<div align="center">
<img src="./media/logo.png" alt="MCP Gearbox Logo"/>
<h1>MCP Gearbox</h1>
<h3><em>Setup high-quality MCP servers faster.</em></h3>
</div>
<p align="center">
<strong>CLI tool to quickly download, configure and deploy MCP servers for AI agents in minutes.</strong>
</p>
<p align="center">
<a href="https://github.com/rohitsoni007/mcp-kit/actions/workflows/release.yml"><img src="https://github.com/rohitsoni007/mcp-kit/actions/workflows/release.yml/badge.svg" alt="Release"/></a>
<a href="https://github.com/rohitsoni007/mcp-kit/stargazers"><img src="https://img.shields.io/github/stars/rohitsoni007/mcp-kit?style=social" alt="GitHub stars"/></a>
<a href="https://github.com/rohitsoni007/mcp-kit/blob/main/LICENSE"><img src="https://img.shields.io/github/license/github/spec-kit" alt="License"/></a>
<a href="https://github.com/rohitsoni007/mcp-kit/"><img src="https://img.shields.io/badge/docs-GitHub_Pages-blue" alt="Documentation"/></a>
</p>
---
## 🤔 Overview
MCP Gearbox is a powerful Python CLI dev-tools package that provides an interactive way to discover, download, and configure Model Context Protocol (MCP) servers from the official ecosystem. This AI-powered tool automatically configures model-context-protocol servers for your preferred AI coding agent with cross-platform support and intelligent configuration management.
## ⚡ Installation
### Using uv (recommended)
```bash
uv tool install mcp-cli --from git+https://github.com/rohitsoni007/mcp-kit
```
### To upgrade mcp-cli run:
```bash
uv tool install mcp-cli --force --from git+https://github.com/rohitsoni007/mcp-kit
```
### Using uvx (one-time execution)
```bash
uvx --from git+https://github.com/rohitsoni007/mcp-kit mcp-cli
```
### Development installation
```bash
git clone https://github.com/rohitsoni007/mcp-kit
cd mcp-kit
uv sync
```
## 🤖 Supported AI Agents
| Agent | Support | Notes |
|-------|---------|-------|
| **[GitHub Copilot](https://code.visualstudio.com)** | ✅ | |
| **[Continue](https://github.com/continuedev/continue)** | ✅ | |
| **[Kiro](https://kiro.dev)** | ✅ | |
| **[Cursor](https://cursor.sh)** | ✅ | |
| **[Claude Code](https://www.claude.com/product/claude-code)** | ✅ | |
| **[Gemini CLI](https://github.com/google-gemini/gemini-cli)** | ✅ | |
| **[Qoder](https://qoder.com)** | ⚠️ | Qoder [does not support](https://forum.qoder.com/t/project-specific-mcp-support/260) project-level MCP configuration |
| **[LM Studio](https://lmstudio.ai)** | ✅ | LM Studio does not need project-level MCP configuration |
## 🔧 MCP CLI Reference
The `mcp` command supports the following options:
### Commands
| Command | Description |
|-------------|----------------------------------------------------------------|
| `init` | Initialize MCP configuration (supports both project-specific and global configuration) |
### `mcp init` Arguments & Options
| Argument/Option | Type | Description |
|-----------------|----------|------------------------------------------------------------------------------|
| `<directory>` | Argument | Directory to initialize MCP configuration (use `.` for current directory, omit for global configuration) |
| `--agent`, `-a` | Option | AI agent to configure: `copilot`, `continue`, `kiro`, `cursor`, `claude`, `gemini`, `qoder`, or `lmstudio` |
### 🔧 Usage Examples
```bash
# Interactive Model Context Protocol server selection (choose from available AI agents)
# Configure MCP globally
mcp init
# Configure MCP globally for GitHub Copilot AI agent
mcp init -a copilot
# Configure MCP globally for Continue AI
mcp init -a continue
# Configure MCP globally for Kiro AI agent
mcp init -a kiro
# Configure MCP globally for Cursor AI agent
mcp init -a cursor
# Configure MCP globally for Qoder AI agent
mcp init -a qoder
# Configure MCP globally for Claude Code
mcp init -a claude
# Configure MCP globally for Gemini CLI
mcp init -a gemini
# Configure MCP globally for LM Studio AI agent
mcp init -a lmstudio
# Initialize MCP in current directory
mcp init .
