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.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
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 and capabilities
- Prompt management tools
- Trace/dataset exploration
- Experiment execution
- Cross-provider evaluation
Use cases
- Debugging LLM app behavior
- Prompt iteration
- Running eval experiments