An MCP server that provides structured, token-efficient code search and file discovery for AI agents. It wraps ripgrep and fd to search file contents, find files by name or pattern, and count matches with JSON output.
From the registry: MCP server for code search (ripgrep + fd) with structured, token-efficient output
Please install the `search` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install ripgrep** — Required for the `search` and `count` tools. Provides the `rg` executable used by the server. (https://github.com/BurntSushi/ripgrep},{)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@paretools/search"]
Note: This server is distributed as an npm package and is part of the Pare suite, but this README provides standalone install/config instructions for this specific server. No environment variables are documented.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.MCP server for searching Airweave collections with natural language queries.