The Arize AX MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Arize AX account. It provides structured and secure access to your projects, datasets, prompts, experiments, traces, and spans, so your agent can inspect AI activity, manage evaluation data, maintain prompts, run experiments, and review results on your behalf.
- Project and space discovery: Have your agent find accessible spaces and projects, then retrieve details about the AI applications you monitor.
- Dataset management: Let the agent create and rename datasets, add or update examples, and review examples from current or named dataset versions.
- Prompt versioning: Direct your agent to create prompts, publish new immutable versions, update prompt descriptions, and review current or previous versions.
- Experiment tracking: Instruct your agent to create experiments, append runs, and inspect experiment outputs for evaluation and comparison.
- Trace and span analysis: Have your agent review bounded sets of traces and spans within chosen time ranges and filters to investigate application behavior.