The MCP server exposes a set of tools that your AI assistant (Claude, ChatGPT, Gemini, etc.) can call to read Agent configuration, query metrics, pull conversation data, manage test cases and test runs, and propose changes to resources (knowledge articles, custom instructions, test cases). Each tool page documents parameters, response shape, and example usage.
get_available_filters → get_conversations → get_conversation (for selected IDs) → get_ada_metric for aggregates.get_ada_configuration → search_knowledge / search_coaching to cross-reference existing content.get_improvement_guide → get_ada_metric (to find under-performing conversations) → get_conversation (for transcripts) → get_ada_configuration (to identify gaps) → search_knowledge / search_coaching → propose_change to create or update entities.get_conversations (production samples) → propose_change with test_case → propose_change with test_run → get_test_runs to review results.