FS-MCP: Universal File Reader & Intelligent Search MCP Server

Created By
boleyna year ago
文件资料查找mcp服务
Overview

What is FS-MCP?

FS-MCP is a Universal File Reader and Intelligent Search MCP Server that provides advanced capabilities for reading various file formats and performing semantic searches.

How to use FS-MCP?

To use FS-MCP, clone the repository, install the required dependencies, configure the environment variables, and start the server. Access the server at http://localhost:3002.

Key features of FS-MCP?

  • Intelligent text detection without relying on file extensions.
  • Multi-format support for text files and documents (Word, Excel, PDF, etc.).
  • Security features including restricted access to safe directories.
  • Range reading for large files.
  • Automatic document conversion to Markdown.
  • AI-powered semantic search capabilities.
  • High performance with batch processing and intelligent caching.
  • Multi-language support for English and Chinese content.

Use cases of FS-MCP?

  1. Reading and searching through large codebases.
  2. Extracting information from various document formats.
  3. Performing semantic searches across mixed-language content.

FAQ from FS-MCP?

  • What file formats does FS-MCP support?
    FS-MCP supports a wide range of formats including programming languages, configuration files, and document formats like Word and PDF.

  • Is FS-MCP secure?
    Yes, FS-MCP includes security features such as directory restrictions and path traversal protection.

  • Can I contribute to FS-MCP?
    Absolutely! Contributions are welcome, and you can find guidelines in the repository.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
boleyn
Star
3
Language
Python
License
MIT license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago