evaluate_capability — Agentic Keychain MCP Tool
evaluate_capability
(evaluate capability) is one of 11 tools on the
Agentic Keychain
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call evaluate_capability from your client
- Claude Code Agentic Keychain evaluate_capability run in your project directory
- Claude Desktop Agentic Keychain evaluate_capability ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor Agentic Keychain evaluate_capability ~/.cursor/mcp.json
- VS Code Agentic Keychain evaluate_capability .vscode/mcp.json
- Zed Agentic Keychain evaluate_capability ~/.config/zed/settings.json
- Windsurf Agentic Keychain evaluate_capability ~/.codeium/windsurf/mcp_config.json
- Cline Agentic Keychain evaluate_capability ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI Agentic Keychain evaluate_capability ~/.gemini/settings.json
- Grok Agentic Keychain evaluate_capability .mcp.json (in your project root)
- ChatGPT Agentic Keychain evaluate_capability Settings → Connectors → Advanced → Developer mode
- Claude.ai Agentic Keychain evaluate_capability Settings → Connectors → Add custom connector
- LangChain Agentic Keychain evaluate_capability pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http agentic-keychain https://agentickeychain.com/mcpOther tools on this server
This list was read from the server itself, by connecting to it and calling tools/list on 5 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.