> ## Documentation Index
> Fetch the complete documentation index at: https://arizeai-433a7140.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Claude Agent SDK (Python)

> Trace Anthropic's Claude Agent SDK applications in Python with Phoenix

<Note>Looking for TypeScript? See the [TypeScript guide](/docs/phoenix/integrations/typescript/claude-agent-sdk).</Note>

[![PyPI Version](https://img.shields.io/pypi/v/openinference-instrumentation-claude-agent-sdk.svg)](https://pypi.python.org/pypi/openinference-instrumentation-claude-agent-sdk)

This module provides [OpenInference](https://github.com/Arize-ai/openinference) instrumentation for [Anthropic's Claude Agent SDK](https://platform.claude.com/docs/en/agent-sdk/overview), automatically capturing **AGENT** and **TOOL** spans that follow OpenInference semantic conventions.

## Install

```bash theme={null}
pip install openinference-instrumentation-claude-agent-sdk claude-agent-sdk arize-phoenix-otel
```

## Setup

Use the `register` function to connect your application to Phoenix:

```python theme={null}
from phoenix.otel import register

tracer_provider = register(
  project_name="claude-agent-sdk",
  auto_instrument=True,
)
```

## Run Claude Agent SDK

A simple Claude Agent SDK application that is now instrumented:

```python expandable theme={null}
import asyncio
from claude_agent_sdk import query, ClaudeAgentOptions, AssistantMessage, TextBlock


async def main():
    async for message in query(
        prompt="What files are in the current directory?",
        options=ClaudeAgentOptions(allowed_tools=["Bash", "Glob"]),
    ):
        if isinstance(message, AssistantMessage):
            for block in message.content:
                if isinstance(block, TextBlock):
                    print(block.text)


asyncio.run(main())
```

## Observe

With instrumentation enabled, you will see the following in Phoenix:

* **AGENT spans** wrapping the full `query()` call, capturing the prompt and final response
* **TOOL spans** for each tool invocation made by the agent during execution (e.g., Bash commands, file reads)

These spans follow [OpenInference semantic conventions](https://github.com/Arize-ai/openinference), making them fully compatible with Phoenix's trace visualization and evaluation features.

## Privacy Configuration

If you need to hide sensitive data, use the instrumentor directly instead of `auto_instrument`:

```python theme={null}
from phoenix.otel import register
from openinference.instrumentation.claude_agent_sdk import ClaudeAgentSDKInstrumentor

tracer_provider = register(project_name="claude-agent-sdk")

ClaudeAgentSDKInstrumentor().instrument(
    tracer_provider=tracer_provider,
    hide_inputs=True,
    hide_outputs=True,
)
```

## Resources

* [PyPI Package](https://pypi.python.org/pypi/openinference-instrumentation-claude-agent-sdk)

* [OpenInference package for Claude Agent SDK](https://github.com/Arize-ai/openinference/tree/main/python/instrumentation/openinference-instrumentation-claude-agent-sdk)

* [Claude Agent SDK Documentation](https://platform.claude.com/docs/en/agent-sdk/overview)