> ## Documentation Index
> Fetch the complete documentation index at: https://www.adaline.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Use MCP servers in prompts

> Connect to Model Context Protocol servers to access external tools and data sources from your prompts

The [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) is an open protocol that enables AI models to securely access external data sources, tools, and resources through a standardized interface. Adaline's Editor lets you connect to remote MCP servers and use their tools directly in your prompts — enabling powerful integrations without custom backend code.

## Enable MCP

<Steps>
  <Step title="Select a compatible model">
    Open the model selector and choose an LLM that supports MCP integration.

    <Warning>
      MCP integration currently requires selecting an **Anthropic** model. If you need MCP support for other providers, contact [support@adaline.ai](mailto:support@adaline.ai) for a private preview.
    </Warning>
  </Step>

  <Step title="Open MCP settings">
    In the model settings panel, select **MCP**.

    <img src="https://mintcdn.com/adaline/-Bsa4BuK4fSdmy67/images/iterate/select-mcp.png?fit=max&auto=format&n=-Bsa4BuK4fSdmy67&q=85&s=0cb61d71edece43fc2a55095725b1bf1" alt="Selecting MCP in Adaline" title="Selecting MCP in Adaline" style={{ width: "100%" }} width="947" height="785" data-path="images/iterate/select-mcp.png" />
  </Step>

  <Step title="Toggle MCP on">
    Set the MCP toggle to **On** to enable the integration.

    <img src="https://mintcdn.com/adaline/-Bsa4BuK4fSdmy67/images/iterate/mcp-toggle-on.png?fit=max&auto=format&n=-Bsa4BuK4fSdmy67&q=85&s=7922948221f307c77925e10a98be4980" alt="Enabling MCP in Adaline" title="Enabling MCP in Adaline" style={{ width: "100%" }} width="1013" height="353" data-path="images/iterate/mcp-toggle-on.png" />
  </Step>
</Steps>

Once enabled, the Editor displays the MCP configuration panel where you can add your server settings:

<img src="https://mintcdn.com/adaline/-Bsa4BuK4fSdmy67/images/iterate/mcp-integration-ready.png?fit=max&auto=format&n=-Bsa4BuK4fSdmy67&q=85&s=b6e398fc56118095fb969dd7f0b52b22" alt="MCP integration ready in Adaline" title="MCP integration ready in Adaline" style={{ width: "100%" }} width="1021" height="674" data-path="images/iterate/mcp-integration-ready.png" />

## Configure an MCP server

Each MCP server requires a JSON configuration object. Here is the complete schema:

```json theme={null}
{
  "type": "url",
  "url": "https://example-server.modelcontextprotocol.io/sse",
  "name": "example-mcp",
  "tool_configuration": {
    "enabled": true,
    "allowed_tools": ["example_tool_1", "example_tool_2"]
  },
  "authorization_token": "YOUR_TOKEN"
}
```

### Configuration reference

| Field                              | Type    | Required | Description                                                            |
| ---------------------------------- | ------- | -------- | ---------------------------------------------------------------------- |
| `type`                             | String  | Yes      | Currently only `"url"` is supported.                                   |
| `url`                              | String  | Yes      | The MCP server URL. Must start with `https://`.                        |
| `name`                             | String  | Yes      | A unique identifier for the server. Choose a descriptive name.         |
| `tool_configuration`               | Object  | No       | Controls which tools from the server are available.                    |
| `tool_configuration.enabled`       | Boolean | No       | Whether to enable tools from the server (default: `true`).             |
| `tool_configuration.allowed_tools` | Array   | No       | Restrict which tools are allowed. By default, all tools are available. |
| `authorization_token`              | String  | No       | OAuth authorization token, if required by the server.                  |

## Connect to multiple servers

You can connect to multiple MCP servers simultaneously by providing an array of server configurations:

```json theme={null}
[
  {
    "type": "url",
    "url": "https://mcp.example1.com/sse",
    "name": "mcp-server-1",
    "authorization_token": "YOUR_TOKEN_1"
  },
  {
    "type": "url",
    "url": "https://mcp.example2.com/sse",
    "name": "mcp-server-2",
    "authorization_token": "YOUR_TOKEN_2"
  }
]
```

Each server's tools become available to the model independently. The model can choose which server's tools to invoke based on the conversation context.

## Authentication

Many MCP servers require OAuth authentication. To obtain an access token:

1. Use the [MCP Inspector](https://modelcontextprotocol.io/docs/tools/inspector) or your server provider's OAuth flow to generate a token.
2. Paste the token into the `authorization_token` field in your server configuration.

<Note>
  Keep your authorization tokens secure. If your MCP server's tokens have an expiry, you will need to refresh them periodically.
</Note>

## Next steps

<CardGroup cols={2}>
  <Card title="Use Tools in Prompts" icon="wrench" href="/docs/iterate/use-tools-in-prompt">
    Define custom tools with JSON schemas and HTTP backends.
  </Card>

  <Card title="Tool Calls in Playground" icon="play" href="/docs/iterate/tool-calls-in-playground">
    Test MCP-powered and tool-powered prompts in the Playground.
  </Card>
</CardGroup>