> For the complete documentation index, see [llms.txt](https://v2.dataos.info/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://v2.dataos.info/consume/consume-with-ai/connect-an-agentic-framework/vercel-ai-sdk.md).

# Vercel AI SDK

Connect Vercel AI SDK applications to Data Product MCP tools.

Connecting Data Product MCP to a Vercel AI SDK application lets it answer from governed products instead of guessing. The `@ai-sdk/mcp` package exposes DataOS tools to your app's tool loop. See the [Vercel AI SDK MCP documentation](https://ai-sdk.dev/docs/ai-sdk-core/mcp-tools) for client setup and tool usage.

## Prerequisites

Node.js 18 or later, your DataOS instance URL, and a [DataOS API token](https://v2.dataos.info/consume/get-started/before-you-begin.md).

## Connect

1. Install the packages:

```bash
npm install @ai-sdk/mcp ai @ai-sdk/openai
```

2. Following the Vercel AI SDK MCP docs, initialize an MCP client over HTTP transport with these DataOS values:

| Parameter    | Value                                           |
| ------------ | ----------------------------------------------- |
| Transport    | `http`                                          |
| URL          | `https://<instance-url>/dataproduct-mcp/api/v1` |
| Header key   | `apikey`                                        |
| Header value | Your DataOS API token                           |

{% hint style="warning" %}
[API tokens](https://v2.dataos.info/references/key-concepts/api-tokens) are secrets. Pass the token through an environment variable rather than hardcoding it.
{% endhint %}

## Verify

Run the application and confirm the MCP client loads Data Product MCP tools. Then ask the agent `What data products am I authorized to access?`. A working connection returns products scoped to your token.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://v2.dataos.info/consume/consume-with-ai/connect-an-agentic-framework/vercel-ai-sdk.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
