About File Search MCP
File Search MCP is an MCP server written in Rust that performs full-text keyword search across text files in a specified directory. It uses the Tantivy search engine to build in-memory indexes and skips binary files. It suits users who want AI assistants to search local text files.
Key features
- 01Full-text keyword search across text files in a directory
- 02Results ranked by relevance score
- 03Automatic text file detection that skips binary files
- 04In-memory index for temporary search operations
- 05Read the content of a specified text file
Use cases
- 01Ask an AI assistant to find keywords in a project directory
- 02Locate relevant passages across local notes or documents
- 03Read the contents of files returned by a search
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEFile Search MCP
A specialized Model Context Protocol (MCP) server for full-text search within a filesystem, built with Rust.
🔍 Overview
File Search MCP is a tool that provides powerful full-text search capabilities for text files in a specified directory. It uses the Tantivy search engine to index and search through text content efficiently.
This project implements the Model Context Protocol (MCP), making it compatible with AI assistants and other systems that support the protocol.
✨ Features
- Full-text search: Search for keywords in text files across a directory structure
- File content reader: Read and display the content of specific text files
- Smart file detection: Automatically identifies text files and skips binary files
- MCP integration: Works with systems that support the Model Context Protocol
- In-memory indexing: Creates fast, temporary indexes for search operations
- Score-based results: Returns search hits with relevance scores
🛠️ Technology Stack
- Rust: For performance, safety, and concurrency
- Tantivy: A full-text search engine library in Rust
- RMCP: Rust implementation of the Model Context Protocol
- Tokio: Asynchronous runtime for Rust
📋 Usage
First, install Rust sdk from here.
Clone this repository.
git clone [email protected]:Kurogoma4D/file-search-mcp.git
And add this to your MCP settings (in Cursor, Claude, ...).
- command:
<path-to-repo>/target/release/file-search-mcp
Replace <path-to-repo> to your cloned repository path.
🔄 How It Works
- The server indexes text files in the specified directory, excluding binary files
- It processes the content of text files and adds them to an in-memory Tantivy index
- When a search is performed, it queries the index for matches and ranks them by relevance
- Results are returned with file paths and relevance scores
- The file content reader tool allows you to view the content of any text file by providing its path
🛠️ Available Tools
Search Tool
- Description: Search for keywords in text files within a specified directory
- Parameters:
directory: Path to the directory to searchkeyword: Keyword to search for
File Content Reader Tool
- Description: Read and display the content of a specific file
- Parameters:
file_path: Path to the file to read
📄 License
MIT License
🙏 Acknowledgements
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.