"The server had an error processing your request" w/ Streamablehttp MCP example

[dokato]

Describe the bug

I follow the steps from:
https://github.com/openai/openai-agents-python/tree/main/examples/mcp/streamablehttp_example

but when the first question goes to the agent it fails with:

  File "/Users/dd/miniconda3/envs/myenv/lib/python3.13/site-packages/openai/_base_client.py", line 1794, in post
    return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/dd/miniconda3/envs/myenv/lib/python3.13/site-packages/openai/_base_client.py", line 1594, in request
    raise self._make_status_error_from_response(err.response) from None
openai.InternalServerError: Error code: 500 - {'error': {'code': 500, 'message': 'The server had an error processing your request. Sorry about that! You can retry your request,
or contact support@openai.com if you keep seeing this error.', 'param': None, 'type': 'cr_error'}}

Debug information

• Agents SDK version: 0.6.1
• Python 3.13

Repro steps

Just running https://github.com/openai/openai-agents-python/tree/main/examples/mcp/streamablehttp_example

Expected behavior

The agent responds with my local MCP server tool.

[seratch]

Thanks for writing in. I just run the example uv run -m examples.mcp.streamablehttp_example.main and it worked without any issues for me. Could you rerun the example now? If the same error still arises, please share the error details with our technical support team like the error message suggests. They can check your org situation and what's going on on the server side.