AI-powered intelligent code search with LLM reranking - MCP server for Claude, Cursor, Cline
npm install cheetah-grebSemantic code search for AI agents. Search your codebase using natural language queries.
Install Greb globally using pip or npm:
Python:
``bash`
pip install cheetah-greb
Node.js:
`bash`
npm install -g cheetah-greb
> ✅ No native compilation required! Greb uses WASM-based tree-sitter for AST parsing, which works everywhere without C++ compilation. This means it installs and runs on any platform - Windows, macOS, Linux, Docker, CI/CD - without build tools.
1. Go to Dashboard → API Keys
2. Click Create API Key
3. Copy the key (starts with grb_)
Add to your MCP client config (Cursor, Windsurf, Claude Code, etc.):
Python installation:
`json`
{
"mcpServers": {
"greb-mcp": {
"command": "greb-mcp",
"env": {
"GREB_API_KEY": "grb_your_api_key_here"
}
}
}
}
Node.js installation:
`json`
{
"mcpServers": {
"greb-mcp": {
"command": "greb-mcp-js",
"env": {
"GREB_API_KEY": "grb_your_api_key_here"
}
}
}
}
Mac/Linux (Python):
`bash`
claude mcp add --transport stdio greb-mcp --env GREB_API_KEY=grb_your_api_key_here -- greb-mcp
Windows PowerShell (Python):
`bash`
claude mcp add greb-mcp greb-mcp --transport stdio --env "GREB_API_KEY=grb_your_api_key_here"
Ask your AI assistant to search code naturally:
```
"Use greb mcp to find authentication middleware"
"Use greb mcp to find all API endpoints"
"Use greb mcp to look for database connection setup"