File Search MCP indexes text files with Tantivy and returns relevant matches or file contents through a Rust MCP server.
File Search MCP indexes text files with Tantivy and returns relevant matches or file contents through a Rust MCP server.
The project uses Tantivy to build an in-memory index for text files in a selected directory. It skips binary files and ranks search hits by relevance. A separate reader returns file content for a supplied path. This makes it useful for an assistant answering questions over notes, source files or local documentation.
The repository documents a compiled release binary as the MCP command. Build the Rust project before using that path; a source checkout does not contain the release executable automatically. The server uses the Rust MCP SDK and Tokio runtime.
Choose a small directory with several known text files. Search for a distinctive word, inspect the ranked paths and read the relevant file. Then test a word that is absent. A relevance score ranks matches within the index; it does not certify that the highest result answers a particular question.
The documented index is temporary and lives in memory. Recreating a process can require indexing again, which affects startup time and memory for large collections. Supply a directory with appropriate scope, since the reader operates on local file paths. Keep source files and query results together when checking an answer that the assistant derives from the retrieved content.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| command | <path-to-repo>/target/release/file-search-mcp |
A Rust toolchain for building the project and access to the intended text directory.
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Chat with your second brain — search, read and write vault notes through the Local REST API.
Manage Proxmox hypervisors through a Model Context Protocol server, providing a clean interface for nodes, VMs, and containers.