> For the complete documentation index, see [llms.txt](https://paypal.gitbook.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://paypal.gitbook.com/agent-toolkit-and-mcp-server/agent-toolkit-and-mcp-server.md).

# Agent Toolkit & MCP Server

Connect agent frameworks, integrate PayPal APIs, and build intelligent workflows with function calling.

<a href="/agent-toolkit-and-mcp-server/agent-toolkit/quickstart.md" class="button primary">Agent Quickstart</a> <a href="/agent-toolkit-and-mcp-server/mcp-server/set-up-a-local-mcp-server.md" class="button primary">Set up an MCP server</a>

### Key features

The PayPal agent toolkit enables you to:

* **Integrate with PayPal APIs** to access orders, invoices, subscriptions, shipment tracking, transaction details, and dispute management through pre-built functions.
* **Develop with your preferred tools**, including:
  * AI agent frameworks like [OpenAI’s Agents SDK](https://github.com/openai/openai-agents-python), [Vercel’s AI SDK](https://sdk.vercel.ai/), [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction), [LangChain](https://www.langchain.com/), and [CrewAI](https://www.crewai.com/)
  * Multiple languages, including TypeScript and Python
* **Build custom agent capabilities** to extend core PayPal features and connect with other toolkits to create multi-step agent workflows.

Model Context Protocol (MCP) facilitates the management and transmission of relevant information to models, ensuring their effective operation within specified contexts. Leveraging this technology, PayPal developed an MCP server that enables merchants to interact with their preferred MCP clients using natural language. This functionality allows users to efficiently perform various business tasks with their choice of MCP client.

Examples in this content use Claude as the MCP client, but you can use any MCP client that you prefer, such as Cursor or Cline.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://paypal.gitbook.com/agent-toolkit-and-mcp-server/agent-toolkit-and-mcp-server.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.