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., "@mcp-task-tools Prioritize my tasks using RICE scoring"
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.
MCP server providing task and project management tools for AI agents.
In-memory task list management. Add, complete, update status, delete, and list tasks with filtering by status, priority, and tags. Data persists within the session.
Sort tasks using established prioritization frameworks:
Eisenhower Matrix — categorize by urgent/important into four quadrants (Do First, Schedule, Delegate, Eliminate)
RICE Scoring — rank by Reach, Impact, Confidence, and Effort
MoSCoW Method — classify as Must Have, Should Have, Could Have, or Won't Have
Estimate task duration using PERT methodology. Break work into subtasks, provide optimistic/realistic/pessimistic estimates, and get weighted expected time with configurable buffer.
Generate daily standup updates from the current task list. Outputs yesterday (completed), today (in progress), and blockers with summary statistics.
Calculate sprint burndown data. Given tasks with story points and sprint duration, computes ideal vs actual burndown, velocity metrics, and completion forecast.
Related MCP server: Kanban MCP
npm install
npm run buildAdd to your Claude Desktop config:
{
"mcpServers": {
"task-tools": {
"command": "node",
"args": ["path/to/mcp-task-tools/dist/index.js"]
}
}
}MIT
Calculate sprint burndown chart data. Given tasks with story points and sprint duration, computes ideal vs actual burndown, velocity metrics, and completion forecast.
Inputs: tasks (required), sprint_duration_days (required), current_day (required), sprint_name.
Sort and prioritize tasks using proven frameworks: Eisenhower matrix (urgent/important quadrants), RICE scoring (reach, impact, confidence, effort), or MoSCoW method (must/should/could/wont).
Inputs: method (required), tasks (required).
Generate a daily standup update from the current task list. Shows yesterday (recently completed), today (in progress), and blockers. Uses data from todo_manager.
Inputs: lookback_hours.
Estimate task duration using PERT methodology. Break a task into subtasks, provide optimistic/realistic/pessimistic estimates for each. Returns weighted expected time plus configurable buffer.
Inputs: task (required), subtasks (required), buffer_percent, unit.
Manage an in-memory task list. Add, complete, update status, delete, and list tasks. Supports filtering by status, priority, and tags. Persistent within session.
Inputs: action (required), id, title, description, +5 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 5 tools
Each tool has a clearly distinct purpose: todo_manager for CRUD, priority_sorter for frameworks, time_estimator for duration, burndown_calculator for sprint metrics, standup_generator for reports. No overlap or ambiguity.
All tool names follow a consistent 'domain_verb' pattern (e.g., burndown_calculator, priority_sorter, todo_manager). The naming style is uniform with snake_case and predictable suffixes.
Five tools is well-scoped for a task management server offering core functions (CRUD, prioritization, estimation, sprint tracking, standup). No tool seems extraneous or missing.
The tool set covers full task lifecycle (CRUD), prioritization, estimation, burndown, and standups. However, story points for burndown and subtask support for estimation are not explicitly tied into todo_manager, leaving minor gaps.
AI-native project management + agent memory: tasks, sprints, risk, burnout, knowledge search.
Project management for AI agents: tasks, docs, decisions and time in one shared team context.
AI project management for any team: agents write plans, deliver and report. You accept the work.
AI-native project management for tasks, docs, collaboration, and agents.
