mcp-server-grok-image

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.

Category
访问服务器

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

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

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选