What are the runtime requirements?
Ruby 3.1+ and the vector_mcp gem version 0.3.1 or later.
@sergiobayona
基本信息
Ruby server implementing Model Context Protocol (MCP) for filesystem operations using the https://rubygems.org/gems/vector_mcp gem.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"filesystem": {
"command": "ruby",
"args": [
"/Users/your_username/file_system_mcp/file_system_mcp.rb",
"/Users/your_username/Desktop",
"/path/to/other/allowed/dir"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Filesystem MCP Server is a Ruby server implementing the Model Context Protocol (MCP) for filesystem operations. It integrates with the vector_mcp gem to provide file and directory manipulation, search, and metadata tools while enforcing secure filesystem boundaries via MCP roots.
Install Ruby 3.1+ and bundler, clone the repository, run bundle install, then invoke with directories as arguments (e.g., ruby file_system_mcp.rb ~/Documents ~/Desktop). For secure mode, set the FILESYSTEM_MCP_API_KEY environment variable and add --enable-auth. Configure with Claude Desktop by editing claude_desktop_config.json.
Ruby 3.1+ and the vector_mcp gem version 0.3.1 or later.
It uses MCP roots to restrict access to only the directories specified as command-line arguments. Optional authentication adds API key verification.
Yes, by setting `FILESYSTEM_MCP_API_KEY` and passing `--enable-auth`, all operations require a valid API key.
Add it to `claude_desktop_config.json` under `mcpServers` with the command `ruby` and arguments pointing to the script and allowed directories.
Yes, the `edit_file` tool allows precise text replacements with a diff preview.
📄 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 Workspace Server: A secure Model Context Protocol server providing file, git, and GitHub tools for AI assistants within a sandboxed project directory.
MCP server that exposes a V8 JavaScript runtime as a tool for AI agents like Claude and Cursor. Supports persistent heap snapshots via S3 or local filesystem, and is ready for integration with modern AI development environments.
Manage your Hevy workouts, routines, folders, and exercise templates. Create and update sessions faster, organize plans, and search exercises to build workouts quickly. Stay synced with changes so your training log is always up to date.
📄 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.
评论