Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
MCP server for Trello in Claude Code and Gemini CLI
This repository provides an MCP server that connects Trello to AI assistants. Once configured, your client can search boards, inspect cards, create and move cards, add comments, and read lists, labels, attachments, and activity history.
Builders who want their agent to manage Trello boards, cards, and lists from Claude Code, Gemini CLI, or any MCP client.
You can handle Trello work through your agent instead of switching back and forth between Trello and your editor.
What it does
Search across Trello
Searches boards, cards, members, and organizations with a single tool.
Board and card management
Gets board details, creates cards, updates cards, and moves cards between lists.
Collaboration actions
Adds comments, reads member details, and tracks card activity history.
Organization tools
Creates lists and reads labels, checklists, attachments, and cards in a list or board.
MCP client setup
Includes config examples for Claude Desktop, Claude Code, Gemini CLI, and other stdio MCP clients.
How to get it
- 1Clone the repository
git clone https://github.com/kocakli/trello-desktop-mcp.git cd trello-desktop-mcp
- 2Install dependencies
npm install
- 3Build the project
npm run build
- 4Add the server using the Claude Code CLI
claude mcp add trello -- node /absolute/path/to/trello-desktop-mcp/dist/index.js \ -e TRELLO_API_KEY=your-api-key-here \ -e TRELLO_TOKEN=your-token-here
- 5Once configured, you can use natural language with your AI assistant to interact with…
"Show me all my Trello boards" "Create a new card called 'Update documentation' in the To Do list" "Move card X from In Progress to Done" "Add a comment to card Y saying 'This is ready for review'" "Search for all cards with 'bug' in the title" "Show me all cards assigned to me"
README
Trello MCP
A Model Context Protocol (MCP) server that provides comprehensive Trello integration for any MCP-compatible client — including Claude Desktop, Claude Code, Gemini CLI, and more. This server enables AI assistants to interact with Trello boards, cards, lists, and more through a secure local connection.
Features
🔍 Search & Discovery
- Universal Search: Search across all Trello content (boards, cards, members, organizations)
- User Boards: Get all boards accessible to the current user
- Board Details: Retrieve detailed information about boards including lists and cards
📝 Card Management
- Create Cards: Add new cards to any list with descriptions, due dates, and assignments
- Update Cards: Modify card properties like name, description, due dates, and status
- Move Cards: Transfer cards between lists to update workflow status
- Get Card Details: Fetch comprehensive card information including members, labels, and checklists
💬 Collaboration
- Add Comments: Post comments on cards for team communication
- Member Management: View board members and member details
- Activity History: Track card actions and changes
📋 Organization
- List Management: Create new lists and get cards within specific lists
- Labels: View and manage board labels for categorization
- Checklists: Access card checklists and checklist items
- Attachments: View card attachments and linked files
Installation
Prerequisites
- Node.js 18+ installed
- An MCP-compatible client (Claude Desktop, Claude Code, Gemini CLI, etc.)
- Trello account with API credentials
Setup Steps
-
Clone the repository
git clone https://github.com/kocakli/trello-desktop-mcp.git cd trello-desktop-mcp -
Install dependencies
npm install -
Build the project
npm run build -
Get Trello API credentials
- Visit https://trello.com/app-key
- Copy your API Key
- Generate a Token (never expires, read/write access)
-
Configure your MCP client
Choose the instructions for your client below:
Claude Desktop
Edit your Claude Desktop configuration file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
Add the Trello MCP server:
{ "mcpServers": { "trello": { "command": "node", "args": ["/absolute/path/to/trello-desktop-mcp/dist/index.js"], "env": { "TRELLO_API_KEY": "your-api-key-here", "TRELLO_TOKEN": "your-token-here" } } } }Then restart Claude Desktop.
Claude Code (CLI)
Add the server using the Claude Code CLI:
claude mcp add trello -- node /absolute/path/to/trello-desktop-mcp/dist/index.js \ -e TRELLO_API_KEY=your-api-key-here \ -e TRELLO_TOKEN=your-token-hereOr add it to your project's
.mcp.json:{ "mcpServers": { "trello": { "command": "node", "args": ["/absolute/path/to/trello-desktop-mcp/dist/index.js"], "env": { "TRELLO_API_KEY": "your-api-key-here", "TRELLO_TOKEN": "your-token-here" } } } }Gemini CLI
Edit your Gemini CLI settings file at
~/.gemini/settings.json:{ "mcpServers": { "trello": { "command": "node", "args": ["/absolute/path/to/trello-desktop-mcp/dist/index.js"], "env": { "TRELLO_API_KEY": "your-api-key-here", "TRELLO_TOKEN": "your-token-here" } } } }Other MCP Clients
Any MCP-compatible client that supports stdio transport can use this server. You need to configure it to:
- Run
node /absolute/path/to/trello-desktop-mcp/dist/index.js - Set environment variables
TRELLO_API_KEYandTRELLO_TOKEN
Refer to your client's documentation for the exact configuration format.
