list_watched — AgentWatch MCP Tool Read-only
list_watched
(list watched) is one of 21 tools on the
AgentWatch
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call list_watched from your client
- Claude Code AgentWatch list_watched run in your project directory
- Claude Desktop AgentWatch list_watched ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor AgentWatch list_watched ~/.cursor/mcp.json
- VS Code AgentWatch list_watched .vscode/mcp.json
- Zed AgentWatch list_watched ~/.config/zed/settings.json
- Windsurf AgentWatch list_watched ~/.codeium/windsurf/mcp_config.json
- Cline AgentWatch list_watched ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI AgentWatch list_watched ~/.gemini/settings.json
- Grok AgentWatch list_watched .mcp.json (in your project root)
- ChatGPT AgentWatch list_watched Settings → Connectors → Advanced → Developer mode
- Claude.ai AgentWatch list_watched Settings → Connectors → Add custom connector
- LangChain AgentWatch list_watched pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http agentwatch https://agentwatch.agentwatch.workers.dev/mcpOther tools on this server
- get_feed
- run_audit
- get_capabilities
- get_alerts
- get_pending_proposals
- get_fidelity
- get_leaderboard
- get_benchmark
- get_tca
- register_intent
- add_watch
- watch_demo_set
- refresh_watches
- get_agent_passport
- set_agent_passport
- list_recovery_owners
- set_recovery_owner
- remove_recovery_owner
- get_safe_defaults
- get_dashboard
This list was read from the server itself, by connecting to it and calling tools/list on 5 November 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.