lunar
Verified Safeby TheLunarCompany
Overview
A Model Context Protocol (MCP) server that acts as a control plane for AI agents and tools, providing management, access control, and observability for AI API calls.
Installation
npm run startEnvironment Variables
- MCPX_PORT
- LOG_LEVEL
- AUTH_KEY
- APP_CONFIG_PATH
- UI_URL
- UI_PORT
- LUNAR_API_KEY
- LUNAR_TELEMETRY
- LOKI_URL
- LOKI_USER
- LOKI_PASSWORD
- SERVE_METRICS_PORT
- OAUTH_CLIENT_ID_ENV_VAR
- OAUTH_CLIENT_SECRET_ENV_VAR
Security Notes
The MCP server uses robust input validation (Zod) and environment variables for sensitive data, which are good security practices. However, its core functionality involves dynamic Docker operations (e.g., building images with CA certificates for interception, running containers for target servers) and orchestrating external AI agents. These capabilities introduce an elevated attack surface, requiring careful configuration and runtime isolation to prevent potential misuse if inputs to these powerful operations are not perfectly controlled. No direct `eval` of user-supplied code was found in the Node.js server itself.
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.
bifrost
A high-performance AI gateway with a unified interface for multiple providers, offering real-time monitoring, configuration management, and comprehensive observability for AI infrastructure.
mcp-gateway-registry
This MCP server provides programmatic interaction with the MCP Gateway Registry API, enabling management of registered services and AI agents, including registration, toggling, health monitoring, group-based access control, and intelligent (semantic) discovery of tools and agents.
mockloop-mcp
Provides a comprehensive platform for generating and managing mock API servers with AI-driven test generation, scenario management, proxy capabilities, and robust monitoring and auditing features.