Knowledge Base MCP Server

This MCP server provides tools for listing and retrieving content from different knowledge bases.

Setup Instructions

These instructions assume you have Node.js and npm installed on your system.

Installing via Smithery

To install Knowledge Base Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @jeanibarz/knowledge-base-mcp-server --client claude

Manual Installation

Prerequisites

• Node.js (version 16 or higher)
• npm (Node Package Manager)

1. Clone the repository:

   git clone <repository_url>
   cd knowledge-base-mcp-server
   

2. Install dependencies:

   npm install
   

3. Configure environment variables:

   This server supports three embedding providers: Ollama (recommended for reliability), OpenAI and HuggingFace (fallback option).

   Option 1: Ollama Configuration (Recommended)

   • Set EMBEDDING_PROVIDER=ollama to use local Ollama embeddings
   • Install Ollama and pull an embedding model: ollama pull dengcao/Qwen3-Embedding-0.6B:Q8_0
   • Configure the following environment variables:

     EMBEDDING_PROVIDER=ollama
     OLLAMA_BASE_URL=http://localhost:11434  # Default Ollama URL
     OLLAMA_MODEL=dengcao/Qwen3-Embedding-0.6B:Q8_0          # Default embedding model
     KNOWLEDGE_BASES_ROOT_DIR=$HOME/knowledge_bases
     

   Option 2: OpenAI Configuration

   • Set EMBEDDING_PROVIDER=openai to use OpenAI API for embeddings
   • Configure the following environment variables:

     EMBEDDING_PROVIDER=openai
     OPENAI_API_KEY=your_api_key_here
     OPENAI_MODEL_NAME=text-embedding-ada-002
     KNOWLEDGE_BASES_ROOT_DIR=$HOME/knowledge_bases
     

   Option 3: HuggingFace Configuration (Fallback)

   • Set EMBEDDING_PROVIDER=huggingface or leave unset (default)
   • Obtain a free API key from HuggingFace
   • Configure the following environment variables:

     EMBEDDING_PROVIDER=huggingface          # Optional, this is the default
     HUGGINGFACE_API_KEY=your_api_key_here
     HUGGINGFACE_MODEL_NAME=sentence-transformers/all-MiniLM-L6-v2
     KNOWLEDGE_BASES_ROOT_DIR=$HOME/knowledge_bases
     

   Additional Configuration

   • The server supports the FAISS_INDEX_PATH environment variable to specify the path to the FAISS index. If not set, it will default to $HOME/knowledge_bases/.faiss.
   • Logging can be routed to a file by setting LOG_FILE=/path/to/logs/knowledge-base.log. Log verbosity defaults to info and can be adjusted with LOG_LEVEL=debug|info|warn|error.
   • You can set these environment variables in your .bashrc or .zshrc file, or directly in the MCP settings.

4. Build the server:

   npm run build
   

5. Add the server to the MCP settings:

   • Edit the cline_mcp_settings.json file located at /home/jean/.vscode-server/data/User/globalStorage/saoudrizwan.claude-dev/settings/.

   • Add the following configuration to the mcpServers object:

   • Option 1: Ollama Configuration

   "knowledge-base-mcp-ollama": {
     "command": "node",
     "args": [
       "/path/to/knowledge-base-mcp-server/build/index.js"
     ],
     "disabled": false,
     "autoApprove": [],
     "env": {
       "KNOWLEDGE_BASES_ROO
   

... View full README on GitHub