xAI MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| XAI_API_KEY | Yes | Your xAI API key from x.ai/api (starts with 'xai-'). |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_imageB | Generate images from text descriptions using xAI's Grok Imagine model. Returns image URLs or base64 data. |
| chatB | Chat with xAI's Grok models. Send messages and receive AI-generated responses. |
| analyze_imageC | Analyze images using xAI's vision-capable Grok models. Describe, extract text, or answer questions about images. |
| live_searchB | Perform real-time web search using xAI's Grok. Search web, news, or X/Twitter for current information. |
| generate_videoB | Generate videos from text descriptions using xAI. Can also animate images or edit existing videos. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose with no overlap: analyze_image handles image analysis, chat is for text conversations, generate_image creates images, generate_video creates videos, and live_search performs web searches. The descriptions reinforce these distinct domains, making tool selection unambiguous.
All tool names follow a consistent verb_noun pattern (e.g., analyze_image, generate_video, live_search) using snake_case throughout. This predictable naming scheme makes the tool set easy to navigate and understand at a glance.
With 5 tools, this server is well-scoped for its purpose of interacting with xAI's Grok models across different modalities (text, image, video, search). Each tool earns its place by covering a distinct aspect of the AI service without being overly sparse or bloated.
The tool set covers core AI functionalities: chat, image analysis/generation, video generation, and web search. A minor gap is the lack of audio-related tools (e.g., speech-to-text or text-to-speech), but agents can work around this given the comprehensive coverage of visual and text domains.