Sequential Thinking

reasoningplanningreferencethinking

Summary

A tool for dynamic, reflective problem-solving through structured, revisable sequences of thoughts.

Features

Structured step-by-step reasoning
Revise earlier thoughts
Branch into alternatives
Track thought progress
Model-agnostic

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

Open your agent's MCP configuration file.
Merge the snippet below into it.
Restart the agent — the "Sequential Thinking" tools will be available.

{
  "mcpServers": {
    "sequential-thinking": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-sequential-thinking"
      ]
    }
  }
}

Claude Code

Add the server with a single CLI command.

claude mcp add sequential-thinking -- npx -y @modelcontextprotocol/server-sequential-thinking

Claude Desktop

Add the server to claude_desktop_config.json (Settings → Developer → Edit Config).

{
  "mcpServers": {
    "sequential-thinking": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-sequential-thinking"
      ]
    }
  }
}

Description

The reference Sequential Thinking MCP server. It exposes a single tool that helps a model break a hard problem into an explicit, revisable chain of thoughts — branching, revising, and continuing as understanding evolves. Useful for planning and multi-step reasoning tasks.