Which integrations are available for this server?

Utilizes [.env](/mcp/servers/integrations/dotenv) files for environment variable configuration Supports cloning the WisdomForge repository from [GitHub](/mcp/servers/integrations/github) for installation and setup Requires [Node.js](/mcp/servers/integrations/node-dot-js) 20.x or later as a prerequisite for running the server Uses [npm](/mcp/servers/integrations/npm) for dependency management and build processes Mentions [nvm](/mcp/servers/integrations/nvm) as an option for ensuring the correct Node.js version when using Cursor AI IDE

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.

Features

Intelligent knowledge management and retrieval
Support for multiple knowledge types (best practices, lessons learned, insights, experiences)
Configurable database selection via environment variables
Uses Qdrant's built-in FastEmbed for efficient embedding generation
Domain knowledge storage and retrieval
Deployable to Smithery.ai platform

Related MCP server: Memory MCP Server

Prerequisites

Node.js 20.x or later (LTS recommended)
npm 10.x or later
Qdrant or Chroma vector database

Installation

Clone the repository:

git clone https://github.com/hadv/wisdomforge cd wisdomforge

Install dependencies:

npm install

Create a .env file in the root directory based on the .env.example template:

cp .env.example .env

Configure your environment variables in the .env file:

Required Environment Variables

Database Configuration

DATABASE_TYPE: Choose your vector database (qdrant or chroma)
COLLECTION_NAME: Name of your vector collection
QDRANT_URL: URL of your Qdrant instance (required if using Qdrant)
QDRANT_API_KEY: API key for Qdrant (required if using Qdrant)
CHROMA_URL: URL of your Chroma instance (required if using Chroma)

Server Configuration

HTTP_SERVER: Set to true to enable HTTP server mode
PORT: Port number for local development only (default: 3000). Not used in Smithery cloud deployment.

Example .env configuration for Qdrant:

DATABASE_TYPE=qdrant COLLECTION_NAME=wisdom_collection QDRANT_URL=https://your-qdrant-instance.example.com:6333 QDRANT_API_KEY=your_api_key HTTP_SERVER=true PORT=3000 # Only needed for local development

Build the project:

npm run build

AI IDE Integration

Cursor AI IDE

Add this configuration to your ~/.cursor/mcp.json or .cursor/mcp.json file:

{ "mcpServers": { "wisdomforge": { "command": "/bin/zsh", "args": [ "/path/to/wisdomforge/run-wisdomforge-mcp.sh" ] } } }

Replace the following placeholders in the configuration:

YOUR_API_KEY: Your Smithery API key
YOUR_COLLECTION_NAME: Your Qdrant collection name
YOUR_QDRANT_URL: Your Qdrant instance URL
YOUR_QDRANT_API_KEY: Your Qdrant API key

Note: Make sure you have Node.js installed and npx available in your PATH. If you're using nvm, ensure you're using the correct Node.js version by running nvm use --lts before starting Cursor.

Claude Desktop

Add this configuration in Claude's settings:

{ "processes": { "knowledge_server": { "command": "/path/to/your/project/run-mcp.sh", "args": [] } }, "tools": [ { "name": "store_knowledge", "description": "Store domain-specific knowledge in a vector database", "provider": "process", "process": "knowledge_server" }, { "name": "retrieve_knowledge_context", "description": "Retrieve relevant domain knowledge from a vector database", "provider": "process", "process": "knowledge_server" } ] }