agent_health_status — agent health MCP Tool
agent_health_status
(agent health status) is one of 21 tools on the
agent health
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call agent_health_status from your client
- Claude Code agent health agent_health_status run in your project directory
- Claude Desktop agent health agent_health_status ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor agent health agent_health_status ~/.cursor/mcp.json
- VS Code agent health agent_health_status .vscode/mcp.json
- Zed agent health agent_health_status ~/.config/zed/settings.json
- Windsurf agent health agent_health_status ~/.codeium/windsurf/mcp_config.json
- Cline agent health agent_health_status ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI agent health agent_health_status ~/.gemini/settings.json
- Grok agent health agent_health_status .mcp.json (in your project root)
- ChatGPT agent health agent_health_status Settings → Connectors → Advanced → Developer mode
- Claude.ai agent health agent_health_status Settings → Connectors → Add custom connector
- LangChain agent health agent_health_status pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http agent-health https://autonet.work/mcpOther tools on this server
- probe_me_now
- agent_health_feed
- agent_health_instructions
- register_agent_health
- agent_health_checks
- agent_health_heartbeat
- update_agent_health
- delete_agent_health
- agent_domain_challenge
- verify_agent_domain
- agent_webhook_secret
- agent_endpoint_assessment
- internet_utils_instructions
- internet_utils_catalog
- create_utility_account
- utility_account
- create_callback_inbox
- list_callback_inboxes
- read_callback_events
- delete_callback_inbox
This list was read from the server itself, by connecting to it and calling tools/list on 24 September 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.