FS-MCP: Universal File Reader & Intelligent Search MCP Server
@boleyn
About FS-MCP: Universal File Reader & Intelligent Search MCP Server
文件资料查找mcp服务
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"fs-mcp-server": {
"command": "uv",
"args": [
"sync"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is FS-MCP: Universal File Reader & Intelligent Search MCP Server?
FS-MCP: Universal File Reader & Intelligent Search MCP Server is a powerful MCP (Model Context Protocol) server that provides intelligent file reading and semantic search capabilities. It automatically detects text files, supports multiple document formats, and offers AI-powered vector search for developers using MCP-compatible clients.
How to use FS-MCP: Universal File Reader & Intelligent Search MCP Server?
Clone the repository, install dependencies with uv sync or pip install -r requirements.txt, and configure environment variables (e.g., SAFE_DIRECTORY, MAX_FILE_SIZE_MB, and embedding API keys) in a .env file. Start the server with python main.py, then connect via SSE at http://localhost:3002 or add the server to your MCP client configuration (e.g., Claude Desktop).
Key features of FS-MCP: Universal File Reader & Intelligent Search MCP Server?
- Intelligent text detection without relying on file extensions
- Multi-format support (text, Word, Excel, PDF, etc.) with automatic Markdown conversion
- Security-first access restricted to configured safe directories
- Line range reading for large files and quick file previews
- Semantic vector search using AI embeddings (BAAI/bge-m3 model)
- Multi-language support for English and Chinese content
Use cases of FS-MCP: Universal File Reader & Intelligent Search MCP Server?
- Search code semantically for “authentication logic” and find related “login verification” code
- Read specific line ranges from large log or source files efficiently
- Preview file contents and list files with pattern matching for quick exploration
- Rebuild vector indexes and retrieve index statistics for monitoring
FAQ from FS-MCP: Universal File Reader & Intelligent Search MCP Server
What file formats does the server support?
It supports auto-detected text files (.py, .js, .json, .md, etc.) and document formats (.docx, .xlsx, .pptx, .pdf, .odt, .ods, .odp) that are automatically converted to Markdown.
How do I restrict which directories the server can access?
Set the SAFE_DIRECTORY environment variable to the root directory you want to allow; the server will limit all file
Frequently asked questions
What file formats does the server support?
It supports auto-detected text files (`.py`, `.js`, `.json`, `.md`, etc.) and document formats (`.docx`, `.xlsx`, `.pptx`, `.pdf`, `.odt`, `.ods`, `.odp`) that are automatically converted to Markdown.
How do I restrict which directories the server can access?
Set the `SAFE_DIRECTORY` environment variable to the root directory you want to allow; the server will limit all file
Basic information
More Search MCP servers
Google Search Tool
web-agent-masterA Playwright-based Node.js tool that bypasses search engine anti-scraping mechanisms to execute Google searches. Local alternative to SERP APIs with MCP server integration.
DuckDuckGo Search MCP Server
nickclydeA Model Context Protocol (MCP) server that provides web search capabilities through DuckDuckGo, with additional features for content fetching and parsing.
Version 2.0 is here!!
mixelpixxMCP Server built for use with Claude Code, Claude Desktop, VS Code, Cline - enable google search and ability to follow links and research websites
Goalie Trademark Search MCP
goalie-mcpSearch & filter 14M+ USPTO trademark records from an AI agent. This is a trademark MCP server, not a TSDR lookup.
patent-literature-search-mcp
patsnapA professional tool for searching Patsnap’s global patent and literature databases using natural language, semantic, or keyword queries. It supports precise filtering and retrieves bibliographic data in Markdown format.
Comments