agent_health_checks — agent health MCP Tool
agent_health_checks
(agent health checks) 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_checks from your client
- Claude Code agent health agent_health_checks run in your project directory
- Claude Desktop agent health agent_health_checks ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor agent health agent_health_checks ~/.cursor/mcp.json
- VS Code agent health agent_health_checks .vscode/mcp.json
- Zed agent health agent_health_checks ~/.config/zed/settings.json
- Windsurf agent health agent_health_checks ~/.codeium/windsurf/mcp_config.json
- Cline agent health agent_health_checks ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI agent health agent_health_checks ~/.gemini/settings.json
- Grok agent health agent_health_checks .mcp.json (in your project root)
- ChatGPT agent health agent_health_checks Settings → Connectors → Advanced → Developer mode
- Claude.ai agent health agent_health_checks Settings → Connectors → Add custom connector
- LangChain agent health agent_health_checks 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_status
- 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.