grok-imagine-mcp
An MCP server that automates a headless Chromium browser to generate images using Grok Imagine via text prompts. It supports configurable aspect ratios and saves images directly to disk using cookie-based authentication.
README
grok-imagine-mcp
An MCP (Model Context Protocol) server that generates images using Grok Imagine. It automates a headless Chromium browser to submit prompts, wait for generation, and save the resulting images to disk.
Features
- Image generation via text prompts with configurable aspect ratios
- Cookie-based authentication -- paste a cURL command from your browser to log in
- Concurrent generation -- up to 4 parallel tabs with automatic queuing for additional requests
- Auto-closing browser -- closes Chromium after 1 minute of inactivity, reopens on next request
- Error handling -- detects rate limits, expired sessions, and sign-in redirects with clear messages
- Stealth mode -- uses
playwright-extrawith stealth plugin to avoid bot detection
Prerequisites
- Bun v1.3+
- A Grok account (free tier works)
Installation
bun install
MCP Configuration
Add the server to your MCP client config (e.g. .cursor/mcp.json):
{
"mcpServers": {
"grok-imagine-mcp": {
"command": "bun",
"args": ["run", "/path/to/grok-imagine-mcp/src/index.ts"]
}
}
}
Set "env": { "DEV": "true" } to run the browser in visible (non-headless) mode for debugging.
Tools
auth
Authenticate with Grok by providing cookies from your browser session.
- Open https://grok.com in your browser (make sure you're logged in)
- Open Developer Tools (F12 or Cmd+Option+I)
- Go to the Network tab
- Refresh the page
- Click on any request to grok.com
- Right-click -> "Copy as cURL"
- Pass the entire curl command to the
authtool
The tool extracts and saves the essential cookies (sso, sso-rw, cf_clearance, x-userid). Cookies persist in data/storage-state.json.
generate_images
Generate images using Grok Imagine.
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt |
string | yes | Text prompt describing the image(s) to generate |
quantity |
number | no | Number of images to save (1-6, default: 1). Each batch produces ~3 images. |
saveFolderFullPath |
string | yes | Absolute path to the folder where images will be saved |
aspectRatio |
string | no | 2:3, 3:2, 1:1, 9:16, or 16:9 (default: 1:1) |
Images are saved as grok-{timestamp}-{index}.jpg (or .png).
Development
# Run in dev mode (visible browser, file watching)
bun run dev
# Type check
bun run typecheck
# Lint & format
bun run fix
Project Structure
src/
index.ts MCP server entry point and tool registration
browser.ts Browser lifecycle, tab pool, and idle timeout
generate.ts Image generation logic (prompt submission, polling, saving)
chromium.ts Playwright + stealth plugin setup
cookies.ts Cookie parsing, saving, and loading
console.ts Browser console log capture
constants.ts Configuration constants
data/
profile/ Chromium persistent user data
storage-state.json Saved cookies and storage state
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.