@markelaugust74
Basic information
API service to search vectorized Cursor IDE chat history using LanceDB and Ollama
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"cursor-history-mcp-markelaugust74": {
"command": "python",
"args": [
"cursor_history_extractor.py"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
This server extracts user prompts from Cursor IDE’s local SQLite databases, generates embeddings via a local Ollama instance (using nomic-embed-text), stores them in a LanceDB vector database, and provides a Dockerized FastAPI API for vector similarity search. It is designed for developers who want to make their Cursor chat history searchable for Retrieval Augmented Generation (RAG) or LLM-based analysis.
Two main steps: (1) Run python cursor_history_extractor.py on your host machine to create or update the LanceDB database at ./cursor_chat_history.lancedb. (2) Build the Docker image with docker build -t cursor-chat-search-api . and run the container with docker run -p 8001:8001 -v /absolute/path/to/cursor_chat_history.lancedb:/data/cursor_chat_history.lancedb -e OLLAMA_HOST="http://host.docker.internal:11434" cursor-chat-search-api. The search API will be accessible at http://localhost:8001.
state.vscdb filesPOST /search_chat_historyGET /health)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.
The extraction script creates the database at `./cursor_chat_history.lancedb` on the host machine. Inside the Docker container it is expected at `/data/cursor_chat_history.lancedb` (mounted via the `-v` flag).
No. Currently only user prompts from the `aiService.prompts` key are extracted and stored. AI responses and other conversation details are not included.
MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools
JiCo for Jira & Confluence: local MCP server for Jira Data Center - redacts personal data before the AI model, holds every write for approval
Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.
Pugi is an AI product team that builds, checks and publishes websites and apps. Its MCP server gives agents a passive website security check graded A+ to F (headers, TLS, cookies, exposed keys in scripts), free with a no
Comments