Trello Task Manager MCP
Integrates with Trello to manage tasks and cards with features like creating, updating, and marking tasks as in-progress or completed, as well as managing checklists and providing an interactive feedback UI.
README
Trello Task Manager MCP
LLM Task management System that integrates as an MCP Server and uses Trello for managing tasks/cards.

See Demo Video
Features
- Create and manage tasks in Trello boards
- Update task descriptions
- Mark tasks as in-progress or completed
- Get next available task
- Get filtered list of tasks (all, work-in-progress, or completed)
- Add and manage checklists for tasks
- Get next unchecked checklist item for focused work
- Interactive feedback UI for collecting user feedback on project changes
Prerequisites
- Python 3.10 or higher
- uv
- A Trello account with API Key and Token
Installation
-
Clone the repository:
git clone https://github.com/namuan/trello-task-manager-mcp.git cd trello-task-manager-mcp -
Install dependencies:
uv sync -
Create a
.envfile in the project root with your Trello credentials:TRELLO_API_KEY=your_api_key TRELLO_API_TOKEN=your_api_token TRELLO_BOARD_NAME=your_board_name HOST=127.0.0.1 # Optional, defaults to 127.0.0.1 PORT=8050 # Optional, defaults to 8050 -
Run the application
trello-task-manager-mcpor
make run
MCP Integration
Add the following entry to your MCP client:
{
"mcpServers": {
"trello-task-manager": {
"type": "sse",
"url": "http://localhost:8050/sse",
"note": "For SSE connections, add this URL directly in your MCP Client"
}
}
}
Usage
Ask MCP Client to use Trello task manager along with the instructions to use one of these tools.
add_task: Create a new taskupdate_task_description: Update a task's descriptionget_next_available_task: Get the next available taskget_tasks: Get a list of tasks with optional filtering (all, wip, done)mark_as_in_progress: Mark a task as in progressmark_as_completed: Mark a task as completedupdate_task_with_checklist: Add or update a checklist for a taskcomplete_checklist_item: Mark a specific checklist item as completedget_next_unchecked_checklist_item: Get the next unchecked checklist item for a taskinteractive_feedback: Launch an interactive GUI for collecting user feedback on project changes
Development
Setup Development Environment
This project uses uv for dependency management. Run the following command to set up your development environment:
make install
This will:
- Create a virtual environment using uv
- Install project dependencies
- Set up pre-commit hooks
Development Commands
The project includes several helpful make commands:
make help # Show all available commands with descriptions
make check # Run code quality tools (lock file check and pre-commit)
make run # Run the application
make build # Build wheel file
License
This project is licensed under the MIT License - see the LICENSE file for details.
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.