# Initialize MCP in a new project directory
mcp init my-project
# Initialize MCP for GitHub Copilot AI agent in new project directory
mcp init my-project -a copilot
# Initialize MCP for Continue AI agent in new project directory
mcp init my-project -a continue
# Initialize MCP for Kiro AI agent in new project directory
mcp init my-project -a kiro
# Initialize MCP for Cursor AI agent in new project directory
mcp init my-project -a cursor
# Initialize MCP for Claude Code in new project directory
mcp init my-project -a claude
# Initialize MCP for Gemini CLI in new project directory
mcp init my-project -a gemini
# Initialize MCP for Qoder AI agent in new project directory
mcp init my-project -a qoder
# Show version
mcp --version
mcp -v
```
## 📚 Features
- 🎯 Interactive AI agent selection and configuration
- 📋 Interactive MCP server selection with intelligent filtering
- 🔧 Automatic model-context-protocol configuration file generation
- 🌍 Cross-platform Python dev-tools support (Windows, Linux, macOS)
- 📁 Automatic AI agent configuration path detection
- 🛠️ CLI-based workflow for seamless developer experience
## 🎯 Experimental Goals
- **Common MCP server for all AI agents** - Unified configuration and management across different AI platforms
- **Future edit feature** - Planned functionality to modify and update existing MCP configurations
## Development
### Project Structure
```
mcp-kit/
├── src/mcp_cli/ # Main CLI package
│ ├── __init__.py # Core CLI functionality
├── templates/ # Configuration templates
└── scripts/ # Build and deployment scripts
```
## 🔧 Requirements
- **Linux/macOS/Windows**
- [uv](https://docs.astral.sh/uv/) for package management
- [Python 3.11+](https://www.python.org/downloads/)
- [Git](https://git-scm.com/downloads)
If you encounter issues with an agent, please open an issue so we can refine the integration.
## 👥 Maintainers
- Rohit Soni ([@rohitsoni007](https://github.com/rohitsoni007))
## 💬 Support
For support, please open a [GitHub issue](https://github.com/rohitsoni007/mcp-kit/issues/new). We welcome bug reports, feature requests, and questions about using MCP CLI.
## 🙏 Acknowledgements
This project is based on the data from [Model Context Protocol Servers](https://github.com/modelcontextprotocol/servers) and [Github MCP Registry](https://github.com/mcp).
## Keywords
`MCP` `model-context-protocol` `ai` `cli` `dev-tools` `python` `artificial-intelligence` `developer-tools` `command-line` `automation` `ai-agents` `github-copilot` `continue` `configuration-management` `cross-platform`
## 📄 License
This project is licensed under the terms of the MIT open source license. Please refer to the [LICENSE](./LICENSE) file for the full terms.
