cursor-search-mcp
Exposes Cursor's semantic code search through MCP, enabling tools like codebase_search to query indexed repos.
README
Cursor Search MCP
Expose Cursor's semantic code search through MCP.
Requirements
- Python 3.10+
- Cursor installed and logged in (once)
- uv or pip
Cursor must index the repo. Open it in Cursor and wait for indexing to finish.
Install
git clone https://github.com/philipk19238/cursor-search-mcp.git
cd cursor-search-mcp
uv pip install -e .
Run
cursor-search-mcp
# or
fastmcp run src/cursor_search_mcp/server.py
MCP Client Setup
Claude Code
claude mcp add cursor-search -- \
env CURSOR_WORKSPACE_PATH=/path/to/your/repo \
uv run --directory /path/to/cursor-search-mcp cursor-search-mcp
Or add to ~/.claude.json:
{
"mcpServers": {
"cursor-search": {
"command": "env",
"args": [
"CURSOR_WORKSPACE_PATH=/path/to/your/repo",
"uv", "run", "--directory", "/path/to/cursor-search-mcp",
"cursor-search-mcp"
]
}
}
}
OpenAI Codex
codex mcp add cursor-search -- \
env CURSOR_WORKSPACE_PATH=/path/to/your/repo \
uv run --directory /path/to/cursor-search-mcp cursor-search-mcp
Or add to ~/.codex/config.toml:
[mcp_servers.cursor-search]
command = "env"
args = [
"CURSOR_WORKSPACE_PATH=/path/to/your/repo",
"uv", "run", "--directory", "/path/to/cursor-search-mcp",
"cursor-search-mcp"
]
OpenCode
Add to opencode.json:
{
"mcp": {
"cursor-search": {
"type": "local",
"command": "env",
"args": [
"CURSOR_WORKSPACE_PATH=/path/to/your/repo",
"uv", "run", "--directory", "/path/to/cursor-search-mcp",
"cursor-search-mcp"
],
"enabled": true
}
}
}
Config (optional)
CURSOR_REPO_NAME/CURSOR_REPO_OWNERCURSOR_WORKSPACE_PATHCURSOR_ACCESS_TOKENCURSOR_CONFIG_PATHCURSOR_VERSION
If the server is launched outside the repo, set CURSOR_WORKSPACE_PATH to the
indexed workspace root. Startup fails if the workspace is not indexed.
Tools
codebase_search: semantic search in the indexensure_codebase_indexed: trigger index creationrefresh_repo_info: refresh repo detectionlist_indexed_repos: show locally indexed repos
Acknowledgements
Based on reverse engineering work from:
- cursor-rpc - Go library with protobuf definitions
- cursor-unchained - Cursor API reverse engineering
Disclaimer
Unofficial project; Cursor may change the API.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.