task-tracker-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@task-tracker-mcp show my open tasks"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
task-tracker-mcp
Description
task-tracker-mcp is a task management system for LLM-based agents. All tasks are stored in a single tree, available immediately after the server starts.
Related MCP server: Task Orchestration
Main Goal
Enable LLM agents to manage their tasks through a unified Task manager.
Requirements
Python 3.13 or higher
Node.js and npm (for @modelcontextprotocol/inspector)
Installation
Cloning the Repository
git clone git@github.com:feodal01/task-tracker-mcp.git
cd task-tracker-mcpSetting Up the Environment
Configuration
Open the Claude Desktop configuration file located at:
On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json Add the following:
{
"mcpServers": {
"mcpServer": {
"command": "uv",
"args": [
"--directory",
"/Path/to/task-tracker-mcp",
"run",
"python",
"-m",
"mcp_server.mcp_service"
],
"env": {
"PYTHONPATH": "/Path/to/task-tracker-mcp/src"
}
}
}
}Running the Project
Starting the MCP Server
Using uv:
export PYTHONPATH=/Path/to/task-tracker-mcp/src
uv run python -m src.mcp_server.mcp_serviceStarting the Inspector
To inspect the MCP server, use: uv:
npx @modelcontextprotocol/inspector uv --directory /Path/to/task-tracker-mcp run python -m mcp_server.mcp_service Running Tests
uv:
export PYTHONPATH=/Path/to/task-tracker-mcp/src
uv run pytest tests/Running FastApi service with MCP tools
export PYTHONPATH=/Path/to/task-tracker-mcp/src
uv --directory /Path/to/task-tracker-mcp run python -m mcp_server.mcp_rest_serviceLicense
This project is licensed under the MIT License — see the LICENSE file for details.
Contribution
Want to contribute? Fork the repository and submit a pull request.
Contacts
If you have any questions, contact me at: evgenyorlov1991@gmail.com
Available Tools
7 toolscreate_taskA
Creates a new task (or subtask) in the single task tree. Args: description: Task description dod: Definition of Done (optional) deadline: Deadline (optional, ISO8601 string or datetime) assignee: Assignee (optional) parent_id: Parent task ID (if not specified, will be added to the root)
Inputs: description (required), dod, assignee, deadline, +1 more.
delete_taskC
Deletes a task. Args: task_id: Task ID
Inputs: task_id (required).
get_taskC
Retrieves information about a task. Args: task_id: Task ID
Inputs: task_id (required).
list_tasksA
Returns a list of all tasks in the tree (including subtasks).
Inputs: no named parameters.
test_toolA
Test function for checking MCP server health.
Inputs: no named parameters.
update_statusC
Closes a task. Args: task_id: Task ID status: Status (todo/done/cancelled/in_progress) reason: Close reason (optional)
Inputs: status (required), task_id (required), reason.
update_taskA
Updates an existing task. You can update any of the following fields:
Args:
task_id (str): ID of the task to update.
description (str, optional): New description for the task.
dod (str, optional): New Definition of Done for the task.
deadline (str, optional): New deadline for the task.
assignee (str, optional): New assignee for the task.
Any combination of these fields can be provided. Only non-null values will be updated.
Inputs: task_id (required), dod, assignee, deadline, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Each tool targets a distinct action: create, update fields, update status, delete, get, list, and health check. There is no real overlap between updating task fields and updating task status.
Most tools follow a clear verb_noun pattern like create_task, update_task, delete_task, get_task, and list_tasks. Minor inconsistencies include update_status instead of update_task_status and the non-domain test_tool.
Seven tools is well-scoped for a task tracker: core CRUD, status transitions, and listing are all covered without unnecessary redundancy. Each tool earns its place.
The surface covers create, read, update, delete, status changes, and listing, which is solid for basic task tracking. The main gap is the lack of an operation to move a task within the task tree after creation, since parent_id is only supported on create.
Maintenance
Related MCP Connectors
Task management for teams building with AI agents. Agents claim tasks and report progress.
Task manager for AI agents. Orchestrate agents to achieve large goals in unified control plane.
Shared graph-based task tracker for agents, agents’ agents and people. Source-available, free cloud.
Shared task layer for AI agents: tasks, handoffs and decisions that persist across tools.
Related MCP Servers
- AlicenseAqualityDmaintenanceA task management server that helps AI assistants break down user requests into manageable tasks and track their completion with user approval steps.2425 npm30MIT
- AlicenseBqualityDmaintenanceElevate your LLM task management with Task Orchestrator, an MCP server that empowers you to define, organize, and track goals and tasks with hierarchical precision. Integrate intelligent task management into your workflow.57MIT
- AlicenseAqualityDmaintenanceAn AI agent task management system that provides structure and visualization for long-term task planning with support for the Model Context Protocol (MCP) standard.151MIT
- AlicenseNot gradedqualityCmaintenanceA multi-agent task management system for AI applications that enables users to create agents with roles and capabilities, delegate tasks with trust-based routing, coordinate file access to prevent conflicts, and monitor performance through a unified dashboard.8 npmMIT