agentmods.dev

task-master-ai

task-master-ai is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from TICnine/autotask-mcp. Its token cost is not measured, scanned A, a copy of task-master-ai, Apache-2.0.

A locally run task-management service for software projects that use AI to help organize development work. It runs through the task-master-ai package and requires an API key for an AI provider.

In plain words
What is it for?
Use it to connect an AI coding environment to Task Master and manage project tasks through its local service.
Why use it?
It provides a central system for managing AI-assisted development tasks, but setup requires configuring one or more supported AI services.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it. Also seen: listed in a Claude config.

not rated 0repo 6mo ago A scan tokens not measured copy · 100% Apache-2.0

Good fit Use it to connect an AI coding environment to Task Master and manage project tasks through its local service.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/ticnine/autotask-mcp/task-master-ai
View source ↗ TICnine/autotask-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/TICnine/autotask-mcp

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for task-master-ai

README.md
[![agentmods](https://agentmods.dev/badge/mcp/ticnine/autotask-mcp/task-master-ai/github.svg)](https://agentmods.dev/mcp/ticnine/autotask-mcp/task-master-ai)
Your own site
<a href="https://agentmods.dev/mcp/ticnine/autotask-mcp/task-master-ai"><img src="https://agentmods.dev/badge/mcp/ticnine/autotask-mcp/task-master-ai/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for task-master-ai

Your own site · 80×15
<a href="https://agentmods.dev/mcp/ticnine/autotask-mcp/task-master-ai"><img src="https://agentmods.dev/badge/mcp/ticnine/autotask-mcp/task-master-ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Security

Grade A, and why

task-master-ai scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to task-master-ai — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.mcp.json · 21 lines

What it actually says

{
  "task-master-ai": {
    "type": "stdio",
    "command": "npx",
    "args": [
      "-y",
      "task-master-ai"
    ],
    "env": {
      "ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE",
      "PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY_HERE",
      "OPENAI_API_KEY": "YOUR_OPENAI_KEY_HERE",
      "GOOGLE_API_KEY": "YOUR_GOOGLE_KEY_HERE",
      "XAI_API_KEY": "YOUR_XAI_KEY_HERE",
      "OPENROUTER_API_KEY": "YOUR_OPENROUTER_KEY_HERE",
      "MISTRAL_API_KEY": "YOUR_MISTRAL_KEY_HERE",
      "AZURE_OPENAI_API_KEY": "YOUR_AZURE_KEY_HERE",
      "OLLAMA_API_KEY": "YOUR_OLLAMA_API_KEY_HERE"
    }
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 21 lines scan A 79c1ddc8d119

Subscribe to this mod's changes

task-master-ai is an MCP server published in the GitHub repository TICnine/autotask-mcp (0 stars, last pushed 6mo ago), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. It is 100% identical to task-master-ai, differing in 0 lines, and is treated as a copy.

Project management
Related

Other mcp servers, from other repositories

amazing-marvin-complete-mcp

MCP server for Amazing Marvin with complete public-API coverage (50 tools). Runs locally from the amazing-marvin-complete-mcp Python package. Needs 3 environment variables to run.

andreasd083/amazing-marvin-complete-mcp · not measured

p4plan-mcp

MCP server for P4 Plan — tasks, sprints, bugs, comments, custom fields via GraphQL API. Runs locally from the @perforce/p4plan-mcp npm package. Needs 3 environment variables to run.

perforce/p4plan-mcp · not measured

jira-product-discovery-mcp

MCP server for Jira Cloud REST APIs, native Jira Product Discovery Insights, and supporting attachments. Runs locally from the @enterpret/jira-product-discovery-mcp npm package.

aavaz-ai/jira-product-discovery-mcp · not measured

megaplan

MCP server for Megaplan — tasks, deals, project management (Russia). Runs locally from the @theyahia/megaplan-mcp npm package. Needs 2 environment variables to run.

theYahia/megaplan-mcp · not measured

autonomous-sdlc-command-center

MCP server "autonomous-sdlc-command-center" as configured in Senpai-Sama7/autonomous-sdlc-command-center. Runs locally from the autonomous-sdlc-command-center Python package.

Senpai-Sama7/autonomous-sdlc-command-center · not measured

pm-copilot

MCP server "pm-copilot" as configured in dkships/pm-copilot. Runs dist/index.js with node.

dkships/pm-copilot · not measured