MCP.so
登录

Cursor Chat History Vectorizer & Dockerized Search MCP

@markelaugust74

代码仓库

关于 Cursor Chat History Vectorizer & Dockerized Search MCP

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

#api#docker#self-hosted#embeddings#chat-history#rag#fastapi#vector-database#local-llm#lancedb#ollama#mcp-server

基本信息

分类

开发工具

运行时

python

传输方式

stdio

发布者

markelaugust74

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "cursor-history-mcp-markelaugust74": {
      "command": "python",
      "args": [
        "cursor_history_extractor.py"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Cursor Chat History Vectorizer & Dockerized Search MCP?

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.

How to use Cursor Chat History Vectorizer & Dockerized Search MCP?

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.

Key features of Cursor Chat History Vectorizer & Dockerized Search MCP

  • Extracts user prompts from Cursor’s state.vscdb files
  • Generates embeddings using local Ollama (nomic-embed-text)
  • Stores vectors and metadata in LanceDB database
  • Provides Dockerized FastAPI search server
  • Supports vector similarity search via POST /search_chat_history
  • Includes health check endpoint (GET /health)

Use cases of Cursor Chat History Vectorizer & Dockerized Search MCP

  • Search past Cursor conversations to quickly recall previous solutions
  • Feed relevant chat history into LLMs for context-aware code assistance
  • Analyze coding patterns by querying vectorized user prompts

FAQ from Cursor Chat History Vectorizer & Dockerized Search MCP

What dependencies are required to run the extraction script?

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.

Where is the vector database stored?

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).

Does this tool extract AI model responses?

No. Currently only user prompts from the aiService.prompts key are extracted and stored. AI responses and other conversation details are not included.

How can I use a custom Cursor workspace

评论

开发工具 分类下的更多 MCP 服务器

mcp-excalidraw

yctimlin

MCP server and Claude Code skill for Excalidraw — programmatic canvas toolkit to create, edit, and export diagrams via AI agents with real-time canvas sync.

2.1K

test

prysmaticlabs

Go implementation of Ethereum proof of stake

3.8K

test

harlanc

A simple,high performance and secure live media server in pure Rust (RTMP[cluster]/RTSP/WebRTC[whip/whep]/HTTP-FLV/HLS).🦀

2.3K

Test

x1xhlol

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, Dia & v0. (And other Open Sou

141.7K

Sentry

modelcontextprotocol

Model Context Protocol Servers

88.1K