evaluate_step — AgenticRail Gate - sequence enforcement and verifiable audit receipts for AI agent compliance MCP Tool
evaluate_step
(evaluate step) is one of 2 tools on the
AgenticRail Gate - sequence enforcement and verifiable audit receipts for AI agent compliance
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call evaluate_step from your client
- Claude Code AgenticRail Gate - sequence enforcement and verifiable audit receipts for AI agent compliance evaluate_step run in your project directory
- Claude Desktop AgenticRail Gate - sequence enforcement and verifiable audit receipts for AI agent compliance evaluate_step ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor AgenticRail Gate - sequence enforcement and verifiable audit receipts for AI agent compliance evaluate_step ~/.cursor/mcp.json
- VS Code AgenticRail Gate - sequence enforcement and verifiable audit receipts for AI agent compliance evaluate_step .vscode/mcp.json
- Zed AgenticRail Gate - sequence enforcement and verifiable audit receipts for AI agent compliance evaluate_step ~/.config/zed/settings.json
- Windsurf AgenticRail Gate - sequence enforcement and verifiable audit receipts for AI agent compliance evaluate_step ~/.codeium/windsurf/mcp_config.json
- Cline AgenticRail Gate - sequence enforcement and verifiable audit receipts for AI agent compliance evaluate_step ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI AgenticRail Gate - sequence enforcement and verifiable audit receipts for AI agent compliance evaluate_step ~/.gemini/settings.json
- Grok AgenticRail Gate - sequence enforcement and verifiable audit receipts for AI agent compliance evaluate_step .mcp.json (in your project root)
- ChatGPT AgenticRail Gate - sequence enforcement and verifiable audit receipts for AI agent compliance evaluate_step Settings → Connectors → Advanced → Developer mode
- Claude.ai AgenticRail Gate - sequence enforcement and verifiable audit receipts for AI agent compliance evaluate_step Settings → Connectors → Add custom connector
- LangChain AgenticRail Gate - sequence enforcement and verifiable audit receipts for AI agent compliance evaluate_step pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http gate https://mcp.agenticrail.nz/Other 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.