Raw data
{
"_id": null,
"home_page": null,
"name": "mcp-gearbox",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.11",
"maintainer_email": null,
"keywords": "mcp, model-context-protocol, cli, project-initialization, ai-tools",
"author": "Rohit Soni",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/9e/4d/cca094a915a37658e13217375c9ffc1704dec92baff7fe8f91c0e7e4a2fe/mcp_gearbox-0.0.9.tar.gz",
"platform": null,
"description": "<div align=\"center\">\r\n <img src=\"./media/logo.png\" alt=\"MCP Gearbox Logo\"/>\r\n <h1>MCP Gearbox</h1>\r\n <h3><em>Setup high-quality MCP servers faster.</em></h3>\r\n</div>\r\n<p align=\"center\">\r\n <strong>CLI tool to quickly download, configure and deploy MCP servers for AI agents in minutes.</strong>\r\n</p>\r\n<p align=\"center\">\r\n <a href=\"https://github.com/rohitsoni007/mcp-kit/actions/workflows/release.yml\"><img src=\"https://github.com/rohitsoni007/mcp-kit/actions/workflows/release.yml/badge.svg\" alt=\"Release\"/></a>\r\n <a href=\"https://github.com/rohitsoni007/mcp-kit/stargazers\"><img src=\"https://img.shields.io/github/stars/rohitsoni007/mcp-kit?style=social\" alt=\"GitHub stars\"/></a>\r\n <a href=\"https://github.com/rohitsoni007/mcp-kit/blob/main/LICENSE\"><img src=\"https://img.shields.io/github/license/github/spec-kit\" alt=\"License\"/></a>\r\n <a href=\"https://github.com/rohitsoni007/mcp-kit/\"><img src=\"https://img.shields.io/badge/docs-GitHub_Pages-blue\" alt=\"Documentation\"/></a>\r\n</p>\r\n\r\n---\r\n\r\n## \ud83e\udd14 Overview\r\n\r\nMCP Gearbox is a powerful Python CLI dev-tools package that provides an interactive way to discover, download, and configure Model Context Protocol (MCP) servers from the official ecosystem. This AI-powered tool automatically configures model-context-protocol servers for your preferred AI coding agent with cross-platform support and intelligent configuration management.\r\n\r\n\r\n## \u26a1 Installation\r\n\r\n### Using uv (recommended)\r\n\r\n```bash\r\nuv tool install mcp-cli --from git+https://github.com/rohitsoni007/mcp-kit\r\n```\r\n\r\n### To upgrade mcp-cli run:\r\n```bash\r\nuv tool install mcp-cli --force --from git+https://github.com/rohitsoni007/mcp-kit\r\n```\r\n\r\n### Using uvx (one-time execution)\r\n\r\n```bash\r\nuvx --from git+https://github.com/rohitsoni007/mcp-kit mcp-cli\r\n```\r\n\r\n### Development installation\r\n\r\n```bash\r\ngit clone https://github.com/rohitsoni007/mcp-kit\r\ncd mcp-kit\r\nuv sync\r\n```\r\n\r\n\r\n## \ud83e\udd16 Supported AI Agents\r\n\r\n| Agent | Support | Notes |\r\n|-------|---------|-------|\r\n| **[GitHub Copilot](https://code.visualstudio.com)** | \u2705 | |\r\n| **[Continue](https://github.com/continuedev/continue)** | \u2705 | |\r\n| **[Kiro](https://kiro.dev)** | \u2705 | |\r\n| **[Cursor](https://cursor.sh)** | \u2705 | |\r\n| **[Claude Code](https://www.claude.com/product/claude-code)** | \u2705 | |\r\n| **[Gemini CLI](https://github.com/google-gemini/gemini-cli)** | \u2705 | |\r\n| **[Qoder](https://qoder.com)** | \u26a0\ufe0f | Qoder [does not support](https://forum.qoder.com/t/project-specific-mcp-support/260) project-level MCP configuration |\r\n| **[LM Studio](https://lmstudio.ai)** | \u2705 | LM Studio does not need project-level MCP configuration |\r\n\r\n## \ud83d\udd27 MCP CLI Reference\r\n\r\nThe `mcp` command supports the following options:\r\n\r\n### Commands\r\n\r\n| Command | Description |\r\n|-------------|----------------------------------------------------------------|\r\n| `init` | Initialize MCP configuration (supports both project-specific and global configuration) |\r\n\r\n### `mcp init` Arguments & Options\r\n\r\n| Argument/Option | Type | Description |\r\n|-----------------|----------|------------------------------------------------------------------------------|\r\n| `<directory>` | Argument | Directory to initialize MCP configuration (use `.