token_risk_metrics — agentforge MCP Tool
token_risk_metrics
(token risk metrics) is one of 20 tools on the
agentforge
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call token_risk_metrics from your client
- Claude Code agentforge token_risk_metrics run in your project directory
- Claude Desktop agentforge token_risk_metrics ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor agentforge token_risk_metrics ~/.cursor/mcp.json
- VS Code agentforge token_risk_metrics .vscode/mcp.json
- Zed agentforge token_risk_metrics ~/.config/zed/settings.json
- Windsurf agentforge token_risk_metrics ~/.codeium/windsurf/mcp_config.json
- Cline agentforge token_risk_metrics ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI agentforge token_risk_metrics ~/.gemini/settings.json
- Grok agentforge token_risk_metrics .mcp.json (in your project root)
- ChatGPT agentforge token_risk_metrics Settings → Connectors → Advanced → Developer mode
- Claude.ai agentforge token_risk_metrics Settings → Connectors → Add custom connector
- LangChain agentforge token_risk_metrics pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http agentforge https://agentforge-taupe.vercel.app/mcpOther tools on this server
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.