GrokMCP
The GrokMCP server provides an MCP interface to xAI's Grok models for chat, reasoning, vision, and AI video generation (powered by AceDataCloud).
Chat & Reasoning
grok_chat_completions: Converse with Grok models (grok-4.5,grok-4,grok-3) with support for vision/image input, tool/function calling, and configurable parameters (temperature, top_p, max_tokens, etc.)
Video Generation
grok_text_to_video: Generate a video from a text description. Supports configurable duration (1–30s), resolution (480p/720p/1080p), aspect ratio (1:1, 16:9, 9:16, etc.), and optional webhook callback.grok_image_to_video: Animate a reference image into a video, with an optional motion prompt and additional style/reference images.
Task Management
grok_get_task: Poll the status and retrieve results (video URLs) for a single generation task.grok_get_tasks_batch: Check the status of multiple tasks in one request (up to 50).
Discovery & Reference
grok_list_models: View all available chat and video models with their capabilities.grok_list_actions: Browse all tools with example workflows.grok_get_prompt_guide: Get tips and best practices for writing effective video generation prompts.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@GrokMCPGenerate a 15-second video of a golden retriever running on a beach"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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 4.5 / Grok 4 / Grok 3 models, with image input 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
Related MCP server: xbridge-mcp
Tools
Tool | Description |
| Chat completion (reasoning / vision / tool calling) with Grok chat models. |
| Generate a video from a text prompt (any model except |
| Generate a video from an input image (+ optional motion prompt). |
| Query the status/result of a single generation task. |
| Query the status/result of multiple tasks at once. |
| List available models and their capabilities. |
| List all tools and example workflows. |
| Tips for writing effective video prompts. |
Models
Chat (grok_chat_completions)
Model | Notes |
| Default — latest flagship reasoning model |
| Previous flagship reasoning model |
| Earlier-generation model |
Video
Model | Text→Video | Image→Video | Notes |
| ✅ | ✅ | Default. Fastest & cheapest. 6-30s, duration-banded billing. |
| ✅ | ✅ | Standard. 1-15s, billed per output second. |
| ✅ | ✅ | Official endpoint, higher fidelity. 1-15s, per second. |
| ❌ | ✅ | Official image-to-video only (requires |
Parameters
Parameter | Applies to | Values |
| both | Text description (required for text-to-video) |
| image-to-video | Input image URL (required for |
| image-to-video | Optional list of style/content reference images |
| both |
|
| both |
|
| both |
|
| both | Optional async webhook |
Installation
Via uvx (recommended)
uvx mcp-grokVia pip
pip install mcp-grok
mcp-grokConfiguration
Set your AceDataCloud API token (get one at https://platform.acedata.cloud):
export ACEDATACLOUD_API_TOKEN=your_api_token_hereClaude 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/mcpEnvironment Variables
Variable | Description | Default |
| API token (required) | — |
| API base URL |
|
| Default model |
|
| Request timeout (seconds) |
|
| MCP server name |
|
| Transport mode ( |
|
| Logging level |
|
Usage Notes
Generation is asynchronous: the generation tools return a
task_idquickly. Poll withgrok_get_task(task_id)until the state issucceededand thevideo_urlis available.Generation typically takes ~30 seconds to a few minutes.
Keep
resolutionat480panddurationshort for faster, cheaper iterations.
Development
pip install -e ".[dev,test]"
pytest --cov=core --cov=tools
ruff check .License
MIT — see LICENSE.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityCmaintenanceUse XAI's latest api functionalities with Grok MCP. It supports image understanding and generation, live search, latest models and more.Last updated2248MIT
- Alicense-qualityAmaintenanceMCP server for xAI Grok API with 19 tools for chat, web and X search, session management, tool chaining, image and video generation, and documentation.Last updated2MIT
- AlicenseAqualityBmaintenanceMCP server for generating, editing, and batch processing videos using xAI's Grok Imagine Video API, with support for text-to-video, image-to-video, and video editing via natural language prompts.Last updated4391MIT
- AlicenseAqualityCmaintenanceMCP server for integrating xAI's Grok model into OpenAI Codex Desktop/GUI, enabling direct Grok calls via chat completions or responses with OAuth or API key authentication.Last updated9MIT
Related MCP Connectors
MCP server for AI dialogue using various LLM models via AceDataCloud
MCP server for GLM chat completions using Zhipu AI models via AceDataCloud
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/AceDataCloud/GrokMCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server