` for current directory, omit for global configuration) |\r\n| `--agent`, `-a` | Option | AI agent to configure: `copilot`, `continue`, `kiro`, `cursor`, `claude`, `gemini`, `qoder`, or `lmstudio` |\r\n\r\n### \ud83d\udd27 Usage Examples\r\n\r\n```bash\r\n# Interactive Model Context Protocol server selection (choose from available AI agents)\r\n# Configure MCP globally\r\nmcp init\r\n\r\n# Configure MCP globally for GitHub Copilot AI agent\r\nmcp init -a copilot\r\n\r\n# Configure MCP globally for Continue AI\r\nmcp init -a continue\r\n\r\n# Configure MCP globally for Kiro AI agent\r\nmcp init -a kiro\r\n\r\n# Configure MCP globally for Cursor AI agent\r\nmcp init -a cursor\r\n\r\n# Configure MCP globally for Qoder AI agent\r\nmcp init -a qoder\r\n\r\n# Configure MCP globally for Claude Code\r\nmcp init -a claude\r\n\r\n# Configure MCP globally for Gemini CLI\r\nmcp init -a gemini\r\n\r\n# Configure MCP globally for LM Studio AI agent\r\nmcp init -a lmstudio\r\n\r\n# Initialize MCP in current directory\r\nmcp init .\r\n\r\n# Initialize MCP in a new project directory\r\nmcp init my-project\r\n\r\n# Initialize MCP for GitHub Copilot AI agent in new project directory\r\nmcp init my-project -a copilot\r\n\r\n# Initialize MCP for Continue AI agent in new project directory\r\nmcp init my-project -a continue\r\n\r\n# Initialize MCP for Kiro AI agent in new project directory\r\nmcp init my-project -a kiro\r\n\r\n# Initialize MCP for Cursor AI agent in new project directory\r\nmcp init my-project -a cursor\r\n\r\n# Initialize MCP for Claude Code in new project directory\r\nmcp init my-project -a claude\r\n\r\n# Initialize MCP for Gemini CLI in new project directory\r\nmcp init my-project -a gemini\r\n\r\n# Initialize MCP for Qoder AI agent in new project directory\r\nmcp init my-project -a qoder\r\n\r\n# Show version\r\nmcp --version\r\nmcp -v\r\n\r\n```\r\n## \ud83d\udcda Features\r\n\r\n- \ud83c\udfaf Interactive AI agent selection and configuration\r\n- \ud83d\udccb Interactive MCP server selection with intelligent filtering\r\n- \ud83d\udd27 Automatic model-context-protocol configuration file generation\r\n- \ud83c\udf0d Cross-platform Python dev-tools support (Windows, Linux, macOS)\r\n- \ud83d\udcc1 Automatic AI agent configuration path detection\r\n- \ud83d\udee0\ufe0f CLI-based workflow for seamless developer experience\r\n\r\n## \ud83c\udfaf Experimental Goals\r\n\r\n- **Common MCP server for all AI agents** - Unified configuration and management across different AI platforms\r\n- **Future edit feature** - Planned functionality to modify and update existing MCP configurations\r\n\r\n## Development\r\n\r\n### Project Structure\r\n\r\n```\r\nmcp-kit/\r\n\u251c\u2500\u2500 src/mcp_cli/ # Main CLI package\r\n\u2502 \u251c\u2500\u2500 __init__.py # Core CLI functionality\r\n\u251c\u2500\u2500 templates/ # Configuration templates\r\n\u2514\u2500\u2500 scripts/ # Build and deployment scripts\r\n```\r\n\r\n## \ud83d\udd27 Requirements\r\n\r\n- **Linux/macOS/Windows**\r\n- [uv](https://docs.astral.sh/uv/) for package management\r\n- [Python 3.11+](https://www.python.org/downloads/)\r\n- [Git](https://git-scm.com/downloads)\r\n \r\n If you encounter issues with an agent, please open an issue so we can refine the integration.