Arize Phoenix
Observability MCP for LLM apps: manage prompts, explore datasets, and run experiments.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Arize Phoenix, derived from its capabilities.
AIVSS 8.2 · High
View MAESTRO 7-layer threat model →Overview
Arize Phoenix is an open-source LLM observability and evaluation platform whose MCP server lets agents manage prompts, explore trace datasets, and run experiments across providers. It surfaces traces, spans, and eval results to the agent. Since traces can contain sensitive prompts, PII, and tool I/O, exposing them to an agent raises data-governance considerations.
Key features
- Prompt management tools
- Trace/dataset exploration
- Experiment execution
- Cross-provider evaluation
Use cases
- Debugging LLM app behavior
- Prompt iteration
- Running eval experiments