Sponsored by Deepsite.site

MCP DevTools

Created By
DXHeroes9 months ago
MCP DevTools: A suite of Model Context Protocol servers enabling AI assistants to interact with developer tools and services
Content

MCP DevTools

License: MIT Beta Status

MCP (Model Context Protocol) DevTools is a collection of packages that enable AI assistants to interact with external tools and services through the Model Context Protocol.

✨ Highlights

  • 🔌 Seamless Integration: Connect AI assistants to external services and tools
  • 🛠 Extensible Framework: Easily create new integrations with the Model Context Protocol
  • 🔍 Powerful Interactions: Enable AI to access and manipulate data from external services
  • 📊 Robust Integrations: Comprehensive functionality for Jira and Linear
  • 🚀 Developer-Friendly: Simple setup with detailed documentation for the best developer experience

Note: This project is currently in beta (0.x.x versions). APIs may change between minor versions during the beta phase.

📦 Available Packages

PackageDescriptionStatus
@mcp-devtools/jiraJira MCP server integrationnpm version
@mcp-devtools/linearLinear MCP server integrationnpm version

🚀 Quick Start

Configuration in Cursor IDE

Jira Integration

  1. Open Cursor Settings → MCP
  2. Click "Add New MCP Server"
  3. Fill in the following details:
    • Name: Jira
    • Type: command
    • Command: env JIRA_URL=https://[YOUR_WORKSPACE].atlassian.net JIRA_API_MAIL=[YOUR_EMAIL] JIRA_API_KEY=[YOUR_API_KEY] npx -y @mcp-devtools/jira

Required Environment Variables:

  • JIRA_URL: Your Jira instance URL (e.g., https://your-company.atlassian.net)
  • JIRA_API_MAIL: Your Atlassian account email
  • JIRA_API_KEY: Your Atlassian API key (Create one here)

Linear Integration

  1. Open Cursor Settings → MCP
  2. Click "Add New MCP Server"
  3. Fill in the following details:
    • Name: Linear
    • Type: command
    • Command: env LINEAR_API_KEY=[YOUR_API_KEY] npx -y @mcp-devtools/linear

Required Environment Variables:

  • LINEAR_API_KEY: Your Linear API key (Create one in Linear app: Settings → API → Create Key)

Using Tools

Once configured, you can interact with tools through natural language commands in Cursor.

Jira Examples:

# Fetch a specific ticket
get ticket SCRUM-123

# Search for tickets
execute jql "project = SCRUM AND status = 'In Progress'"

# Get ticket details
read ticket SCRUM-123

# Create a new ticket
create ticket project=SCRUM summary="Fix login bug" description="Users can't log in" issuetype=Bug

Linear Examples:

# Get a specific issue
get_issue SS-33

# Search for issues
search_issues "priority is high" with limit 5

# Create a new issue
create_issue for team "eng" titled "Fix API response format" with description "The API is returning incorrect data format" and priority 1

# List teams
list_teams

For a complete list of available commands, refer to the package documentation:

📖 Documentation

🧩 Repository Structure

mcp-devtools/
├── core/                 # Infrastructure and utility packages
│   ├── typescript-config/  # Shared TypeScript configuration
│   └── http-client/        # HTTP client utilities
├── packages/             # Functional MCP server packages
│   ├── jira/               # Jira integration MCP server
│   │   └── README.md         # Package documentation
│   └── linear/             # Linear integration MCP server
│       └── README.md         # Package documentation
└── ...

🛠 Development

# Install dependencies
pnpm install

# Build all packages
pnpm build

# Development with auto-rebuild
pnpm dev

🤝 Contributing

Contributions are welcome! Please check our Contributing Guidelines for details.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🆘 Support

  • GitHub Issues: For bug reports and feature requests
  • Discussions: For questions and community support

Project Structure

mcp-devtools/
├── core/ # Infrastructure and utility packages
│ ├── typescript-config/ # Shared TypeScript configuration
│ └── http-client/ # HTTP client utilities
├── packages/ # Functional MCP server packages
│ ├── jira/ # Jira integration MCP server
│ └── linear/ # Linear integration MCP server
├── package.json # Root package configuration
└── pnpm-workspace.yaml # Workspace configuration

Development

Getting Started

This repository uses pnpm workspaces for package management. To get started:

  1. Install pnpm if you don't have it:

    npm install -g pnpm
    
  2. Install dependencies:

    pnpm install
    
  3. Build all packages:

    pnpm build
    

Development Workflow

For development with auto-rebuild:

pnpm dev

Publishing to NPM

This repository is set up with automated release management using release-please and GitHub Actions for publishing packages to npmjs.org.

Beta Status

All published packages are currently in beta status (0.x.x versions) and use the beta npm tag. During this phase:

  • Breaking changes may occur in minor version updates
  • Install the packages using: npm install @mcp-devtools/package-name@beta
  • When the project reaches stability, we will release version 1.0.0

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a workspace script:

pnpm inspector

The Inspector will provide a URL to access debugging tools in your browser.

Contributing

  1. Fork the repository
  2. Create a feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add some amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

Conventional Commits

This project uses Conventional Commits to automate versioning and changelog generation. Please format your commit messages following this pattern:

<type>[optional scope]: <description>

[optional body]

[optional footer(s)]

Types:

  • feat: A new feature
  • fix: A bug fix
  • docs: Documentation changes
  • style: Changes that don't affect the code's meaning (formatting, etc.)
  • refactor: Code changes that neither fix bugs nor add features
  • perf: Performance improvements
  • test: Adding or fixing tests
  • chore: Changes to the build process or auxiliary tools

Examples:

feat(jira): add comment creation endpoint
fix(http-client): resolve timeout issue
docs: update README with new setup instructions

Breaking changes should be indicated by adding an exclamation mark after the type/scope and describing the breaking change in the body of the commit message:

feat!: redesign http-client API

BREAKING CHANGE: The http-client API has been completely redesigned to improve usability.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Troubleshooting

Common Issues

  1. Connection Problems

    • Ensure your API credentials are correct
    • Check network connectivity to your service instances
    • Verify URLs and workspace names
  2. Permission Errors

    • Ensure your accounts have appropriate permissions for the actions you're attempting
    • API tokens may need specific permissions enabled in your account settings
  3. Command Not Found

    • If using npx, ensure you're connected to npm registry
    • For local installations, check that your package installation was successful

For more troubleshooting help, open an issue on our GitHub repository.

Roadmap

Future development plans for MCP DevTools include:

  • Additional service integrations (GitHub, Confluence, etc.)
  • Enhanced security features
  • Support for custom authentication methods
  • Expanded querying capabilities
  • Performance optimizations

Community and Support

  • GitHub Issues: For bug reports and feature requests
  • Discussions: For questions and community support
  • Contributing: See our contributing guidelines above

We welcome feedback and contributions from the community to help improve these tools.

Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
WindsurfThe new purpose-built IDE to harness magic
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
ChatWiseThe second fastest AI chatbot™
TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
DeepChatYour AI Partner on Desktop
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
Context7Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright McpPlaywright MCP server
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
Tavily Mcp
CursorThe AI Code Editor
Serper MCP ServerA Serper MCP Server
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
Amap Maps高德地图官方 MCP Server