Knowledge Base Server is an MCP server that enables browsing and semantic search across local knowledge bases. It provides content retrieval and listing capabilities with vector-based similarity search. Key features of Knowledge Base Server: - List and retrieve documents from configurable local knowledge base directories - Semantic search with embeddings using FAISS vector indexes for fast similarity matching - Multiple embedding provider support: Ollama (local, recommended), OpenAI API, and HuggingFace - Structured knowledge management with environment-based configuration - Automatic document indexing and embedding generation

Knowledge Base MCP Server

[](https://smithery.ai/server/@jeanibarz/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

1. Clone the repository:

    git clone 
    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_ROOT_DIR": "/path/to/knowledge_bases",
        "EMBEDDING_PROVIDER": "ollama",
        "OLLAMA_BASE_URL": "http://localhost:11434",
        "OLLAMA_MODEL": "dengcao/Qwen3-Embedding-0.6B:Q8_0"
      },
      "description": "Retrieves similar chunks from the knowledge base based on a query using Ollama."
    },
    

* Option 2: OpenAI Configuration

    "knowledge-base-mcp-openai": {
      "command": "node",
      "args": [
        "/path/to/knowledge-base-mcp-server/build/index.js"
      ],
      "disabled": false,
      "autoApprove": [],
      "env": {
        "KNOWLEDGE_BASES_ROOT_DIR": "/path/to/knowledge_bases",
        "EMBEDDING_PROVIDER": "openai",
        "OPENAI_API_KEY": "YOUR_OPENAI_API_KEY",
        "OPENAI_MODEL_NAME": "text-embedding-ada-002"
      },
      "description": "Retrieves similar chunks from the knowledge base based on a query using OpenAI."
    },
    

* Option 3: HuggingFace Configuration

```json "knowledge-base-m