop
{
  "mcpServers": {
    "sequential-thinking": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-sequential-thinking"
      ]
    }
  }
}

Add this to your ~/Library/Application Support/Claude/claude_desktop_config.json

Installation Methods

npx Run directly with npx
npx -y @modelcontextprotocol/server-sequential-thinking

Tools (1)

sequential_thinking

Facilitates step-by-step thinking process for problem-solving and analysis

Compatibility

Claude Desktop
Cursor
Cline
VS Code
Devin (formerly Windsurf)

About

An MCP server implementation that provides a tool for dynamic and reflective problem-solving through a structured thinking process.

Features

  • Break down complex problems into manageable steps
  • Revise and refine thoughts as understanding deepens
  • Branch into alternative paths of reasoning
  • Adjust total thoughts dynamically as scope becomes clearer
  • Generate and verify hypotheses

Tool: sequential_thinking

Facilitates a detailed, step-by-step thinking process for problem-solving and analysis.

Inputs:

  • thought (string): The current thinking step
  • nextThoughtNeeded (boolean): Whether another thought step is needed
  • thoughtNumber (integer): Current thought number
  • totalThoughts (integer): Estimated total thoughts needed
  • isRevision (boolean, optional): Whether this revises previous thinking
  • revisesThought (integer, optional): Which thought is being reconsidered
  • branchFromThought (integer, optional): Branching point thought number
  • branchId (string, optional): Branch identifier
  • needsMoreThoughts (boolean, optional): If more thoughts are needed

Use Cases

  • Complex problem decomposition — Break down multi-step challenges
  • Planning with revision — Design systems with room for course correction
  • Analysis that needs correction — Research that might reveal new information
  • Scope discovery — Problems where the full scope isn't clear initially
  • Context maintenance — Tasks requiring memory over multiple steps
  • Information filtering — Situations where irrelevant data needs filtering out

Related Resources

Compare LLM Pricing

This server works with Claude, GPT-4o, and other models. Compare API costs side-by-side to find the cheapest option for your workflow.