Task

io.github.rog0xPublished by GitHub account rog0xv1.0.1Updated Oct 24, 2026

Todo, priority, estimation, burndown for AI agents

Overview

AI-generated overview

An in-memory task and project management server that lets an assistant track todos, prioritize work, estimate effort, and compute sprint burndown.

What you can do
Provides five tools for task and project management. todo_manager adds, completes, updates, deletes, and lists tasks with filtering by status, priority, and tags, persisting only within the session. priority_sorter ranks tasks using the Eisenhower Matrix, RICE scoring, or MoSCoW. time_estimator applies PERT methodology to produce weighted expected durations with a configurable buffer, standup_generator produces daily standup summaries, and burndown_calculator computes ideal versus actual burndown, velocity, and completion forecasts from story points and sprint duration.
When to use it
Useful when an assistant needs lightweight, session-scoped task tracking and planning support, such as organizing a backlog, prioritizing work, estimating effort, drafting standup notes, or checking sprint progress. It suits conversational planning rather than durable project records.
Requirements
Runs locally as a Node.js process over stdio, installed from the npm package @rog0x/mcp-task-tools and built with npm install and npm run build. It is desktop-only and not web-executable. No authentication, environment variables, or headers are declared.
Before you install
Task data is in-memory and persists only within the session, so it is lost when the process ends. The tools can add, update, and delete tasks, so changes should be reviewed. No credentials, payments, or third-party data sharing are indicated.

Installation

In SourceWeft

  1. Open Task in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

mcp-task-tools

MCP server providing task and project management tools for AI agents.

Tools

todo_manager

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.

priority_sorter

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

time_estimator

Estimate task duration using PERT methodology. Break work into subtasks, provide optimistic/realistic/pessimistic estimates, and get weighted expected time with configurable buffer.

standup_generator

Generate daily standup updates from the current task list. Outputs yesterday (completed), today (in progress), and blockers with summary statistics.

burndown_calculator

Calculate sprint burndown data. Given tasks with story points and sprint duration, computes ideal vs actual burndown, velocity metrics, and completion forecast.

Setup

bash
npm installnpm run build

Usage with Claude Desktop

Add to your Claude Desktop config:

json
{  "mcpServers": {    "task-tools": {      "command": "node",      "args": ["path/to/mcp-task-tools/dist/index.js"]    }  }}

License

MIT

Source: README.md at commit 9a5c848

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.1LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.