Skip to content
Conduit

mcp server

oh-my-mcp

A powerful Model Context Protocol (MCP) server offering a broad set of practical tools across multiple categories — built with FastMCP.一款强大的模型上下文协议（MCP）服务器，提供覆盖多个类别的丰富实用工具——基于 FastMCP 构建。

quyansiyuanwang/oh-my-mcpcommunitylistedunreviewednot running here yet
Use tool

Set up

Runs on your computer. Pick your agent and operating system.

Before you start

  • uv (`curl -LsSf https://astral.sh/uv/install.sh | sh`)
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "oh-my-mcp": {
      "command": "uvx",
      "args": [
        "oh-my-mcp"
      ]
    }
  }
}

same format Cursor, GitHub Copilot CLI, Junie, JetBrains AI Assistant, Augment (Auggie CLI), Factory Droid, Kiro, Devin CLI +12

Values in angle brackets are placeholders. Restart Claude Desktop after editing its config.Claude Desktop docs

README

synced Oct 14, 2026

oh-my-mcp

English | 中文

A powerful Model Context Protocol (MCP) server with 154 practical tools across 11 categories, built using FastMCP.

Build and Release Tests Lint Python 3.12+ License: MIT Platform

🚀 Features

oh-my-mcp provides tools for:

  • 🌐 Browser Automation (33 tools): Selenium-based browser automation: navigation, interaction, screenshots, JS execution, console logs, cookies, network monitoring, form filling, multi-tab management
  • 📦 Compression (5 tools): ZIP/TAR compression and extraction with security features
  • 🖥️ Computer Use (26 tools): AI desktop control: screen capture (multi-monitor, base64/file), mouse control (move/click/drag/scroll), keyboard input (typing/keys/hotkeys), clipboard access, window management, safety failsafe configuration
  • 📊 Data Processing (15 tools): JSON, CSV, XML, YAML, TOML parsing and manipulation
  • ⚡ Command Execution (5 tools): Secure allowlist-based command execution: run whitelisted commands with argument sanitization, timeout protection, output size limits and audit logging; manage the persistent command allowlist
  • 📁 File System (16 tools): Read, write, search files and directories, file comparison
  • 🤖 Subagent AI Orchestration (6 tools): Delegate subtasks to external AI models with parallel execution and cost tracking
  • 💻 System (11 tools): System info, CPU/memory monitoring, environment variables
  • 📝 Text Processing (9 tools): Regex, encoding, email/URL extraction, text similarity
  • 🛠️ Utilities (10 tools): UUID, hashing, date/time operations, math, password generation
  • 🌐 Web & Network (18 tools): Web search, page fetching, HTML parsing, downloads, HTTP API client, DNS lookup

📚 Documentation

The full index lives in docs/README.md — every topic is available in English (X.md, default) and Chinese (X.zh.md). Highlights:

Document
InstallationINSTALLATION.md / 中文
Tool Reference (all 146 tools)TOOL_REFERENCE.md / 中文
Computer Use GuideCOMPUTER_USE_GUIDE.md / 中文
Setup Guide (Claude Desktop)SETUP_GUIDE.md / 中文
Command ExecutionCONFIGURATION.md · see Tool Reference
Build GuideBUILD.md / 中文
ArchitectureARCHITECTURE.md / 中文
Subagent GuideSUBAGENT_GUIDE.md / 中文
ContributingCONTRIBUTING.md / 中文
ChangelogCHANGELOG.md / 中文

Tool counts and descriptions in the docs are generated from code — see Documentation Generation.

📦 Installation

git clone https://github.com/quyansiyuanwang/oh-my-mcp.git
cd oh-my-mcp
pip install -e .            # or: uv sync --all-extras

Configure Claude Desktop:

python -m mcp_server.cli.config --claude

Start the server:

python -m mcp_server.main

Details: Installation Guide and Setup Guide.

🔧 Configuration

Logging

Logs are configured in mcp_server/utils.py — level, destinations and format.

Security Features

  • Path validation: prevents path traversal attacks
  • Safe evaluation: math expressions only allow whitelisted operations
  • Masked values: sensitive environment variables are masked
  • Confirmation required: file deletion requires confirm=True
  • Allowlisted execution: commands only run after explicit trust
  • Retry logic: network operations retry up to 3 times

🛡️ Error Handling

All tools return JSON with descriptive messages instead of raising:

  • ValidationError — invalid input parameters
  • NetworkError — network request failures
  • FileOperationError — file system errors
  • DataProcessingError — data parsing/conversion errors

📝 Development

Project Structure

oh-my-mcp/
├── pyproject.toml               # Dependencies & tool config
├── configure.py                 # Interactive setup wizard
└── src/
    └── mcp_server/
        ├── main.py              # Server entry point
        ├── utils.py             # Infrastructure & utilities
        ├── command_executor.py  # Secure command execution
        ├── cli/config.py        # Configuration generator
        └── tools/               # Tool plugins (11 categories, auto-discovered)

Full layout: PROJECT_STRUCTURE.md.

Adding New Tools

from mcp_server.tools.registry import tool_handler

@tool_handler
def your_tool(param: str) -> str:
    """Tool description.

    Args:
        param: Parameter description

    Returns:
        Return value description
    """
    ...

Documentation Generation

Tool counts and descriptions in the docs are generated from code (AST analysis of @tool_handler docstrings + each plugin's config.yaml). After adding, removing, or renaming tools run:

python scripts/docs/generate_docs.py --write

CI verifies docs are fresh with --check and fails if they are out of date. Generated fragments live between <!-- DOCGEN:...:start/end --> markers; do not edit inside them.

🤝 Contributing

See CONTRIBUTING.md. Client configuration details: SETUP_GUIDE.md.

📄 License

This project is provided as-is for educational and practical use.

🔗 Links

Enjoy oh-my-mcp! 🚀

↑↓ navigate openesc close