Back to Home
mrorigo icon

mcp-orchestrator

Verified Safe

by mrorigo

Overview

Orchestrates multiple Model Context Protocol (MCP) servers, enabling LLMs to generate and execute TypeScript code for complex, multi-step workflows, and integrating with Agent-to-Agent (A2A) protocols for collaborative AI.

Installation

Run Command
ANTHROPIC_API_KEY=your_key npx ts-node examples/a2a_server.ts

Environment Variables

  • OPENAI_API_KEY
  • ANTHROPIC_API_KEY
  • ENABLE_SNIPPET_MODE
  • SNIPPET_STORAGE_PATH
  • OPENAI_BASE_URL

Security Notes

The project uses a secure sandboxed `vm` environment for executing LLM-generated TypeScript code. Dangerous Node.js globals (`process`, `require`, `__dirname`, `__filename`, `global`, `Buffer`, `module`, `exports`) are explicitly blocked. Execution includes a configurable timeout. All external interactions (e.g., file system, network) must occur through registered MCP tools, which can be controlled and audited. The `SamplingSecurityManager` further enhances security by implementing approval workflows, rate limiting, and policy enforcement for LLM sampling requests, ensuring human-in-the-loop oversight for sensitive operations. No direct `eval` calls in critical paths were found, and code is compiled into a script for execution. The overall design prioritizes secure execution of untrusted code.

Similar Servers

Stats

Interest Score34
Security Score9
Cost ClassLow
Avg Tokens750
Stars2
Forks0
Last Update2025-12-14

Tags

AI AgentsLLM OrchestrationCode GenerationSecure SandboxMulti-server