Trello MCP Server
Enables AI assistants to retrieve Trello card information by ID or link, providing access to card details including labels, members, due dates, and attachments through a standardized interface.
README
Trello MCP Server
A Model Context Protocol (MCP) server for interacting with the Trello API. This server enables AI assistants to retrieve information from Trello cards through a standardized interface.
Features
- Card Retrieval: Get Trello cards by ID or direct link
- Read-only Mode: Optional read-only mode for safe operations
- Type Safety: Built with TypeScript and Zod for robust type validation
- Debug Support: Optional debug logging for troubleshooting
Installation
Prerequisites
- Node.js ≥ 22.7.0
- npm ≥ 10.8.2
- A Trello account with API access
Setup
- Clone the repository:
git clone https://github.com/LorhanSohaky/trello-mcp.git
cd trello-mcp
- Install dependencies:
npm install
- Get your Trello API credentials:
- Visit Trello Developer API Keys
- Copy your API Key
- Generate a Token by clicking the "Token" link
Configuration
The server requires the following configuration parameters:
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
apiKey |
string | Yes | - | Your Trello API Key |
apiToken |
string | Yes | - | Your Trello API Token |
debug |
boolean | No | false | Enable debug logging |
readOnly |
boolean | No | false | Enable read-only mode |
Example Configuration
{
"apiKey": "your_trello_api_key_here",
"apiToken": "your_trello_api_token_here",
"debug": false,
"readOnly": true
}
Available Tools
getCardById
Retrieves a Trello card by its unique ID.
Parameters:
idCard(string): The ID of the Trello card to retrieve
Example:
{
"tool": "getCardById",
"input": { "idCard": "5f1a2b3c4d5e6f7g8h9i0j1k" }
}
getCardByLink
Retrieves a Trello card using its public link.
Parameters:
link(string): The URL of the Trello card to retrieve
Example:
{
"tool": "getCardByLink",
"input": { "link": "https://trello.com/c/abc123def/123-card-title" }
}
Development
This project uses Smithery for MCP server development and deployment.
Running in Development Mode
npm run dev
This will start the MCP server using Smithery's development tools with hot reloading.
Linting and Formatting
The project uses Biome for linting and formatting:
# Format and fix linting issues
npm run lint:fix
# Check for linting issues only
npm run lint
Project Structure
├── .editorconfig # Editor configuration
├── .gitignore # Git ignore rules
├── biome.json # Biome linter/formatter config
├── lefthook.yaml # Git hooks configuration
├── LICENSE.md # MIT license
├── package.json # Node.js dependencies and scripts
├── smithery.yaml # Smithery MCP server configuration
├── README.md # This file
└── src/
├── index.ts # Main MCP server implementation
└── trello/
├── index.ts # Trello API client
├── cards.ts # Cards API implementation
└── schemas.ts # Zod schemas for type validation
Usage with AI Assistants
This MCP server is designed to work with AI assistants that support the Model Context Protocol. Once configured, the assistant can use the provided tools to:
- Retrieve complete card information for project management tasks
- Get detailed card data when provided with Trello links
- Access all card properties including labels, members, due dates, and attachments
- Integrate Trello data into workflows and automation
API Response Format
Both tools return the complete card object as JSON, containing all available card information including:
{
"id": "card_id_here",
"name": "Card Title",
"desc": "Card Description",
"url": "https://trello.com/c/...",
"shortLink": "abc123",
"idBoard": "board_id",
"idList": "list_id",
"labels": [...],
"members": [...],
"due": "2025-01-01T00:00:00.000Z",
// ... and many other properties
}
Tools and Technologies
- Model Context Protocol (MCP): Standardized protocol for AI-tool integration
- Smithery: MCP server development and deployment platform
- TypeScript: Type-safe JavaScript development
- Zod: Runtime type validation and schema definition
- Biome: Fast linter and formatter
- Lefthook: Git hooks manager
Error Handling
The server includes robust error handling for:
- Invalid card IDs
- Malformed Trello links
- API authentication failures
- Network connectivity issues
Security
- The server supports read-only mode to prevent accidental modifications
- API credentials are required for all operations
- All inputs are validated using Zod schemas
Contributing
- Fork the repository
- Create a feature branch:
git checkout -b feature-name - Make your changes and add tests
- Run linting:
npm run lint:fix - Commit your changes:
git commit -am 'Add feature' - Push to the branch:
git push origin feature-name - Submit a pull request
License
This project is licensed under the MIT License - see the LICENSE.md file for details.
Support
For issues and questions:
- Open an issue on GitHub Issues
- Check the repository homepage for updates
This MCP server is built using the @modelcontextprotocol/sdk and follows MCP best practices for tool integration.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.