mcp-server-grok-image
MCP server for generating and editing images using xAI's Grok API. Provides tools for image generation, editing, and style listing with configurable models and output options.
README
mcp-server-grok-image
An MCP (Model Context Protocol) server for xAI's Grok image generation API. Built in Rust, exposes image generation and editing as MCP tools.
Communicates via stdio using JSON-RPC 2.0, like all MCP servers.
Tools
| Tool | Description |
|---|---|
generate_image |
Generate an image from a text prompt |
edit_image |
Edit an existing image using natural language instructions |
list_styles |
List available image styles for use with generate_image |
generate_image
Generate an image from a text description.
Parameters:
| Name | Type | Required | Description |
|---|---|---|---|
prompt |
string | yes | Text description of the desired image |
model |
string | no | Model to use (default: grok-imagine-image) |
n |
integer | no | Number of images to generate (1-10, default 1) |
aspect_ratio |
string | no | Aspect ratio: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 2:1, 1:2, auto, etc. |
resolution |
string | no | Output resolution: 1k (~1024px, default) or 2k (~2048px) |
response_format |
string | no | Output format: url (default, temporary) or b64_json |
style |
string | no | Style name to apply (use list_styles to see options) |
When a style is set, the prompt is wrapped in the style's template. For example, with style: "watercolor" and prompt: "a cat on a roof", the API receives "a cat on a roof, as a watercolor painting". Avoid including style language in the prompt itself when using this parameter.
The response includes the resolved prompt so you can see exactly what was sent to the API.
edit_image
Edit an existing image using natural language instructions.
Parameters:
| Name | Type | Required | Description |
|---|---|---|---|
image_url |
string | yes | URL, base64 data URI, or local file path of the source image |
prompt |
string | yes | Natural language edit instructions |
model |
string | no | Model to use (default: grok-imagine-image) |
n |
integer | no | Number of variations to generate (1-10, default 1) |
resolution |
string | no | Output resolution: 1k (~1024px, default) or 2k (~2048px) |
response_format |
string | no | Output format: url (default, temporary) or b64_json |
Note: The style parameter is intentionally not available on edit_image -- edit prompts are instructions (e.g. "remove the background"), not descriptions, so wrapping them in style templates would produce nonsense.
list_styles
Returns all available image styles with their name, description, and prompt template. No parameters.
Built-in Styles
| Style | Description |
|---|---|
watercolor |
Watercolor painting style |
oil-painting |
Oil painting with visible brushstrokes |
pencil-sketch |
Detailed pencil sketch |
pixel-art |
Retro pixel art |
anime |
Anime style illustration |
pop-art |
Bold pop art style |
art-nouveau |
Art nouveau with flowing organic lines |
cinematic |
Cinematic photography with dramatic lighting |
portrait |
Professional portrait photography |
macro |
Extreme macro photography |
aerial |
Aerial drone photography |
studio |
Studio photography on clean background |
noir |
Dark film noir style |
vintage |
Faded vintage photograph |
Available Models
| Model | Resolution | Cost | Rate Limit |
|---|---|---|---|
grok-imagine-image (default) |
1k/2k | $0.02/image | 300 RPM |
Prerequisites
- Rust (edition 2024)
- An xAI API key from console.x.ai
Setup
Create the config file:
mkdir -p ~/.config/mcp-server-grok-image
Create ~/.config/mcp-server-grok-image/config.toml:
api_key = "xai-..."
Custom Styles
Add custom styles to your config file. Custom styles with the same name as a built-in will override it.
api_key = "xai-..."
[[styles]]
name = "my-style"
description = "My custom look"
template = "{prompt}, in my custom style"
[[styles]]
name = "watercolor"
description = "My watercolor variant"
template = "{prompt}, as a loose expressive watercolor with ink outlines"
Templates must contain the {prompt} placeholder. Any custom style missing it will be skipped with a warning at startup.
Build
cargo build --release
This produces target/release/mcp-server-grok-image.
For development:
cargo build # debug build
cargo run # run in dev mode
RUST_LOG=debug cargo run # run with debug logging
MCP Configuration
Add to your Claude Desktop config (~/.config/Claude/claude_desktop_config.json):
{
"mcpServers": {
"grok-image": {
"command": "/path/to/mcp-server-grok-image"
}
}
}
Project Structure
src/
main.rs - everything: config, styles, API types, MCP server, tool definitions
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。