@arizeai/phoenix-mcp

--- description: Pull and push prompt changes via Phoenix's Python and TypeScript Clients --- # Prompts in Code <figure><img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/prompts_in_code.png" alt=""><figcaption><p>Pull and push prompt changes via Phoenix's Python and TypeScript Clients</p></figcaption></figure> Using Phoenix as a backend, Prompts can be managed and manipulated via code by using our Python or TypeScript SDKs. With the Phoenix Client SDK you can: * [Create / Update](../how-to-prompts/create-a-prompt.md#using-the-phoenix-client) prompts dynamically * [Pull prompts](../how-to-prompts/using-a-prompt.md) templates by name, version, or tag * [Format prompt](../how-to-prompts/using-a-prompt.md#using-a-prompt) templates with runtime variables and use them in your code. Native support for OpenAI, Anthropic, Gemini, Vercel AI SDK, and more. No propriatry client necessary. * Support for [tool calling](https://app.gitbook.com/s/fqGNxHHFrgwnCxgUBNsJ/prompt-engineering/prompts-concepts#tools) and [response formats](https://app.gitbook.com/s/fqGNxHHFrgwnCxgUBNsJ/prompt-engineering/prompts-concepts#response-format). Execute tools defined within the prompt. Phoenix prompts encompasses more than just the text and messages. To learn more about managing Prompts in code, see [using-a-prompt.md](../how-to-prompts/using-a-prompt.md "mention")