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.
No reviews yet. Be the first to review!
Sign in to join the conversation
Highlight AIList all available prompts.
Retrieve a specific prompt by its ID.
Get the most recent prompt.
Fetch a prompt using a unique identifier.
Get details of a specific version of a prompt.
List all versions of a specific prompt.
Retrieve a prompt version using its associated tag.
List all tags associated with a specific prompt version.
Add a new tag to a specific prompt version.
Create or update a prompt.
List all projects available for observability data.
Retrieve details of a specific project.
List all available traces.
Get detailed information about a specific trace.
Retrieve spans associated with a specific trace.
Get annotations for a specific span.
List all available sessions.
Retrieve details of a specific session.
Get a list of available annotation configurations.
List all available datasets.
Retrieve a specific dataset by its ID.
Fetch examples from a specific dataset.
List experiments associated with a specific dataset.
Add new examples to a specific dataset.
List all experiments related to a specific dataset.
Retrieve detailed information about a specific experiment by its ID.
