Arize Phoenix MCP server

Phoenix MCP Server is an implementation of the Model Context Protocol for the Arize Phoenix platform, providing a unified interface to Phoenix's capabilities. It allows you to manage projects, work with spans and annotations, handle prompts, explore datasets, and pull experiment results with LLM assistance.

Installation and Setup

You can use the Phoenix MCP server with tools like Claude Desktop, Cursor, and other MCP-compatible clients. The simplest way to get started is using npx:

npx -y @arizeai/phoenix-mcp@latest --baseUrl https://my-phoenix.com --apiKey your-api-key

Configuring MCP Client

To configure the Phoenix MCP server in a compatible client, add the following configuration:

{
  "mcpServers": {
    "phoenix": {
      "command": "npx",
      "args": [
        "-y",
        "@arizeai/phoenix-mcp@latest",
        "--baseUrl",
        "https://my-phoenix.com",
        "--apiKey",
        "your-api-key"
      ]
    }
  }
}

Replace https://my-phoenix.com with your Phoenix instance URL and your-api-key with your actual API key.

Environment Variables

If you're running the server directly, you'll need to set the following environment variables:

• PHOENIX_API_KEY: Your Phoenix API key
• PHOENIX_BASE_URL: The base URL for Phoenix

You can set these in a .env file in your project directory.

Using Phoenix MCP Server

Once configured, the Phoenix MCP Server provides access to several key features:

Projects Management

Use the server to list and explore projects that organize your observability data. Projects serve as containers for your model monitoring and evaluation activities.

Working with Spans & Annotations

Retrieve spans and their annotations for analysis and debugging. This allows you to examine the detailed execution flow of your models and identify potential issues.

Prompt Management

Create, list, update, and iterate on prompts through the MCP interface. This functionality helps you organize and refine the prompts used with your models.

Dataset Exploration

Access and explore datasets, and synthesize new examples as needed. This helps you understand your data better and generate additional test cases.

Experiment Analysis

Pull experiment results and visualize them with the help of an LLM. This feature makes it easier to interpret complex experimental outcomes and draw meaningful conclusions.

Community Resources

For additional help and information, you can:

• Join the Slack community at Arize Slack
• Read the Phoenix documentation
• Report bugs on GitHub Issues
• Follow development on the roadmap

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "phoenix" '{"command":"npx","args":["-y","@arizeai/phoenix-mcp@latest","--baseUrl","https://my-phoenix.com","--apiKey","your-api-key"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "phoenix": {
            "command": "npx",
            "args": [
                "-y",
                "@arizeai/phoenix-mcp@latest",
                "--baseUrl",
                "https://my-phoenix.com",
                "--apiKey",
                "your-api-key"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "phoenix": {
            "command": "npx",
            "args": [
                "-y",
                "@arizeai/phoenix-mcp@latest",
                "--baseUrl",
                "https://my-phoenix.com",
                "--apiKey",
                "your-api-key"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect