> 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.md).

# Connect an agentic framework

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

## What you need

Your DataOS instance URL, a [DataOS API token](/consume/get-started/before-you-begin.md), and a framework that can use MCP tools over HTTP. See [API tokens](https://v2.dataos.info/references/key-concepts/api-tokens) for how tokens work. Every framework uses the same endpoint:

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

From a product page, select **Activate → MCP** to open **Connect with MCP**; the **Agentic Framework** section links each guide.

## Pick your framework

| Framework                                                                               | Use when                                                          |
| --------------------------------------------------------------------------------------- | ----------------------------------------------------------------- |
| [LangChain](/consume/consume-with-ai/connect-an-agentic-framework/langchain.md)         | You register Data Product MCP tools with a Python LangChain agent |
| [Vercel AI SDK](/consume/consume-with-ai/connect-an-agentic-framework/vercel-ai-sdk.md) | You expose the tools to a TypeScript app's AI SDK tool loop       |
| [AgentScope](/consume/consume-with-ai/connect-an-agentic-framework/agentscope.md)       | You register the tools in an AgentScope toolkit                   |
| [Custom](/consume/consume-with-ai/connect-an-agentic-framework/custom.md)               | You use another framework or MCP client library                   |

## Tool behavior

Frameworks receive the same Data Product MCP tool surface as desktop clients. The agent chooses tools based on the request, but DataOS still enforces authorization, tenant boundaries, masking, and product contracts before returning data. Use application-level prompts to preserve citation discipline: instruct the agent to show the metric, source product, filters, and time window for every analytical answer.

Once connected, use [Discover in natural language](/consume/consume-with-ai/discover-in-natural-language.md) and [Understand in natural language](/consume/consume-with-ai/understand-in-natural-language.md).


---

# 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-an-agentic-framework.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.