- macOS:
-
Restart your MCP client to pick up the new configuration.
Available Tools
The MCP server provides 19 tools organized into three phases:
Phase 1: Essential Tools
trello_search- Universal search across all Trello contenttrello_get_user_boards- Get all boards accessible to the current userget_board_details- Get detailed board information with lists and cardsget_card- Get comprehensive card detailscreate_card- Create new cards in any list
Phase 2: Core Operations
update_card- Update card propertiesmove_card- Move cards between liststrello_add_comment- Add comments to cardstrello_get_list_cards- Get all cards in a specific listtrello_create_list- Create new lists on boards
Phase 3: Advanced Features
trello_get_board_cards- Get all cards from a board with filteringtrello_get_card_actions- Get card activity historytrello_get_card_attachments- Get card attachmentstrello_get_card_checklists- Get card checkliststrello_get_board_members- Get board memberstrello_get_board_labels- Get board labelstrello_get_member- Get member details
Legacy Tools (Backward Compatibility)
list_boards- List user's boardsget_lists- Get lists in a board
Usage Examples
Once configured, you can use natural language with your AI assistant to interact with Trello:
"Show me all my Trello boards"
"Create a new card called 'Update documentation' in the To Do list"
"Move card X from In Progress to Done"
"Add a comment to card Y saying 'This is ready for review'"
"Search for all cards with 'bug' in the title"
"Show me all cards assigned to me"
Architecture
MCP Protocol
The server implements the Model Context Protocol (MCP), which provides:
- Standardized tool discovery and invocation
- Type-safe parameter validation
- Structured error handling
- Automatic credential management
Security
- API credentials are stored locally in your MCP client's config
- No credentials are transmitted over the network
- All Trello API calls use HTTPS
- Rate limiting is respected with automatic retry logic
Technical Stack
- TypeScript for type safety
- MCP SDK for protocol implementation
- Zod for schema validation
- Fetch API for HTTP requests
Development
Project Structure
├── src/
│ ├── index.ts # Main MCP server entry point
│ ├── server.ts # Alternative server implementation
│ ├── tools/ # Tool implementations
│ │ ├── boards.ts # Board-related tools
│ │ ├── cards.ts # Card-related tools
│ │ ├── lists.ts # List-related tools
│ │ ├── members.ts # Member-related tools
│ │ ├── search.ts # Search functionality
│ │ └── advanced.ts # Advanced features
│ ├── trello/ # Trello API client
│ │ └── client.ts # API client with retry logic
│ ├── types/ # TypeScript type definitions
│ └── utils/ # Utility functions
├── dist/ # Compiled JavaScript
└── package.json # Project configuration
Building from Source
# Install dependencies
npm install
# Build the project
npm run build
# Run type checking
npm run type-check
Testing
The server includes comprehensive error handling and validation. Test your setup by:
- Checking your MCP client's connection status
- Running a simple command like "Show me my Trello boards"
- Verifying the response includes your board data
Troubleshooting
Common Issues
-
"No Trello tools available"
- Ensure your MCP client is fully restarted after configuration
- Check that the path in config points to
dist/index.js - Verify the file exists and is built
-
"Invalid credentials"
- Double-check your API key and token
- Ensure token has read/write permissions
- Regenerate token if needed
-
"Rate limit exceeded"
- The server includes automatic retry logic
- Wait a few minutes if you hit limits
- Consider reducing request frequency
Debug Logging
Check your MCP client's logs for connection and error details. For Claude Desktop, logs are at:
- macOS:
~/Library/Logs/Claude/mcp-server-trello.log - Windows:
%APPDATA%\Claude\Logs\mcp-server-trello.log
Contributing
Contributions are welcome! Please:
- Fork the repository
- Create a feature branch
- Add tests for new functionality
- Submit a pull request
License
MIT License - see LICENSE file for details
Acknowledgments
- Built with the Model Context Protocol SDK
- Uses the Trello REST API
- Compatible with Claude Desktop, Claude Code, Gemini CLI, and other MCP clients
Files in the repo
- .github
- src
- wiki
- .gitignore
- CLAUDE.md
- CONTRIBUTING.md
- LICENSE
- logo.png
- package.json
- README.md
- tsconfig.json
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More connectors

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
BankMCP™: your AI can now read your bank. Self-hosted, read-only MCP server for your own bank accounts via open banking (Enable Banking). Standard MCP; tested with Claude and Ollama.
Open-source auth gateway connecting 1400+ SaaS providers to AI agents through SDK, CLI, MCP, HTTP, and OpenAPI.