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.
まだレビューはありません. 最初のレビューを投稿しましょう！
会話に参加するにはサインインしてください
Highlight AIRetrieve a list of all available prompts.
Fetch details of a specific prompt.
Get the most recent prompt added.
Fetch a prompt using its unique identifier.
Retrieve a specific version of a prompt.
List all versions of a specific prompt.
Fetch a prompt version using a specific tag.
List all tags associated with a prompt version.
Add a new tag to a prompt version.
Create or update a prompt.
Retrieve a list of all projects.
Fetch details of a specific project.
Retrieve a list of all traces.
Fetch details of a specific trace.
Retrieve spans associated with a specific trace.
Fetch annotations for a specific span.
Retrieve a list of all sessions.
Fetch details of a specific session.
Retrieve a list of all annotation configurations.
Retrieve a list of all datasets.
Fetch details of a specific dataset.
Retrieve examples from a specific dataset.
Fetch experiments associated with a specific dataset.
Add new examples to a dataset.
Retrieve a list of experiments for a specific dataset.
Fetch details of a specific experiment using its ID.
