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

# AI Agent Docs Integration

> Learn how to integrate AI agents with Loqate documentation using llms.txt, Skills or MCP.

Loqate publishes machine-readable documentation metadata that allows AI agents and developer tools to understand Loqate capabilities programmatically.

These integration points can be used by agent frameworks, MCP-compatible tools, IDE extensions, or custom automation.

## Available integration options

Depending on your tooling and integration model, use one or more of the following options.

### The `llms.txt` file

The `llms.txt` file is a structured documentation index.

It lists all the available documentation pages so agents can discover relevant content before answering questions.

See the `llms.txt` file at:

```url theme={null}
https://docs.loqate.com/llms.txt
```

### Skills CLI

The Skills CLI is a command-line tool that allows you to query the documentation and retrieve relevant information programmatically.

If your agent supports the [Skills CLI](https://www.npmjs.com/package/skills), then you can install the skill using:

```bash theme={null}
npx skills add https://docs.loqate.com/
```

During the installation, you'll be prompted to select an agent to install the skill for. Select the agent you want to integrate with Loqate documentation. If you don't see your agent listed, use the Search option to find it.

This command loads the Loqate documentation into the agent's context.

Start with a query like:

```bash theme={null}
based on the loqate .claude skill what is Loqate?
```

### MCP

When an AI application connects to the Loqate documentation Model Context Protocol (MCP) server, it can search the documentation and retrieve full page content directly, in response to your prompts.

Instead of relying on information from its training data or making a generic web search, your MCP server provides access to all indexed content on the documentation site.

Loqate exposes its documentation through a remote MCP server.

This enables MCP-compatible clients to query the documentation dynamically.

To connect, register the following URL as a remote MCP server in your client configuration:

```
https://docs.loqate.com/mcp
```

#### MCP tools

Your MCP server provides two tools that AI applications can use:

* **Search**: Searches across the Loqate documentation to find relevant content, returning snippets with titles and links. Use this when you need to discover information or find pages matching a query.

* **Get page**: Retrieves the full content of a specific documentation page by its path. Use this when you already know the page path, such as from search results, and need the complete content rather than a snippet.

AI applications determine when to use each tool based on the context of the conversation. For example, an AI application might first search your documentation to find relevant pages, then use the get page tool to retrieve the full content of the most relevant result.

#### Use MCP server

The Loqate documentation provides different options for using the MCP server:

<Tabs>
  <Tab title="Claude">
    Add the Loqate MCP server to Claude:

    1. Navigate to the [Connectors](https://claude.ai/settings/connectors) page in the Claude settings.
    2. Select **Add custom connector**.
    3. Add the Loqate MCP server:
       * **Name**: Loqate Docs
       * **URL**: `https://docs.loqate.com/mcp`
    4. Click **Add**.

    Access the MCP server in your chat:

    1. When using Claude, click the attachments button (the plus icon).
    2. Navigate to **Connectors**, you'll see the Loqate docs MCP connector you just added automatically enabled.
    3. Ask Claude a question about Loqate.
  </Tab>

  <Tab title="Claude Code">
    To use the Loqate MCP server with Claude Code, run the following command:

    ```bash theme={null}
    claude mcp add --transport http loqate-docs https://docs.loqate.com/mcp
    ```

    Test the connection by running:

    ```bash theme={null}
    claude mcp list
    ```
  </Tab>

  <Tab title="Cursor">
    To connect the Loqate MCP server to Cursor, follow these steps:

    <Steps>
      <Step title="Open MCP settings">
        1. Use `Command` + `Shift` + `P` (`Ctrl` + `Shift` + `P` on Windows) to open the command palette.
        2. Search for "Open MCP settings".
        3. Select **Add custom MCP**. This opens the `mcp.json` file.
      </Step>

      <Step title="Configure the Loqate MCP server">
        In `mcp.json`, add:

        ```json theme={null}
        {
          "mcpServers": {
            "loqate-docs": {
              "url": "https://docs.loqate.com/mcp"
            }
          }
        }
        ```
      </Step>

      <Step title="Test the connection">
        In Cursor's chat, ask "What tools do you have available?" Cursor should show the Loqate MCP server as an available tool.
      </Step>
    </Steps>
  </Tab>

  <Tab title="VS Code">
    To connect the Loqate MCP server to VS Code, create a `.vscode/mcp.json` file and add:

    ```json theme={null}
    {
      "servers": {
        "loqate-docs": {
          "type": "http",
          "url": "https://docs.loqate.com/mcp"
        }
      }
    }
    ```
  </Tab>
</Tabs>