MCP Agent Health Reporter
Advisory AOS agent health scan before deployment (manifest, services, immune loop, evidence).
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
mcp-agent-healthclaude mcp add mcp-agent-health-reporter -- uvx mcp-agent-health==0.3.1
{
"mcpServers": {
"mcp-agent-health-reporter": {
"command": "uvx",
"args": [
"mcp-agent-health==0.3.1"
]
}
}
}
Documentation
From the project's README on GitHub, refreshed weekly. Links open on GitHub.
mcp-agent-health
MCP Agent Health Reporter — validate agent health under AOS discipline before deployment.
- PyPI: https://pypi.org/project/mcp-agent-health/
- Catalog: https://raw.githubusercontent.com/aos-standard/catalog/main/catalog.json
- Agent card: packaging/agent_card.json
pip install mcp-agent-health==0.3.1
See packaging/README.md for MCP client configuration.
Frequently asked questions
What is MCP Agent Health Reporter?
Advisory AOS agent health scan before deployment (manifest, services, immune loop, evidence).
How do I install MCP Agent Health Reporter?
It runs on your machine. In Claude Code: claude mcp add mcp-agent-health-reporter -- uvx mcp-agent-health==0.3.1. For other clients, paste the JSON configuration from this page into their MCP settings.
Does MCP Agent Health Reporter need an API key?
Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.
Is MCP Agent Health Reporter open source?
Yes. Its code is on GitHub under the MIT license.
Who maintains MCP Agent Health Reporter?
It is published by aos-standard. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.