Sponsored by Deepsite.site

GitHub Actions for Plane-MCP

Created By
Creodot8 months ago
✈ MCP For Plane.so
Content

✨ Plane.so MCP Server ✨

CI License: MIT npm version Node.js Version TypeScript BiomeJS PRs Welcome

A Model Context Protocol (MCP) server acting as a bridge to the Plane.so API. 🚀

This server allows MCP clients (like AI assistants or other tools) to interact with Plane.so resources (initially Issues) through defined tools.

📚 Table of Contents

👤 For Users

This section provides information for users who want to install and run the Plane.so MCP server to connect it with their MCP client (e.g., Cursor, Claude App).

⭐ Available Tools

The server exposes the following tools to interact with the Plane.so API. Tool names use underscores (e.g., plane_get_issue).

plane_get_issue

Retrieves details of a specific issue.

Parameters:

  • project_id (string, required): ID of the project containing the issue.
  • issue_id (string, required): ID of the issue to retrieve.

Example:

{
  "project_id": "your_project_id_here",
  "issue_id": "your_issue_id_here"
}

plane_create_issue

Creates a new issue in a specified project.

Parameters:

  • project_id (string, required): ID of the project where the issue should be created.
  • name (string, required): Title of the issue.
  • description_html (string, optional): HTML description of the issue (Plane API often requires this format).
  • priority (string, optional): Priority of the issue ("urgent", "high", "medium", "low", "none").
  • state_id (string, optional): ID of the state for this issue.
  • assignees (array, optional): Array of user IDs to assign to this issue.

Example:

{
  "project_id": "your_project_id_here",
  "name": "New Feature Request",
  "description_html": "<p>Details about the new feature.</p>",
  "priority": "medium"
}

plane_update_issue

Updates an existing issue in a project.

Parameters:

  • project_id (string, required): ID of the project containing the issue.
  • issue_id (string, required): ID of the issue to update.
  • name (string, optional): Updated title of the issue.
  • description_html (string, optional): Updated HTML description of the issue.
  • priority (string, optional): Updated priority of the issue.
  • state_id (string, optional): Updated state ID of the issue.
  • assignees (array, optional): Updated array of user IDs assigned to this issue.

Example:

{
  "project_id": "your_project_id_here",
  "issue_id": "your_issue_id_here",
  "priority": "high",
  "assignees": ["user_id_1"]
}

✅ Prerequisites

  • Node.js (v20 or higher recommended)
  • npm
  • A Plane.so account and an API Key -> Workspace Icon (top left) -> Settings -> API Tokens -> Add API Token
  • Plane.so Workspace slug -> https://app.plane.so/{workspace_slug}/ (Replace {workspace_slug} with your actual workspace slug)

🛠️ Installation

npm install

🚀 Usage

The server will start and listen for requests on its standard input (stdin) and send responses to its standard output (stdout). You need to configure your MCP client (like Cursor, Claude App, etc.) to launch this server process when needed.

For more details on the Model Context Protocol, visit modelcontextprotocol.io.

✨ Examples

Here are some example prompts you could give your AI assistant (once the server is configured in it):

  • "Get the details for issue BUG-123 in the WebApp project."
  • "Create a new high-priority issue in the API project titled 'Refactor authentication module' with the description 'Need to update the auth library.'"
  • "Update issue FEAT-45 in the Design project and assign it to user_abc."

Your assistant will use the appropriate tools (plane_get_issue, plane_create_issue, plane_update_issue) and likely ask for your confirmation before making changes.

🛡️ Security Considerations

  • API Key Security: Your PLANE_API_KEY stored in the .env file grants access to your Plane.so workspace. Keep this file secure and never commit it to version control.
  • Permissions: Ensure the API key used has the necessary permissions within Plane.so to perform the actions required by the tools (e.g., read issues, create issues, update issues).
  • User Approval: Most MCP clients will require your explicit approval before executing actions that modify data (like creating or updating issues), providing a safety layer.

🧑‍💻 For Developers

This section is for developers who want to contribute to the project, run tests, or use the development environment.

Development 🧑‍💻

npm run dev

Project Structure 📂

The project follows a domain-driven organization:

src/
├── configs/         # Environment and configuration
├── plane-client.js  # API client wrapper
├── schemas/         # Zod validation schemas
│   ├── tools.schema.ts    # Common tool schemas and utilities
│   ├── project.schema.ts  # Project-specific schemas 
│   └── issue.schema.ts    # Issue-specific schemas
├── services/        # Service layer for API interactions
│   ├── project.service.ts
│   └── issue.service.ts
├── tools/           # MCP tool definitions and handlers
│   ├── index.ts           # Tool registration
│   ├── project.tools.ts   # Project tool definitions
│   └── issue.tools.ts     # Issue tool definitions
└── types/           # TypeScript type definitions

Validation and Error Handling ✅

The project uses Zod for comprehensive validation:

  1. Schema Definition: Domain-specific schemas are defined in src/schemas/
  2. Schema Validation: The validateWithSchema utility ensures consistent validation
  3. Error Handling: Custom ValidationError class for structured error reporting

Example of using validation:

// In a service method
const validData = validateWithSchema(MySchema, inputData);
// validData is now correctly typed and validated

Adding New Tools 🔧

To add a new tool:

  1. Define the tool interface in the appropriate domain file (e.g., src/tools/issue.tools.ts)
  2. Add validation schemas in the domain schema file (e.g., src/schemas/issue.schema.ts)
  3. Implement the service method in the service file (e.g., src/services/issue.service.ts)
  4. Register the tool in src/tools/index.ts

Testing 🧪

The project includes multiple types of tests:

Unit Tests

Run unit tests (fast, no API calls):

npm run test:unit

Integration Tests

These tests make real API calls, so they need API credentials:

  1. Create a .env.test file with:
API_KEY=your_plane_api_key
WORKSPACE_SLUG=your_workspace_slug
  1. Run integration tests:
npm run test:local
  1. Quick endpoint check:
npm run check:local

Pre-commit Hooks

The pre-commit hooks only run linting and formatting, not tests. This ensures:

  • Faster commits
  • No API call requirements during development
  • No need for API credentials during regular development

When you want to run tests manually:

# Unit tests only
npm run test:unit

# All tests including integration (needs API credentials)
npm test

Linting and Formatting ✨

Check for linting and formatting errors using Biome:

npm run lint
npm run format:check

Apply formatting and lint fixes automatically:

npm run format

(Note: Formatting is also automatically applied on commit via Husky and lint-staged!)

🙌 Contributing

Contributions are welcome! Please see CONTRIBUTING.md for details on how to contribute, report bugs, or suggest features.

🤝 Code of Conduct

We are committed to providing a welcoming and inclusive environment. Please review our CODE_OF_CONDUCT.md.


📜 License

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

Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
Amap Maps高德地图官方 MCP Server
CursorThe AI Code Editor
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。
Context7Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
Serper MCP ServerA Serper 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.
WindsurfThe new purpose-built IDE to harness magic
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
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.
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.
DeepChatYour AI Partner on Desktop
Playwright McpPlaywright MCP server
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
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"
ChatWiseThe second fastest AI chatbot™
Tavily Mcp
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.