Grok Image MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HTTP_PROXY | No | HTTP/HTTPS proxy for API requests (e.g. http://127.0.0.1:7890) | |
| XAIAPI_KEY | Yes | xAI API key | |
| XAIAPI_BASE_URL | No | API base URL (default: https://api.x.ai/v1). Use a proxy if the API is inaccessible | |
| IMAGE_PROXY_DOMAIN | No | Proxy domain to replace imgen.x.ai in returned image URLs |
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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_imageA | Generate images with xAI. Model and quality affect cost. URLs are temporary unless persisted with storage_options. b64_json returns inline image content. |
| edit_imageA | Edit images with xAI using ordered URLs, data URIs, local paths, or Files API IDs. Supports up to 3 source images with 1.0 or 5 with 2.0. URLs are temporary unless persisted. |
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 2 tools
generate_image creates new images, while edit_image modifies existing images using source inputs. The two tools target distinct actions with clearly different parameters and use cases, leaving no ambiguity.
Both tools follow a consistent snake_case verb_noun pattern: generate_image and edit_image. This is predictable and easy to parse.
Only 2 tools are provided, which feels thin for an image generation/editing service. While they cover the core operations, additional tools like listing models or retrieving image details would make the set feel more complete.
The core create and edit operations are present, covering the main lifecycle for image generation. Minor gaps exist, such as no tool for listing available models or managing stored images, but agents can work around these using external means.