fs-mcp-server

boleyn/fs-mcp-server

3.3

If you are the rightful owner of fs-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

FS-MCP is a powerful Model Context Protocol server designed for intelligent file reading and semantic search capabilities.

FS-MCP, or the Universal File Reader & Intelligent Search MCP Server, is a robust server solution that leverages the Model Context Protocol (MCP) to provide advanced file reading and semantic search functionalities. It is designed to handle a wide range of file formats, including text files and various document types such as Word, Excel, and PDF. The server emphasizes security by restricting access to configured safe directories and supports high-performance operations through batch processing and intelligent caching. With its AI-powered vector search capabilities, FS-MCP can perform semantic searches across documents, making it a valuable tool for developers and organizations looking to enhance their file management and search capabilities. The server is compatible with multiple languages, including English and Chinese, and is built to run efficiently on systems with Python 3.12 or higher.

Features

  • Intelligent Text Detection: Automatically identifies text files without relying on file extensions.
  • Multi-Format Support: Handles text files and document formats such as Word, Excel, and PDF.
  • Security First: Restricted access to configured safe directories only.
  • Range Reading: Supports reading specific line ranges for large files.
  • Vector Search: Semantic search powered by AI embeddings.

Usages

usage with Claude Desktop

{
  "mcpServers": {
    "fs-mcp": {
      "command": "python",
      "args": ["main.py"],
      "cwd": "/path/to/fs-mcp",
      "env": {
        "SAFE_DIRECTORY": "/your/project/directory"
      }
    }
  }
}

Tools

  1. view_directory_tree

    Display directory structure in tree format.

  2. read_file_content

    Read file content with line range support.

  3. search_documents

    Intelligent semantic search across documents.

  4. rebuild_document_index

    Rebuild vector index for search.

  5. get_document_stats

    Get index statistics and system status.