Iron Manus MCP (+ J.A.R.V.I.S. Orchestrator)

by dnnyngyen

A modular MCP server that implements a 6-phase finite state machine for task orchestration, API integration, and knowledge synthesis. No external API keys are required. Runtime parameters are configured via environment variables.

Developer toolsstdioCommunity

Repository-wide counts · Cached 2026-03-07

Overview

The Iron Manus MCP (+ J.A.R.V.I.S. Orchestrator) MCP server is a publicly available project. Review the upstream repository for installation instructions, supported tools, compatibility, permissions, and current maintenance status.

Configuration

Configuration, transport, authentication, and runtime requirements vary by project. Open the repository before connecting and use the smallest set of credentials and permissions required.

Open the Iron Manus MCP (+ J.A.R.V.I.S. Orchestrator) repository to read the latest documentation.

KEEP EXPLORING

Compare source, connection, and authentication details before choosing an implementation.

View the complete category

模型上下文协议服务器

modelcontextprotocol

Community

一组用于模型上下文协议(MCP)的参考实现,展示了对大型语言模型(LLM)工具和数据源的安全且受控的访问方式。

Context7 Platform - Up-to-date Code Docs For Any Prompt

upstash

Community

Context7 MCP server providing up-to-date, version-specific documentation and code examples for libraries, enabling coding agents to fetch accurate docs and code snippets. Requires an API key for higher rate limits, passed via CONTEXT7_API_KEY header.

Playwright MCP

Microsoft Corporation

Community

A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. Enables LLMs to interact with web pages through structured accessibility snapshots, bypassing the need for screenshots or visually-tuned models.

AIHawk

feder-cr

Community

AIHawk is an anti detect browser and web browsing agent, open source, with an MCP server for coding agents: undetected, no captchas, no blocks. It requires an OpenRouter API key for the standalone web UI mode, which can be provided via the --openrouter-key flag or the OPENROUTER_API_KEY environment variable or a .env file in the running directory.

FROM THE SOURCE

Repository README

Build-time snapshot · Retrieved 2026-10-05

View original

MseeP.ai Security Assessment Badge

Iron Manus MCP Banner

Build Status Tests TypeScript Node.js License: MIT Docker Hub GitHub Container Registry Source Code

Iron Manus MCP

Model Context Protocol server for AI workflow orchestration inspired by Manus AI's orchestration patterns and Andrej Karpathy's "Iron Man" analogy.

Extended context management through agent delegation and Todos as a custom agent dispatch tool

Demo

Iron Manus MCP Demo
🎥 Video Tutorial

Iron Manus MCP Deep Dive

Watch the detailed walkthrough

Historical Notes: Architectural Patterns

Note: This project is now archived. The following notes document architectural decisions that later appeared in mainstream AI tooling.

Several patterns implemented in Iron Manus MCP (June 2024) were later adopted by Claude Code and similar tools. These emerged from independent experimentation rather than foresight, solving problems that turned out to be common across the ecosystem.

Patterns That Became Standard

1. Todos as Subagent Dispatch Queue

interface TodoItem {
  type?: 'TaskAgent' | 'SubAgent' | 'DirectExecution';
  meta_prompt?: MetaPrompt;  // Declarative agent configuration
}

This MCP was the first to use todos as a subagent dispatch queue. Claude Code had TodoWrite/TodoRead at that point, but nobody (including Anthropic) was thinking of todos as an agent coordination primitive. The Task tool existed but was just non-specialized agents. Our implementation connected the two: todos become task dispatches. Boris Cherny announced "We're turning Todos into Tasks" on January 22, 2026, seven months after we shipped the same idea.

2. Phase-Gated Tool Access

const PHASE_ALLOWED_TOOLS = {
  PLAN: ['TodoWrite'],
  EXECUTE: ['TodoRead', 'TodoWrite', 'Task', 'Bash', 'Read', 'Write', 'Edit'],
  VERIFY: ['TodoRead', 'Read'],  // Read-only during verification
};

Restricting tool availability by phase prevented misuse (e.g., writing files during verification). This pattern appears in Claude Code Agent Teams (February 2026) via phase-based permissions.

3. Structured Planning Phase

The explicit INIT → QUERY → ENHANCE → KNOWLEDGE → PLAN → EXECUTE → VERIFY → DONE workflow enforced planning before execution. Claude Code's Plan Mode (August 2025) provides similar structure.

4. Context Isolation via File-Based Communication

./iron-manus-sessions/{session_id}/
├── synthesized_knowledge.md
├── primary_research.md
└── agent_output.md

Task() agents have isolated contexts and cannot share state directly. This project used session workspaces for inter-agent coordination. Claude Code Agent Teams implements similar patterns via ~/.claude/teams/ and ~/.claude/tasks/.

5. Role-Based Prompt Switching

Nine specialized roles (planner, coder, critic, researcher, analyzer, synthesizer, ui_architect, ui_implementer, ui_refiner) with distinct thinking methodologies. Claude Code custom subagents (July 2025) provide similar specialization.

6. Meta-Prompt DSL for Agent Spawning

(ROLE: coder) (CONTEXT: auth_system) (PROMPT: Implement JWT auth) (OUTPUT: auth_module.ts)

Declarative syntax for agent configuration embedded in todo content. Similar patterns appear in Claude Code's subagent configuration.

Timeline Context

Iron Manus MCP (June 2024) introduced todos as subagent dispatch, phase-gated tools, structured planning phases, context isolation, and role-based agents. Claude Code adopted these patterns between July 2025 and February 2026. These patterns emerged from practical necessity. Multi-agent orchestration requires task decomposition, context isolation, and workflow structure, all of which eventually appeared in production tooling.

What It Does

8-phase workflow orchestration: INIT → QUERY → ENHANCE → KNOWLEDGE → PLAN → EXECUTE → VERIFY → DONE

Tools:

  • JARVIS - 8-phase workflow controller
  • APITaskAgent - API discovery and fetching with SSRF protection
  • PythonComputationalTool - Python execution for data analysis
  • IronManusStateGraph - Session state management
  • SlideGenerator - HTML slide generation
  • HealthCheck - Runtime diagnostics

Quick Start

From Source

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

Docker

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

Or with docker-compose:

docker-compose up -d

MCP Integration

Add to Claude Code:

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

Or add to your MCP config:

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

Configuration

ALLOWED_HOSTS=api.github.com,httpbin.org    # SSRF whitelist
ENABLE_SSRF_PROTECTION=true                  # Enable security
KNOWLEDGE_MAX_CONCURRENCY=2                  # API concurrency limit
KNOWLEDGE_TIMEOUT_MS=4000                    # Request timeout (ms)

Development

npm run build     # Compile TypeScript
npm run lint      # Check code style
npm run format    # Format code
npm start         # Run server
npm run dev       # Build + watch mode

Security

  • SSRF protection blocks private IPs (192.168.x.x, 127.x.x.x, etc.)
  • URL validation (HTTP/HTTPS only)
  • Host allowlist enforcement
  • Request timeout and size limits

License

MIT