Grok2 Image MCP Server

@fl0w1nd

Basic information

About Grok2 Image MCP Server

grok image mcp server

Grok2 Image MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "grok_image": {
      "command": "npx",
      "args": [
        "grok-image-mcp"
      ],
      "env": {
        "XAIAPI_KEY": "your-xai-api-key"
      }
    }
  }
}

Grok2 Image MCP Server tools

Generate images from text prompts using the Grok image model. Returns image URLs in markdown format. Note: URLs are temporary, download or process promptly.

Edit existing images using a text prompt. Provide 1-3 source images (as URLs, base64 data URIs, or local file paths) along with editing instructions. Returns edited image URLs in markdown format.

Overview

What is Grok2 Image MCP Server?

An MCP (Model Context Protocol) server for generating and editing images using the Grok image model from xAI. It serves developers integrating image capabilities into AI workflows via MCP-compatible clients.

How to use Grok2 Image MCP Server?

Install via npx in your MCP client configuration, setting the required environment variable XAIAPI_KEY. The server exposes two tools: generate_image and edit_image, invoked by the client with parameters such as prompt, image URLs, aspect ratio, resolution, and batch count.

Key features of Grok2 Image MCP Server

Image generation from text prompts with configurable aspect ratio and resolution
Image editing using natural language instructions with 1–3 source images
Local file path support for editing; server auto-reads and encodes them
Optional image proxy domain to replace imgen.x.ai in returned URLs
Optional HTTP/HTTPS network proxy for API requests

Use cases of Grok2 Image MCP Server

Generate images from descriptive prompts with custom dimensions and batch count
Edit existing images by providing URLs, base64 data, or local file paths
Overcome network restrictions on imgen.x.ai using an image proxy domain
Configure network proxying for API calls through corporate or regional gateways

Frequently asked questions

What tools does Grok2 Image MCP Server provide?

Two tools: `generate_image` for creating images from text, and `edit_image` for modifying existing images using natural language.

What environment variables are required?

`XAIAPI_KEY` is required. Optional variables include `XAIAPI_BASE_URL`, `IMAGE_PROXY_DOMAIN`, and `HTTP_PROXY`.

Can I use local image files for editing?

Yes, the `edit_image` tool accepts local file paths in the `image_urls` parameter; the server reads and encodes them automatically.

How do I handle network or image URL restrictions?

Set `XAIAPI_BASE_URL` to an API proxy, `IMAGE_PROXY_DOMAIN` to a custom proxy for image URLs, or `HTTP_PROXY` for a general network proxy.

What are the parameter limits for image generation?

`n` (number of images) supports 1–10 (default 1). Aspect ratio options include `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3`, `2:1`, `1:2`, and `auto`. Resolution can be `1k` or `2k` (default 1k).

Comments

More Media & Design MCP servers

Blaze

Plan, create and schedule social media content from your AI assistant. Blaze makes on-brand posts, carousels and short videos, writes blog posts and newsletters, and schedules them to Instagram, TikTok, YouTube, LinkedIn

SnapDub

Turn long videos into captioned vertical clips for TikTok, Reels and Shorts from Claude, ChatGPT, Cursor or any MCP client. Paste a YouTube, Twitch, Kick, Rumble or Zoom link and get clips with titles, virality scores, d

Organize with AI (OwAI)

Alexander Visheratin

Search and manage photo and video libraries through AI assistants. Find images and video moments, review duplicates, and organize collections, groups, favorites and people across local folders, Apple Photos and OneDrive.

BulkTranscripts: YouTube Transcripts

Transcripts for one YouTube video or a whole channel or playlist, plus YouTube search, channel and playlist listings, and free new-upload tracking.

Notch

Create finished video ads from chat. Give Notch a brief or product URL — it loads your brand context, writes the script, and produces the finished ad: avatar, scenes, voiceover, captions. Built for performance marketers,