Think MCP
Enables structured step-by-step reasoning with branching, revisions, and self-critique to help break down complex problems into manageable steps with confidence tracking and thought history search.
README
🧠Think MCP
MCP Server for structured sequential thinking. Helps LLMs break down complex problems into manageable steps with branching, revisions, and self-critique.
Features
- Sequential Thinking — Step-by-step reasoning with confidence tracking
- Branching & Revisions — Explore alternatives, fix mistakes
- Dead Ends Tracking — Remember rejected paths to avoid circular thinking
- Proactive Coach — Nudges for better thinking (low confidence, missing critique)
- Fuzzy Recall — Search through thought history with Fuse.js
Quick Start
Using npx (recommended)
npx @gofman3/think-mcp
Install globally
npm install -g @gofman3/think-mcp
think-mcp
MCP Configuration
Add to your MCP config (mcp.json):
{
"mcpServers": {
"think": {
"command": "npx",
"args": ["@gofman3/think-mcp"]
}
}
}
Or if installed globally:
{
"mcpServers": {
"think": {
"command": "think-mcp"
}
}
}
Tools
sequentialthinking
Primary tool for step-by-step reasoning.
{
thought: string, // Your current reasoning step
thoughtNumber: number, // Sequential: 1, 2, 3...
totalThoughts: number, // Estimate (auto-adjusts)
confidence?: number, // 1-10
nextThoughtNeeded: boolean,
isRevision?: boolean,
revisesThought?: number,
branchFromThought?: number,
branchId?: string,
subSteps?: string[], // Micro-plan (max 5)
alternatives?: string[] // Quick comparison (max 5)
}
extend_thought
Deep-dive into a specific thought without advancing.
{
targetThoughtNumber: number,
extensionType: 'critique' | 'elaboration' | 'optimization' | 'polish' | ...,
content: string,
impactOnFinalResult: 'low' | 'medium' | 'high' | 'blocker'
}
consolidate_and_verify
Final validation before answering.
{
winningPath: number[], // e.g., [1, 2, 5, 8]
summary: string,
verdict: 'ready' | 'needs_more_work'
}
recall_thought
Fuzzy search through thought history.
{
query: string,
scope?: 'current' | 'all',
searchIn?: 'thoughts' | 'extensions' | 'alternatives' | 'all',
limit?: number,
threshold?: number // 0-1, lower = stricter
}
reset_session
Clear all thoughts and start fresh.
export_session
Export session as Markdown or JSON.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.