> For the complete documentation index, see [llms.txt](https://docs.jetadmin.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.jetadmin.io/user-guide/data-sources/mcp/connect-an-mcp-server.md).

# Connect an MCP server

Step-by-step setup for connecting MCP servers as datasources.

### Steps to connect an MCP server in JetAdmin

1. Open **Data** in your app.
2. Add a new resource → Click Add Resource and choose MCP.
3. Fill in connection details → A popup will appear with the following fields:
   * Resource Name: Defaults to *MCP*, but you can rename it (e.g., Weather Information *MCP*).
   * Server URL: Example → `https://mcp.example.com/mcp`.
   * Protocol: Options include *Auto*, *Streamable HTTP*, and *SSE*.
   * Authorization: choose **Automatic** to use the server's sign-in flow, or **Manual** to configure authentication yourself.
   * Under Manual, Authentication (optional):
     * None
     * API Key
     * Basic Auth
     * OAuth 2.0

<figure><img src="https://3448227606-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-LQ08RFAKZvFADEiXKFy%2Fuploads%2F0IW9KGX4gGDl8uPk0q9i%2FS30-mcp-connection.jpg?alt=media" alt="MCP connection form with server and authorization settings"><figcaption><p>Enter your provider's real endpoint and required authorization settings. Example URLs are placeholders.</p></figcaption></figure>

4. Click Add Resource.

{% @arcade/embed url="<https://app.arcade.software/share/5hbgXqLkwNKN9LhAPkhp>" flowId="5hbgXqLkwNKN9LhAPkhp" %}

Once connected, the MCP server will be available as a datasource in your app. You can now bind it to data components, workflows, or agents. For example, you might call operations like `get_current_weather_tool` to display live weather for a city, or `get_weather_forecast_tool` to show multi-day forecasts directly in your JetAdmin app.

## Verify the connection

Open the resource and check the available actions. Run [Test an MCP tool](/user-guide/data-sources/mcp/test-an-mcp-tool.md) before connecting it to an agent or workflow. The example server URL above is a placeholder; use the endpoint supplied by your MCP provider.


---

# 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://docs.jetadmin.io/user-guide/data-sources/mcp/connect-an-mcp-server.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.