{
  "markdown": "# GrokMCP\n\n<!-- mcp-name: io.github.AceDataCloud/mcp-grok -->\n\n[![PyPI version](https://img.shields.io/pypi/v/mcp-grok.svg)](https://pypi.org/project/mcp-grok/)\n[![Python](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n\nA [Model Context Protocol (MCP)](https://modelcontextprotocol.io) server for **Grok** (xAI) — chat/reasoning/vision **and** Grok Imagine video generation, powered by the [AceDataCloud](https://platform.acedata.cloud) API.\n\nChat 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.).\n\n## Features\n\n- **Chat / Reasoning / Vision** — Talk to Grok 4.5 / Grok 4 / Grok 3 models, with image input and tool calling\n- **Text to Video** — Generate a video clip from a text description\n- **Image to Video** — Animate a reference image into a video\n- **Async task tracking** — Submit a job, poll for the result, single or batch\n- **stdio & HTTP transports** — Local stdio for desktop clients, HTTP for remote hosting\n\n## Tools\n\n| Tool | Description |\n| --- | --- |\n| `grok_chat_completions` | Chat completion (reasoning / vision / tool calling) with Grok chat models. |\n| `grok_text_to_video` | Generate a video from a text prompt (any model except `grok-imagine-video-1.5:official`). |\n| `grok_image_to_video` | Generate a video from an input image (+ optional motion prompt). |\n| `grok_get_task` | Query the status/result of a single generation task. |\n| `grok_get_tasks_batch` | Query the status/result of multiple tasks at once. |\n| `grok_list_models` | List available models and their capabilities. |\n| `grok_list_actions` | List all tools and example workflows. |\n| `grok_get_prompt_guide` | Tips for writing effective video prompts. |\n\n## Models\n\n### Chat (`grok_chat_completions`)\n\n| Model | Notes |\n| --- | --- |\n| `grok-4.5` | Default — latest flagship reasoning model |\n| `grok-4` | Previous flagship reasoning model |\n| `grok-3` | Earlier-generation model |\n\n### Video\n\n| Model | Text→Video | Image→Video | Notes |\n| --- | --- | --- | --- |\n| `grok-imagine-video-1.5-fast:reverse` | ✅ | ✅ | Default. Fastest & cheapest. 6-30s, duration-banded billing. |\n| `grok-imagine-video:reverse` | ✅ | ✅ | Standard. 1-15s, billed per output second. |\n| `grok-imagine-video:official` | ✅ | ✅ | Official endpoint, higher fidelity. 1-15s, per second. |\n| `grok-imagine-video-1.5:official` | ❌ | ✅ | Official image-to-video only (requires `image_url`). Up to 1080p, per second. |\n\n## Parameters\n\n| Parameter | Applies to | Values |\n| --- | --- | --- |\n| `prompt` | both | Text description (required for text-to-video) |\n| `image_url` | image-to-video | Input image URL (required for `-1.5-preview`) |\n| `reference_image_urls` | image-to-video | Optional list of style/content reference images |\n| `aspect_ratio` | both | `1:1`, `16:9` (default), `9:16`, `4:3`, `3:4`, `3:2`, `2:3` |\n| `resolution` | both | `480p` (default), `720p`, `1080p` |\n| `duration` | both | `grok-imagine-video-1.5-fast:reverse`: `6`–`30`s; other models: `1`–`15`s (default `6`) |\n| `callback_url` | both | Optional async webhook |\n\n## Installation\n\n### Via uvx (recommended)\n\n```bash\nuvx mcp-grok\n```\n\n### Via pip\n\n```bash\npip install mcp-grok\nmcp-grok\n```\n\n## Configuration\n\nSet your AceDataCloud API token (get one at <https://platform.acedata.cloud>):\n\n```bash\nexport ACEDATACLOUD_API_TOKEN=your_api_token_here\n```\n\n### Claude Desktop / Claude Code\n\nAdd to your MCP config (`claude_desktop_config.json` or `.mcp.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"grok\": {\n      \"command\": \"uvx\",\n      \"args\": [\"mcp-grok\"],\n      \"env\": {\n        \"ACEDATACLOUD_API_TOKEN\": \"your_api_token_here\"\n      }\n    }\n  }\n}\n```\n\n### Remote (HTTP)\n\nA hosted Streamable HTTP endpoint is available at:\n\n```\nhttps://grok.mcp.acedata.cloud/mcp\n```\n\n## Environment Variables\n\n| Variable | Description | Default |\n| --- | --- | --- |\n| `ACEDATACLOUD_API_TOKEN` | API token (required) | — |\n| `ACEDATACLOUD_API_BASE_URL` | API base URL | `https://api.acedata.cloud` |\n| `GROK_DEFAULT_MODEL` | Default model | `grok-imagine-video-1.5-fast:reverse` |\n| `GROK_REQUEST_TIMEOUT` | Request timeout (seconds) | `180` |\n| `MCP_SERVER_NAME` | MCP server name | `grok` |\n| `MCP_TRANSPORT` | Transport mode (`stdio`/`http`) | `stdio` |\n| `LOG_LEVEL` | Logging level | `INFO` |\n\n## Usage Notes\n\n- 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.\n- Generation typically takes ~30 seconds to a few minutes.\n- Keep `resolution` at `480p` and `duration` short for faster, cheaper iterations.\n\n## Development\n\n```bash\npip install -e \".[dev,test]\"\npytest --cov=core --cov=tools\nruff check .\n```\n\n## Documentation\n\n<!-- canonical-documentation -->\n[Documentation](https://platform.acedata.cloud/documents/grok)\n\n## License\n\nMIT — see [LICENSE](LICENSE).\n",
  "bytes": 5088,
  "sha": "419bb4f11eb008e945429fa8fedfac900df80c3581f371ee3f5bacb21718f48c",
  "repo_slug": "acedatacloud/grokmcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_acedatacloud_mcp_grok_c9b22a03/readme"
}