MCP Agent Health Reporter

Overview

MCP Agent Health Reporter is a Model Context Protocol server that performs advisory AOS agent health scans before deployment, evaluating manifest integrity, services status, immune loop functionality, and evidence collection. It integrates with AI assistants as callable tools, eliminating manual workflows between applications.

The server runs locally via the uvx command mcp-agent-health, requiring only the Python package mcp-agent-health installed on your system. No authentication or external credentials are needed—it operates out of the box. Version v0.3.1 is available under MIT license, with source code at aos-standard/mcp-agent-health on GitHub.

MCP Agent Health Reporter belongs in the AI & Agents category and works with any MCP client including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain this server, claim your listing on mcp.site to verify ownership and keep information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "mcp_agent_health_reporter": {
      "command": "uvx",
      "args": [
        "mcp-agent-health"
      ]
    }
  }
}