Back to Home
dnnyngyen icon

ironmanus-mcp

Verified Safe

by dnnyngyen

Overview

Orchestrates AI workflows with an 8-phase control flow and specialized tools, serving as a Model Context Protocol (MCP) server.

Installation

Run Command
docker-compose up -d

Environment Variables

  • KNOWLEDGE_MAX_CONCURRENCY
  • KNOWLEDGE_TIMEOUT_MS
  • KNOWLEDGE_CONFIDENCE_THRESHOLD
  • KNOWLEDGE_MAX_RESPONSE_SIZE
  • AUTO_CONNECTION_ENABLED
  • RATE_LIMIT_REQUESTS_PER_MINUTE
  • RATE_LIMIT_WINDOW_MS
  • MAX_CONTENT_LENGTH
  • MAX_BODY_LENGTH
  • VERIFICATION_COMPLETION_THRESHOLD
  • EXECUTION_SUCCESS_RATE_THRESHOLD
  • INITIAL_REASONING_EFFECTIVENESS
  • MIN_REASONING_EFFECTIVENESS
  • MAX_REASONING_EFFECTIVENESS
  • ALLOWED_HOSTS
  • ENABLE_SSRF_PROTECTION
  • USER_AGENT
  • NODE_ENV

Security Notes

The project demonstrates strong, explicit, and multi-layered security measures. SSRF protection (`ssrfGuard`, `validateAndSanitizeURL`) is consistently applied to network requests and session IDs. Python execution is sandboxed (`validatePythonCode` blocks dangerous functions) and `pip install` uses an allowlist (`ALLOWED_LIBRARIES`). Path traversal is prevented for file system operations via `isValidSessionId`. An active runtime protection system (`startLegacyFileProtection`) removes legacy JSON files. Configuration validation (`validateConfig`) checks critical security settings in production. No obvious hardcoded secrets were found. The primary remaining risk is the inherent trust boundary of `subprocess.check_call` for `pip install` even with an allowlist, as a malicious package could potentially bypass checks if it made it into a mirror.

Similar Servers

Stats

Interest Score50
Security Score9
Cost ClassHigh
Avg Tokens4000
Stars74
Forks9
Last Update2026-01-19

Tags

AI OrchestrationWorkflow ManagementAgent FrameworkModel Context ProtocolDevOps