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

# Voucherify Docs MCP

> Connect AI tools like Claude, Cursor, and VS Code to Voucherify documentation using MCP

Model Context Protocol (MCP) is an open protocol for a standardized connection between AI tools and other tools, like documentation.

You can connect your AI tool, like Claude, Cursor, or others, directly to Voucherify documentation. This way, when you ask questions about Voucherify to your AI tool, it will base its answers directly on the content of the documentation instead of on the trained data or web-based search. This ensures that the answers are always up-to-date with the documentation.

## Documentation MCP tools

The MCP supports two tools for agents to use:

* Search: Searches across the documentation to find relevant content. Use this to discover information or find pages matching a query.
* Query docs filesystem: Reads and navigates the documentation's virtual filesystem using shell-style commands. Use this to retrieve page content, browse the docs structure, or extract specific sections.

Agents determine when to use each tool based on the context of the conversation.

## Connect to documentation MCP

Voucherify documentation MCP can be accessed through the following URL:

```Voucherify docs MCP theme={null}
https://docs.voucherify.io/mcp
```

<Tabs>
  <Tab title="Quickstart installation">
    You can install the MCP through the **Copy page** context menu in this page:

    1. Unroll **Copy page** drop-down menu at the top of this page.
    2. Select:
       * **Copy MCP Server** to copy the MCP server URL to clipboard.
       * **Copy MCP install command** to copy the `npx` command to install the MCP server.
       * **Connect to Cursor** to open Cursor and install the MCP server.
       * **Connect to VS Code** to open Visual Studio Code and install the MCP server.
  </Tab>

  <Tab title="Claude">
    In Claude settings:

    1. Navigate to the **Connectors** page.
    2. Select **Add custom connector**.
    3. Add Voucherify MCP server name and URL.
    4. Select **Add**.
    5. When using Claude, select the attachments button (the plus icon).
    6. Select Voucherify MCP server.

    See the [Model Context Protocol documentation](https://modelcontextprotocol.io/docs/develop/connect-remote-servers#connecting-to-a-remote-mcp-server) for more details.
  </Tab>

  <Tab title="Claude Code">
    Use the following command to connect Voucherify documentation MCP to Claude Code.

    ```bash Claude command wrap theme={null}
    claude mcp add --transport http VoucherifyDocsMCP https://docs.voucherify.io/mcp
    ```

    See the [Claude Code documentation](https://docs.anthropic.com/en/docs/claude-code/mcp#installing-mcp-servers) for more details.
  </Tab>

  <Tab title="Cursor">
    In Cursor:

    1. Open the command palette.
    2. Search for **Open MCP settings**.
    3. Select **Add custom MCP**. This opens the `mcp.json` file.
    4. In `mcp.json`, configure your server:

    ```json theme={null}
    {
      "mcpServers": {
        "VoucherifyDocsMCP": {
          "url": "https://docs.voucherify.io/mcp"
        }
      }
    }
    ```

    See the [Cursor documentation](https://cursor.com/docs#installing-mcp-servers) for more details.
  </Tab>

  <Tab title="Visual Studio Code">
    In VS Code:

    1. Create a `.vscode/mcp.json` file.
    2. In `mcp.json`, configure your server:

    ```json theme={null}
    {
      "servers": {
        "VoucherifyDocsMCP": {
          "type": "http",
          "url": "https://docs.voucherify.io/mcp"
        }
      }
    }
    ```

    See the [VS Code documentation](https://code.visualstudio.com/docs/copilot/chat/mcp-servers) for more details.
  </Tab>
</Tabs>

## Using MCP servers

You can connect multiple MCP servers to your AI tools. Connected MCP servers don't consume context until the AI calls a search tool. The AI decides when to search based on your query, so it doesn't search every connected server for every question.

When the AI searches, each query returns multiple results that add to the conversation's context. If the AI searches several servers for a single question, this can use up significant context.

Best practices for using multiple MCP servers:

* Connect only the MCP servers that will be useful in your current work.
* Be specific in your questions, so the AI searches the most relevant server.
* Disconnect servers you're not using to reduce context usage.