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.

typescript

5

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

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

WisdomForge MCP Server provides a practical way to store, organize, and retrieve domain knowledge using a vector database. It integrates knowledge types like best practices, lessons learned, insights, and experiences, enabling fast, context-aware retrieval for knowledge work and decision making.

How to use

You run WisdomForge as an MCP server and connect your preferred MCP client to interact with the knowledge store. Use a local, HTTP, or stdio-based workflow to store knowledge, then query and retrieve relevant context when you need it. Your client can store domain knowledge into a vector collection and retrieve context to enrich your workflows.

Typical usage patterns include: 1) storing a new piece of knowledge (e.g., a best practice or lesson learned) into the configured vector database, 2) querying for related context to augment your current task, and 3) combining retrieved context with your working data to improve decisions, summaries, or recommendations.

How to install

Prerequisites: Node.js 20.x or later and npm 10.x or later. A vector database such as Qdrant or Chroma is required.

Step 1: Clone the project and navigate into the project directory.

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

Step 2: Install dependencies.

npm install

Step 3: Create a configuration file based on the example template.

cp .env.example .env

Step 4: Configure environment variables in the produced .env file. At minimum you need to set the database type and connection details for your vector database.

Step 5: Build the project to generate the executable output.

npm run build

Additional setup notes

To enable local HTTP server mode during development, set the HTTP_SERVER variable to true and provide a PORT for local use. In production (e.g., Smithery cloud deployment), use the standard MCP endpoint configuration instead.

Available tools

store_knowledge

Store domain-specific knowledge in a vector database so it can be retrieved later in context-rich queries.

retrieve_knowledge_context

Retrieve relevant domain knowledge from a vector database to augment current tasks or responses.