> 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-agentic-frameworks.md).

# Connect an agentic framework

Integrating Data Product MCP into an agentic application lets your agent answer from governed Data Products instead of guessing — it can run catalog discovery, semantic querying, lineage, quality, run history, and profiling against trusted, authorized data.

## Prerequisites

You need:

* Your DataOS instance URL, such as `pacific-051426.dataos.cloud`.
* A DataOS API token generated from [Home → Generate API tokens](/consume/get-started/readme-1.md#get-a-dataos-api-token).
* A framework or SDK that can use MCP tools over HTTP.

Use this endpoint in each framework:

```
https://<instance-url>/dataproduct-mcp/api/v1
```

## Setup flow

From the Data Product page, select **Activate → MCP** to open the **Connect with MCP** page. The **Agentic Framework** section lists LangChain and Vercel AI SDK, each with a **View install guide** link.

![Connect with MCP page showing the Agentic Framework section and other activation options](/files/1oBLDt2Jnj5lqhyU7beh)

## Supported frameworks

| Framework                                                                             | Use when                                                                                          | Documentation                                                             |
| ------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------- |
| [LangChain](/consume/consume-with-ai/connect-agentic-frameworks/langchain.md)         | You want to register Data Product MCP tools with a Python LangChain agent.                        | [LangChain MCP docs](https://docs.langchain.com/oss/python/langchain/mcp) |
| [Vercel AI SDK](/consume/consume-with-ai/connect-agentic-frameworks/vercel-ai-sdk.md) | You want to expose Data Product MCP tools to a TypeScript application using the AI SDK tool loop. | [Vercel AI SDK MCP docs](https://ai-sdk.dev/docs/ai-sdk-core/mcp-tools)   |
| [Custom](/consume/consume-with-ai/connect-agentic-frameworks/custom.md)               | You use another agentic framework or MCP client library not listed above.                         | Not applicable                                                            |

## Tool behavior

Frameworks receive the same Data Product MCP tool surface as desktop clients. The agent chooses tools based on the user's request, but DataOS still enforces authorization, Tenant boundaries, masking, and Data Product contracts before returning data.

Use application-level prompts to preserve citation discipline. For analytical answers, instruct the agent to show the metric, source Data Product, filters, and time window returned by Data Product MCP.

## Next steps

* [Discover with AI](/consume/discover/discover-with-ai.md) - Find relevant Data Products through natural language.
* [Custom agentic framework](/consume/consume-with-ai/connect-agentic-frameworks/custom.md) - Connect a framework not listed above.


---

# 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://v2.dataos.info/consume/consume-with-ai/connect-agentic-frameworks.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.