What are the prerequisites for MCP File Server?
Node.js version 16 or higher, npm or yarn, and Git (for Git functionality).
@Priyonuj
基本情報
A secure Model Context Protocol (MCP) server for file system operations. Enables AI assistants like Claude and Cursor to access, read, write, and manage files on your system with robust path validation and dynamic storage location management.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"file-server": {
"command": "node",
"args": [
"/path/to/mcp-file-server/mcp_server.js"
],
"disabled": false,
"autoApprove": [
"list_files",
"read_file",
"write_file",
"delete_file",
"set_base_directory",
"get_base_directory",
"git_command"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
MCP File Server is a Node.js application that implements a Model Context Protocol server for secure, standardized file system operations. It is designed for integration with AI assistants like Claude and developer tools like Cursor.
Install with npm install, then start with npm start. Configure via BASE_DIRECTORY environment variable or set the base directory directly from chat using the set_base_directory tool. Git commands can be executed through the git_command tool. Add the server as an MCP server in Claude Desktop or Cursor using a JSON configuration object.
Node.js version 16 or higher, npm or yarn, and Git (for Git functionality).
Use the `set_base_directory` tool by asking the AI assistant, for example “Set the base directory to C:/Users/username/Documents”. Provide an absolute path.
It performs robust path validation to prevent directory traversal attacks, normalizes and resolves file paths carefully, validates commands to prevent injection, and logs all operations to a debug file.
Yes. The modular architecture allows adding new services in the `services/` directory, registering new tools in `toolService.js`, and updating `mcp_server.js`.
Add a JSON configuration object like the one in the README under “Configuration Object Example”, specifying the command, script path, and auto-approved tools.
📄 The PDF intelligence layer for AI agents — Agent Document Twin, evidence-first extraction, visual crops, OCR provenance, trust reports, and benchmark-gated releases. MCP server for Claude, Cursor, VS Code, and any MCP client.
MCP server for working with PDF files
MCP Workspace Server: A secure Model Context Protocol server providing file, git, and GitHub tools for AI assistants within a sandboxed project directory.
filesystem MCP server for accessing WSL distributions from Windows

DeviceLink lets you share folders from your computer with AI assistants, securely and in real-time. Nothing is uploaded. Your files stay on your machine, and are only accessible while the device sharing them is connected
コメント