mcp_coordinator
Verified Safeby angrysky56
Overview
Transforms MCP servers into importable Python libraries to enable efficient, scalable AI agent tool usage with local code execution and skills accumulation.
Installation
uv run mcp-coordinator-serverEnvironment Variables
- MCP_JSON
- MCP_SERVERS_CONFIG
- MCP_EXECUTOR_TYPE
- OLLAMA_API_BASE
- OLLAMA_MODEL
- DOCKER_IMAGE
- DOCKER_MEM_LIMIT
- DOCKER_CPU_QUOTA
- HF_TOKEN
- E2B_API_KEY
- MODAL_TOKEN_ID
- MODAL_TOKEN_SECRET
Security Notes
The server is designed with a strong focus on security, utilizing `smolagents.LocalPythonExecutor` for sandboxed code execution. It explicitly defines `allowed_imports` and `denied_imports` (blocking `os`, `subprocess`, `sys`, `eval`, `exec`, `compile`, `__import__`). The `SecureExecutor` also implements network isolation (using `unshare --net` on Unix-like systems) and resource limits (CPU, memory). Skills are run in a subprocess for further isolation. While running arbitrary code always carries inherent risk, the extensive mitigation strategies employed place this server at a high security standard.
Similar Servers
klavis
Creates an AI agent that uses Klavis Strata to interact with Gmail and YouTube through MCP, demonstrating how to summarize a YouTube video and email the summary.
aicode-toolkit
Acts as an MCP proxy server to connect AI agents to multiple underlying MCP servers through a single connection, enabling progressive tool discovery and reducing initial token usage for tool descriptions.
Polymcp
A comprehensive toolkit and agent framework for building Model Context Protocol (MCP) servers and orchestrating them with Large Language Models (LLMs) across Python and TypeScript environments.
mcp-servers
An MCP server for fetching, cleaning, and intelligently extracting content from web pages, designed for agent-building frameworks.