\r\n\r\n## \ud83d\udc65 Maintainers\r\n\r\n- Rohit Soni ([@rohitsoni007](https://github.com/rohitsoni007))\r\n\r\n## \ud83d\udcac Support\r\n\r\nFor support, please open a [GitHub issue](https://github.com/rohitsoni007/mcp-kit/issues/new). We welcome bug reports, feature requests, and questions about using MCP CLI.\r\n\r\n## \ud83d\ude4f Acknowledgements\r\n\r\nThis project is based on the data from [Model Context Protocol Servers](https://github.com/modelcontextprotocol/servers) and [Github MCP Registry](https://github.com/mcp).\r\n\r\n## Keywords\r\n\r\n`MCP` `model-context-protocol` `ai` `cli` `dev-tools` `python` `artificial-intelligence` `developer-tools` `command-line` `automation` `ai-agents` `github-copilot` `continue` `configuration-management` `cross-platform`\r\n\r\n## \ud83d\udcc4 License\r\n\r\nThis project is licensed under the terms of the MIT open source license. Please refer to the [LICENSE](./LICENSE) file for the full terms.\r\n",
"bugtrack_url": null,
"license": null,
"summary": "A command-line interface tool for MCP server management and project initialization",
"version": "0.0.9",
"project_urls": {
"Changelog": "https://github.com/rohitsoni007/mcp-kit/blob/main/CHANGELOG.md",
"Documentation": "https://github.com/rohitsoni007/mcp-kit#readme",
"Homepage": "https://github.com/rohitsoni007/mcp-kit",
"Issues": "https://github.com/rohitsoni007/mcp-kit/issues",
"Repository": "https://github.com/rohitsoni007/mcp-kit"
},
"split_keywords": [
"mcp",
" model-context-protocol",
" cli",
" project-initialization",
" ai-tools"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "f923a6613c9e48705ee3b5dd70560796974742826261c0e64d5229264218491c",
"md5": "f6708ccbdc7ece3558b275f89fd8ceb4",
"sha256": "fdb32b2a53994771611c5d00e25fbdd031480c6d07a3cb514aa7f06f808af25f"
},
"downloads": -1,
"filename": "mcp_gearbox-0.0.9-py3-none-any.whl",
"has_sig": false,
"md5_digest": "f6708ccbdc7ece3558b275f89fd8ceb4",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.11",
"size": 15087,
"upload_time": "2025-11-01T09:52:44",
"upload_time_iso_8601": "2025-11-01T09:52:44.229504Z",
"url": "https://files.pythonhosted.org/packages/f9/23/a6613c9e48705ee3b5dd70560796974742826261c0e64d5229264218491c/mcp_gearbox-0.0.9-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "9e4dcca094a915a37658e13217375c9ffc1704dec92baff7fe8f91c0e7e4a2fe",
"md5": "3670d45dc5b5f789d88f20e3a7defe04",
"sha256": "dc537c306a6f95bfb72c14bd1f41df40159f2e62afccfe5e13fa668aa6512bac"
},
"downloads": -1,
"filename": "mcp_gearbox-0.0.9.tar.gz",
"has_sig": false,
"md5_digest": "3670d45dc5b5f789d88f20e3a7defe04",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.11",
"size": 17692,
"upload_time": "2025-11-01T09:52:45",
"upload_time_iso_8601": "2025-11-01T09:52:45.716706Z",
"url": "https://files.pythonhosted.org/packages/9e/4d/cca094a915a37658e13217375c9ffc1704dec92baff7fe8f91c0e7e4a2fe/mcp_gearbox-0.0.9.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-11-01 09:52:45",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "rohitsoni007",
"github_project": "mcp-kit",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "mcp-gearbox"
}
JSON
