ThoughtMCP
Built on Node.js runtime, providing cognitive tools for AI systems including thinking modes, memory management, and reasoning analysis
Implemented in TypeScript for type-safe cognitive processing, offering structured thinking tools and memory systems for AI applications
Click on "Install 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., "@ThoughtMCPanalyze this business proposal using critical reasoning"
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.
ThoughtMCP
Production-Ready AI Cognitive Architecture with Human-Like Memory and Reasoning
ThoughtMCP provides AI systems with persistent memory, parallel reasoning, and metacognitive capabilities through the Model Context Protocol (MCP) — plus a web UI for exploring memories and reasoning.

Key Features
Five-Sector Memory: Episodic, Semantic, Procedural, Emotional, and Reflective memory types
Glass Box Observability: Real-time visualization of internal reasoning streams (Thought Console)
Cognitive Personalization: Configurable skepticism levels and thinking styles via User Profile
Visual Intelligence: 3D memory graph with Semantic Zooming and Level-of-Detail (LOD)
Parallel Reasoning: Four concurrent streams (Analytical, Creative, Critical, Synthetic)
Framework Selection: Eight systematic thinking frameworks with >80% selection accuracy
Metacognition: Confidence calibration, bias detection, emotion analysis
Production Ready: 75%+ test coverage, sub-200ms retrieval, PostgreSQL persistence
Related MCP server: Brain-MCP
Quick Start
# Clone and install
git clone https://github.com/keyurgolani/ThoughtMcp.git
cd ThoughtMcp
npm install
# Setup environment
cp .env.example .env
docker-compose up -d
npm run db:setup
# Build and start
npm run build
npm startMCP Tools
Category | Tools | Description |
Memory |
| Persistent five-sector memory |
Reasoning |
| Multi-stream reasoning |
Metacognitive |
| Self-monitoring and quality check |
MCP Configuration
{
"mcpServers": {
"thoughtmcp": {
"command": "node",
"args": ["/path/to/ThoughtMcp/dist/index.js"],
"env": {
"DATABASE_URL": "postgresql://user:pass@localhost:5432/thoughtmcp",
"OLLAMA_HOST": "http://localhost:11434"
}
}
}
}Web UI (Beta)
ThoughtMCP includes a web-based interface for visualizing memories and reasoning processes. The UI is currently in beta and under active development.
# Start the UI development server (from the repo root)
pnpm install
pnpm dev:ui # or: cd packages/ui && pnpm dev⚠️ Beta Notice: The UI is experimental and may have breaking changes between releases. Not recommended for production use yet.
Documentation
Guide | Description |
Getting started and basic usage | |
Tool schemas and examples | |
System design | |
Development workflow | |
Production deployment |
See docs/ for complete documentation.
Contributing
See CONTRIBUTING.md for guidelines.
License
MIT License - see LICENSE for details
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityFmaintenanceProvides advanced AI reasoning capabilities through step-by-step thinking framework, enabling complex problem-solving with dynamic thought revision, multi-path reasoning, and adaptive planning for sophisticated analysis tasks.Last updated1MIT
- AlicenseBqualityDmaintenanceProvides AI with persistent memory management including short-term memory (FIFO queue), long-term memory (graph-based storage with associations), and thought process management with multiple cognitive modes for continuous learning and reasoning.Last updated24343MIT
- FlicenseAqualityDmaintenanceEnables complex problem-solving through multi-modal reasoning, dynamic knowledge graphs, meta-cognitive reflection, and collaborative AI personas.Last updated14
- AlicenseAqualityDmaintenanceEnables multi-level reasoning with configurable depth levels, session-based state management, structured thought input, and real-time trace resources.Last updated1711MIT
Related MCP Connectors
Persistent AI entity framework with causal memory, emotional state, and identity.
Adversarial behavioural-bias engine — audits your decisions for cognitive biases via your own AI.
Chinese-first brain-inspired memory MCP — hybrid recall, 7-layer user profile, workspace assembly.
Appeared in Searches
- Improved thinking frameworks and methodologies beyond sequential thinking
- Information about TILT
- Slow thinking, distributed thinking, and reasoning abilities research
- A server for finding information about Chinese metaphysics and mysticism
- A tool for critical thinking and devil's advocate analysis of AI model plans
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/keyurgolani/ThoughtMcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server