phoenix-support
Get expert guidance on using Phoenix for tracing AI applications, managing datasets and prompts, and conducting evaluations with OpenInference.
Instructions
Get help with Phoenix and OpenInference.
Tracing AI applications via OpenInference and OpenTelemetry
Phoenix datasets, experiments, and prompt management
Phoenix evals and annotations
Use this tool when you need assistance with Phoenix features, troubleshooting, or best practices.
Expected return: Expert guidance about how to use and integrate Phoenix
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Your question about Arize Phoenix, OpenInference, or related topics |
Implementation Reference
- Handler for the 'phoenix-support' tool. It calls the 'callRunLLMQuery' helper with the user query and returns the result formatted as MCP text content.async ({ query }) => { const result = await callRunLLMQuery({ query }); return { content: [ { type: "text", text: result, }, ], }; }
- Input schema for the 'phoenix-support' tool using Zod: a string 'query' with description.{ query: z .string() .describe( "Your question about Arize Phoenix, OpenInference, or related topics" ), },
- js/packages/phoenix-mcp/src/supportTools.ts:81-101 (registration)Registration of the 'phoenix-support' tool on the MCP server within the initializeSupportTools function, including name, description reference, input schema, and inline handler."phoenix-support", PHOENIX_SUPPORT_DESCRIPTION, { query: z .string() .describe( "Your question about Arize Phoenix, OpenInference, or related topics" ), }, async ({ query }) => { const result = await callRunLLMQuery({ query }); return { content: [ { type: "text", text: result, }, ], }; } );
- Core helper function used by the phoenix-support handler. Creates an MCP client to RunLLM server and calls their 'search' tool with the query, extracts and returns text response.export async function callRunLLMQuery({ query, }: { query: string; }): Promise<string> { const client = await createRunLLMClient(); // Call the chat tool with the user's question const result = await client.callTool({ name: "search", arguments: { query: query, }, }); // There's usually only one content item, but we'll handle multiple for safety if (result.content && Array.isArray(result.content)) { const textContent = result.content .filter((item) => item.type === "text") .map((item) => item.text) .join("\n"); if (textContent) { return textContent; } } return "No response received from support"; }
- js/packages/phoenix-mcp/src/index.ts:45-45 (registration)Invocation of initializeSupportTools in the main server setup, which registers the phoenix-support tool among others.initializeSupportTools({ server });