@arizeai/phoenix-mcp

--- description: Available in Phoenix 8.26+ --- # 04.18.2025: Tracing for MCP Client-Server Applications 🔌 {% embed url="https://storage.googleapis.com/arize-phoenix-assets/assets/images/MCP%20tracing.png" %} We’re excited to announce a powerful capability in the [**OpenInference**](https://github.com/Arize-ai/openinference) OSS library **`openinference-instrumentation-mcp` —** seamless OTEL context propagation for MCP clients and servers. ### **What’s New?** This release introduces automatic distributed tracing for **Anthropic’s Model Context Protocol (MCP)**. Using OpenTelemetry, you can now: * **Propagate context** across MCP client-server boundaries * Generate **end-to-end traces** of your AI system across services and languages * Gain full visibility into how models access and use external context The `openinference-instrumentation-mcp` package handles this for you by: * Creating spans for MCP client operations * Injecting trace context into MCP requests * Extracting and continuing the trace context on the server * Associating the context with OTEL spans on the server side ### **Set up** 1. Instrument both MCP client and server with OpenTelemetry. 2. Add the `openinference-instrumentation-mcp` package. 3. Spans will propagate across services, appearing as a **single connected trace** in Phoenix. Full example usage is available:  {% embed url="https://github.com/Arize-ai/phoenix/tree/main/tutorials/mcp/tracing_between_mcp_client_and_server" %} ### **Walkthrough Video** {% embed url="https://youtu.be/dhK2pWQdGjk?si=J5w9a42z58w6oqjE" %} ### **Acknowledgments** Big thanks to Adrian Cole and Anuraag Agrawal for their contributions to this feature.