GrokMCP

A Model Context Protocol (MCP) server for Grok (xAI) — chat/reasoning/vision and Grok Imagine video generation, powered by the AceDataCloud API.

Chat with Grok models, or generate short AI videos from a text prompt or a still image — directly from any MCP-compatible client (Claude Desktop, Claude Code, Cursor, etc.).

Features

• Chat / Reasoning / Vision — Talk to Grok 4 / Grok 3 family models, including vision (grok-2-vision) and tool calling
• Text to Video — Generate a video clip from a text description
• Image to Video — Animate a reference image into a video
• Async task tracking — Submit a job, poll for the result, single or batch
• stdio & HTTP transports — Local stdio for desktop clients, HTTP for remote hosting

Tools

Models

Chat (grok_chat_completions)

Video

Parameters

Installation

Via uvx (recommended)

uvx mcp-grok

Via pip

pip install mcp-grok
mcp-grok

Configuration

Set your AceDataCloud API token (get one at https://platform.acedata.cloud):

export ACEDATACLOUD_API_TOKEN=your_api_token_here

Claude Desktop / Claude Code

Add to your MCP config (claude_desktop_config.json or .mcp.json):

{
  "mcpServers": {
    "grok": {
      "command": "uvx",
      "args": ["mcp-grok"],
      "env": {
        "ACEDATACLOUD_API_TOKEN": "your_api_token_here"
      }
    }
  }
}

Remote (HTTP)

A hosted Streamable HTTP endpoint is available at:

https://grok.mcp.acedata.cloud/mcp

Environment Variables

Usage Notes

• Generation is asynchronous: the generation tools return a task_id quickly. Poll with grok_get_task(task_id) until the state is succeeded and the video_url is available.
• Generation typically takes ~30 seconds to a few minutes.
• Keep resolution at 480p and duration short for faster, cheaper iterations.

Development

pip install -e ".[dev,test]"
pytest --cov=core --cov=tools
ruff check .

License

MIT — see LICENSE.