Arize Phoenix

Provides a unified interface to Arize Phoenix's capabilities for managing prompts, exploring datasets, and running experiments across different LLM providers

Phoenix MCP Server provides a unified interface to Arize Phoenix's capabilities through the Model Context Protocol. Developed by Arize AI, this TypeScript implementation enables AI assistants to manage prompts, explore datasets, and run experiments against the Phoenix platform. The server exposes tools for creating and iterating on prompts across different LLM providers (OpenAI, Anthropic, Google), working with evaluation datasets, and visualizing experiment results, making it particularly valuable for teams building and evaluating LLM applications who want to leverage Phoenix's observability features through AI assistants.