The Arize Phoenix MCP Server provides a unified interface for interacting with the Arize Phoenix platform. With this server, you can:
Prompts Management: Create, list, update, and iterate on prompts, including their templates, model configurations, and invocation parameters. Get specific prompt versions (latest, by ID, by tag).
Datasets: Explore datasets, retrieve examples, and add synthetically generated examples to cover edge cases.
Experiments: List and retrieve experiment results, including metadata, outputs, and annotations for evaluating model performance.
Tags and Versions: Manage prompt versions by adding tags, listing versions, and fetching specific versions.
Integration: Easily integrate with clients like Claude Desktop and Cursor using
npx.Open-Source: Extend functionality by contributing to the open-source project.
Enables environment variable configuration for development, allowing secure management of API keys and base URLs
Provides open-source access to the Phoenix MCP implementation, allowing for contributions and customizations
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@@arizeai/phoenix-mcplist my recent prompts"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Phoenix MCP Server is an implementation of the Model Context Protocol for the Arize Phoenix platform. It provides a unified interface to Phoenix's capabilities.
You can use Phoenix MCP Server for:
Projects Management: List and explore projects that organize your observability data
Spans & Annotations: Retrieve spans and their annotations for analysis and debugging
Prompts Management: Create, list, update, and iterate on prompts
Datasets: Explore datasets and synthesize new examples
Experiments: Pull experiment results and visualize them with the help of an LLM
Don't see a use-case covered? @arizeai/phoenix-mcp is open-source! Issues and PRs welcome.
Installation
This MCP server can be used with npx and can be directly integrated with clients like Claude Desktop, Cursor, and more.
{
"mcpServers": {
"phoenix": {
"command": "npx",
"args": [
"-y",
"@arizeai/phoenix-mcp@latest",
"--baseUrl",
"https://my-phoenix.com",
"--apiKey",
"your-api-key"
]
}
}
}Related MCP server: MCP Server
Development
Install
This package is managed via a pnpm workspace.
// From the /js/ directory
pnpm install
pnpm buildThis only needs to be repeated if dependencies change or there is a change to the phoenix-client.
Building
To build the project:
pnpm buildDevelopment Mode
To run in development mode:
pnpm devDebugging
You can build and run the MCP inspector using the following:
pnpm inspectEnvironment Variables
When developing, the server requires the following environment variables:
PHOENIX_API_KEY: Your Phoenix API keyPHOENIX_BASE_URL: The base URL for Phoenix
Make sure to set these in a .env file. See .env.example.
Community
Join our community to connect with thousands of AI builders:
π Join our Slack community.
π Read the Phoenix documentation.
π‘ Ask questions and provide feedback in the #phoenix-support channel.
π Leave a star on our GitHub.
π Report bugs with GitHub Issues.
π Follow us on π.
πΊοΈ Check out our roadmap to see where we're heading next.
License
Apache 2.0
Resources
Looking for Admin?
Admins can modify the Dockerfile, update the server description, and track usage metrics. If you are the server author, to access the admin panel.