evaluate_safe_call — Trust Live MCP Tool
evaluate_safe_call
(evaluate safe call) is one of 5 tools on the
Trust Live
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call evaluate_safe_call from your client
- Claude Code Trust Live evaluate_safe_call run in your project directory
- Claude Desktop Trust Live evaluate_safe_call ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor Trust Live evaluate_safe_call ~/.cursor/mcp.json
- VS Code Trust Live evaluate_safe_call .vscode/mcp.json
- Zed Trust Live evaluate_safe_call ~/.config/zed/settings.json
- Windsurf Trust Live evaluate_safe_call ~/.codeium/windsurf/mcp_config.json
- Cline Trust Live evaluate_safe_call ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI Trust Live evaluate_safe_call ~/.gemini/settings.json
- Grok Trust Live evaluate_safe_call .mcp.json (in your project root)
- ChatGPT Trust Live evaluate_safe_call Settings → Connectors → Advanced → Developer mode
- Claude.ai Trust Live evaluate_safe_call Settings → Connectors → Add custom connector
- LangChain Trust Live evaluate_safe_call pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http trust-live https://mcp-selection-lab-production.up.railway.app/trust-live/mcpOther tools on this server
This list was read from the server itself, by connecting to it and calling tools/list on 8 October 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.