Cursor Chat History Vectorizer & Dockerized Search MCP Server

API service to search vectorized Cursor IDE chat history using LanceDB and Ollama

Local serverstdioPython

What is the Cursor Chat History Vectorizer & Dockerized Search MCP Server?

API service to search vectorized Cursor IDE chat history using LanceDB and Ollama

What you get

Vectorize your Cursor chat history and serve it via a simple search API.

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

How to install the Cursor Chat History Vectorizer & Dockerized Search MCP Server

{
  "mcpServers": {
    "cursor-history-mcp-markelaugust74": {
      "command": "uvx",
      "args": ["ollama"],
      "env": {
        "WORKSPACE_STORAGE_PATH": "your-value",
        "OLLAMA_HOST": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
WORKSPACE_STORAGE_PATHFilesystem location the server is allowed to use.Optional
OLLAMA_HOSTEndpoint or connection string the server talks to.Optional

Frequently asked questions

Python 3.7+, a running Ollama instance with the `nomic-embed-text:latest` model pulled, and the Python packages `ollama`, `lancedb`, `pyarrow`, `pandas`, and `python-dotenv` (installed via `pip install -r requirements.txt`). Docker Desktop or Docker Engine is needed for the API container.