evaluate — AgentRank MCP Tool
evaluate
(evaluate) is one of 5 tools on the
AgentRank
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call evaluate from your client
- Claude Code AgentRank evaluate run in your project directory
- Claude Desktop AgentRank evaluate ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor AgentRank evaluate ~/.cursor/mcp.json
- VS Code AgentRank evaluate .vscode/mcp.json
- Zed AgentRank evaluate ~/.config/zed/settings.json
- Windsurf AgentRank evaluate ~/.codeium/windsurf/mcp_config.json
- Cline AgentRank evaluate ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI AgentRank evaluate ~/.gemini/settings.json
- Grok AgentRank evaluate .mcp.json (in your project root)
- ChatGPT AgentRank evaluate Settings → Connectors → Advanced → Developer mode
- Claude.ai AgentRank evaluate Settings → Connectors → Add custom connector
- LangChain AgentRank evaluate pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http agentrank https://agentrank-ai.com/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.