#99th of 9 in MCP servers for developers

claude-task-master

Task manager that turns a PRD into tasks for AI coding agents

Documentation ↗ Website ↗ Repository on GitHub ↗

Stars: 28.2k
License: custom license
Last commit: Apr 2026
Last release: Mar 2026
Language: JavaScript

Checked 13 Oct 2026 on GitHub.

Overview

Task Master runs as an MCP server or CLI (task-master) and parses a PRD into structured tasks with dependencies, subtasks, tags and a research command. Editors such as Cursor, Windsurf, VS Code and Q CLI, plus Claude Code, call it to plan and pick the next task. It needs a provider API key (Anthropic, OpenAI, Gemini, Perplexity, xAI, OpenRouter and others) or the Claude Code or Codex CLI.

Who it is for: Developers using Cursor, Claude Code or similar agents on multi-step projects

Strengths

Works as an MCP server or CLI, installed with npx or npm
Separate main, research and fallback models across many providers
Claude Code and Codex CLI usable without an API key
TASK_MASTER_TOOLS limits loaded tools to 7, 15 or all 36

Weaknesses

MIT with Commons Clause: no selling it or offering it as a hosted service
Default loads all 36 tools, about 21,000 tokens of context
Task quality depends on writing a detailed PRD first
AI commands need a provider API key or a Claude Code/Codex CLI login

What it needs

no GPU
Needs Node.js, npm, AI provider API key or Claude Code/Codex CLI
Models: Anthropic, OpenAI, Google Gemini, Perplexity, xAI

Also in MCP servers for developers

See all 9

Also in MCP servers for developers
Rank	Project	Score
1	codegraphLocal code knowledge graph served to coding agents over MCP73.9k starsMIT	81 out of 100
2	chrome-devtools-mcpMCP server that lets coding agents drive and debug a live Chrome53.4k starsApache-2.0	67 out of 100
3	codebase-memory-mcpMCP server that indexes codebases into a queryable knowledge graph46.5k starsMIT	67 out of 100
#4	github-mcp-serverMCP server exposing GitHub repos, issues, PRs and Actions to AI tools33.6k starsMIT	65 out of 100
#5	serenaMCP server giving coding agents symbol-level code search, editing and refactoring30.2k starscustom license	65 out of 100

How to choose

Check what it can change (push, delete, run) and how that is scoped.
Prefer servers that run locally over ones that send your code to a third party.
Look at how many tool calls a task takes; chatty servers burn context.

Health

Releases: 24 in the last 12 monthsLast one 196 days ago
Top contributor: 81% of commits147 of 182 in the last 12 months
Security advisories: NoneOn GitHub, in the last 12 months
npm package: No known advisories ↗ (opens in a new tab)task-master-ai 0.43.1, the latest version
OpenSSF Scorecard: Not checked

Read from GitHub, deps.dev and OpenSSF on 13 Oct 2026. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check.

License in plain words

custom license Custom terms

Use it at work: Check
Change it and rebrand it: Check
Sell it or host it for others: Check

Your part: GitHub could not match these terms to a standard license. Read the license before you use it at work, rebrand it or host it for others.

A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)

For maintainers

Show this rank in your README. It updates twice a day.

[![Archestack](https://archestack.com/badge/eyaltoledano/claude-task-master.svg)](https://archestack.com/best-of-vibe-coding/projects/claude-task-master/)

How badges work

On your site or blog

A card with the rank, score and signals, in light or dark to match the reader.

<iframe src="https://archestack.com/embed/best-of-vibe-coding/claude-task-master/" title="claude-task-master on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>

Preview the card

Best of Vibe Coding on GitHub

Each review comes from the project's README and facts we check on GitHub. The fix form opens with claude-task-master filled in.