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

# Documentation MCP

> Connect the read-only Juicer Documentation MCP server to your AI agent to search the Juicer API docs in natural language.

The **Documentation MCP** server lets an AI agent search and read the Juicer API documentation over [Model Context Protocol](https://modelcontextprotocol.io). Point your agent at it and it can answer questions from these docs, find the right endpoint, and generate correct code — without you copy-pasting pages into the chat.

<Info>
  This server is **read-only** and scoped to the documentation. To let an agent
  actually operate on your account — create feeds, moderate posts, pull
  analytics — use the [MCP Server](/mcp-server) instead.
</Info>

With the Documentation MCP connected, an agent can:

* Search the Juicer API docs and guides for relevant content.
* Read any documentation page or the OpenAPI spec in full.
* Generate accurate, up-to-date code against the current API.
* Ground its answers in the published docs instead of stale prior knowledge.

## Server URL

```text theme={null}
https://developers.juicer.io/mcp
```

No authentication is required — it only exposes public documentation.

## Setup

<Tabs>
  <Tab title="Claude Code">
    ```bash theme={null}
    claude mcp add --transport http juicer-docs https://developers.juicer.io/mcp
    ```
  </Tab>

  <Tab title="Claude Desktop">
    Open **Settings → Connectors → Add custom connector**, then enter:

    * **Name:** `Juicer Docs`
    * **URL:** `https://developers.juicer.io/mcp`

    Save, then click **Connect**.
  </Tab>

  <Tab title="Cursor">
    Open the command palette (`Cmd/Ctrl+Shift+P`) → **Open MCP settings**, and add to `mcp.json`:

    ```json theme={null}
    {
      "mcpServers": {
        "Juicer Docs": {
          "url": "https://developers.juicer.io/mcp"
        }
      }
    }
    ```
  </Tab>

  <Tab title="VS Code">
    Create `.vscode/mcp.json`:

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

<Warning>
  Restart your MCP client after adding the server so the new configuration takes
  effect.
</Warning>

## Try it

Once connected, ask your agent a question about the API and tell it to use the server:

> *"How do I create a feed and add an Instagram source with the Juicer API? Use the Juicer docs MCP server."*

The agent searches the docs, reads the relevant pages, and answers with references back to this site.

## Next steps

<CardGroup cols={2}>
  <Card title="MCP Server" icon="robot" href="/mcp-server">
    The action server that drives your account — feeds, posts, analytics, and more.
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference">
    The full REST reference the docs are built on.
  </Card>
</CardGroup>