iron-manus-mcp

Overview

Iron Manus MCP is a sophisticated Model Context Protocol server designed for AI workflow orchestration. It implements an 8-phase workflow (INIT → QUERY → ENHANCE → KNOWLEDGE → PLAN → EXECUTE → VERIFY → DONE) with specialized tools like JARVIS for workflow control and APITaskAgent for API discovery with SSRF protection. The server introduces innovative patterns that later became standard in the industry, including todos as subagent dispatch queues, phase-gated tool access, and structured planning phases.

Try asking AI

After installing, here are 6 things you can ask your AI assistant:

• JARVIS

  8-phase workflow controller for orchestration

  Try:Start a new 8-phase workflowTry:Initialize a project using the Iron Manus workflow
• APITaskAgent

  API discovery and fetching with SSRF protection

  Try:Fetch data from GitHub APITry:Discover and call a REST API endpoint
• PythonComputationalTool

  Python execution for data analysis

  Try:Analyze this dataset with PythonTry:Perform statistical calculations with Python
• IronManusStateGraph

  Session state management

  Try:Save current workflow stateTry:Restore workflow from previous state
• SlideGenerator

  HTML slide generation

  Try:Create a presentation about project updatesTry:Generate slides for the quarterly review
• HealthCheck

  Runtime diagnostics

  Try:Check system healthTry:Verify all components are running

Comparable tools

Installation

git clone https://github.com/dnnyngyen/iron-manus-mcp
cd iron-manus-mcp
npm install
npm run build
npm start

docker build -t iron-manus-mcp .
docker run -d --name iron-manus-mcp iron-manus-mcp

claude mcp add iron-manus-mcp node dist/index.js

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

FAQ

What is the 8-phase workflow?

Iron Manus MCP implements an 8-phase workflow (INIT → QUERY → ENHANCE → KNOWLEDGE → PLAN → EXECUTE → VERIFY → DONE) that enforces planning before execution and structures agent interactions.

How are todos used as subagent dispatch?

Todos act as task dispatch mechanisms where each todo can specify an agent type (TaskAgent, SubAgent, DirectExecution) and configuration, enabling structured task delegation.

Compare iron-manus-mcp with