WisdomForge

@hadv

About WisdomForge

A powerful knowledge management system that forges wisdom from experiences, insights, and best practices. Built with Qdrant vector database for efficient knowledge storage and retrieval.

#mcp #rag #qdrant #qdrant-vector-database #mcp-server #modelcontextprotocol

Config

No standard config provided

This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.

Repository

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is WisdomForge?

WisdomForge is a knowledge management system that stores and retrieves experiences, insights, best practices, and lessons learned using a vector database. It integrates with the Model Context Protocol (MCP) for use in AI IDEs like Cursor and Claude Desktop, and works with Qdrant or Chroma for efficient embedding-based retrieval.

How to use WisdomForge?

Clone the repository, install dependencies, and build the project with npm install && npm run build.
Create a .env file from the template and configure required environment variables: DATABASE_TYPE (qdrant/chroma), COLLECTION_NAME, and the corresponding database URL/key. Optionally set HTTP_SERVER=true for HTTP mode.
Integrate with Cursor AI by adding the provided MCP configuration to your ~/.cursor/mcp.json file, or configure Claude Desktop following the run-mcp.sh script instructions.
Use the MCP tools store_knowledge and retrieve_knowledge_context to store and retrieve domain knowledge.

Key features of WisdomForge

Intelligent knowledge management and retrieval via vector search
Support for multiple knowledge types (best practices, lessons learned, insights, experiences)
Configurable database selection between Qdrant and Chroma
Uses Qdrant’s built-in FastEmbed for efficient embedding generation
Domain knowledge storage and retrieval for AI assistants
Deployable to Smithery.ai cloud platform

Use cases of WisdomForge

Storing and retrieving team best practices and lessons learned
Providing contextual domain knowledge to AI coding assistants
Managing institutional knowledge for onboarding and training
Powering knowledge retrieval in MCP‑compatible tools like Cursor and Claude

FAQ from WisdomForge

What runtime and dependencies does WisdomForge require?

It requires Node.js 20.x or later, npm 10.x or later, and either a Qdrant or Chroma vector database instance.

How do I configure which database to use?

Set the DATABASE_TYPE environment variable to qdrant or chroma, and supply the corresponding URL (and API key for Qdrant). The COLLECTION_NAME variable defines the vector collection.

Where is the knowledge data stored?

All knowledge is stored in the configured external vector database (Qdrant or Chroma). WisdomForge does not persist data locally.

What transport modes are supported?

WisdomForge supports MCP transport via shell scripts (run-wisdomforge-mcp.sh for Cursor, run-mcp.sh for Claude) and an optional HTTP server mode enabled by HTTP_SERVER=true.

How do I authenticate to a remote Qdrant instance?

If you are using Qdrant, set the QDRANT_API_KEY environment variable with your API key. No authentication is documented for Chroma in the README.

Frequently asked questions