Skip to main content
Glama

@arizeai/phoenix-mcp

Official
by Arize-ai
03.14.2025-openai-agents-instrumentation.md1.43 kB
--- description: Available in Phoenix 8.13+ --- # 03.14.2025: OpenAI Agents Instrumentation 📡 {% embed url="https://storage.googleapis.com/arize-phoenix-assets/assets/gifs/openai_sdk_rn.gif" %} We've introduced the **OpenAI Agents SDK** for Python which provides enhanced visibility into agent behavior and performance. **Installation** ``` pip install openinference-instrumentation-openai-agents openai-agents ``` * Includes an OpenTelemetry Instrumentor that traces agents, LLM calls, tool usage, and handoffs. * With minimal setup, use the `register` function to connect your app to Phoenix and view real-time traces of agent workflows. For more details on a quick setup, check out our integration documentation: {% embed url="https://arize.com/docs/phoenix/tracing/integrations-tracing/openai-agents-sdk" %} ### Walkthrough Video {% embed url="https://youtu.be/iOGu7-HYm6s?si=mOSWYG9wSlGajf4C" %} ### Improvements and Bug Fixes 🐛 * [**Prompt Playground**](https://github.com/Arize-ai/phoenix/issues/6788): Azure API key made optional, included specialized UI for thinking budget parameter * [**Performance**](https://github.com/Arize-ai/phoenix/pull/6756): Make the spans table the default tab * [**Components**](https://github.com/Arize-ai/phoenix/issues/6771): Added react-aria Tabs components * [**Enhancement**](https://github.com/Arize-ai/phoenix/pull/6749): Download experiment runs and annotations as CSV

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Arize-ai/phoenix'

If you have feedback or need assistance with the MCP directory API, please join our Discord server