Complete documentation for integrating Image MCP into your AI workflows.
Image MCP is a hosted Model Context Protocol (MCP) server that provides AI agents with image generation capabilities. It uses the MCP standard for seamless integration with LLM applications.
Image MCP requires an API key for authentication. Get your API key from the Dashboard.
🔑 Credit System: Each image generation costs 10 credits. New accounts receive free credits to get started.
| Header | Authorization |
| Format | Bearer YOUR_API_KEY |
| Get API Key | Dashboard → API Keys |
💡 Replace YOUR_API_KEY with your actual API key from the Dashboard.
{
"mcpServers": {
"image-mcp": {
"url": "https://imagemcp.io/api/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}claude mcp add --transport http --header "Authorization: Bearer YOUR_API_KEY" image-mcp https://imagemcp.io/api/mcp
| URL | https://imagemcp.io/api/mcp |
| Protocol | Model Context Protocol (MCP) |
| Transport | Streamable HTTP |
| Method | POST |
| Authentication | Authorization: Bearer YOUR_API_KEY |
Generate an image from a text prompt
promptText description of the image to generate
modelModel ID to use. Default: google/gemini-3-pro-image-preview
{
"url": "https://cdn.../generated/1234-abc.png",
"model": "google/gemini-3-pro-image-preview",
"prompt": "A serene Japanese garden...",
"filename": "1234-abc.png"
}google/gemini-3-pro-image-previewdefaultopenai/gpt-5-imageblack-forest-labs/flux.2-flexblack-forest-labs/flux.2-progoogle/gemini-2.5-flash-imageBasic image generation prompt
descriptionUser's description of the desired image
Detailed generation with style parameters
subjectMain subject of the image
styleArt style (e.g., photorealistic, cartoon, oil painting)
moodMood or atmosphere (e.g., dramatic, peaceful, vibrant)
lightingLighting conditions (e.g., sunset, studio, neon)
mcp://image-mcp/modelsReturns a list of all available image generation models.
{
"models": [
{ "id": "google/gemini-3-pro-image-preview", "name": "Gemini 3 Pro Image Preview" },
{ "id": "openai/gpt-5-image", "name": "GPT-5 Image" },
{ "id": "black-forest-labs/flux.2-flex", "name": "FLUX.2 Flex" },
{ "id": "black-forest-labs/flux.2-pro", "name": "FLUX.2 Pro" },
{ "id": "google/gemini-2.5-flash-image", "name": "Gemini 2.5 Flash Image" }
]
}{
"name": "generate_image",
"arguments": {
"prompt": "A majestic snowy mountain peak at sunrise, photorealistic, golden hour lighting, dramatic clouds"
}
}{
"name": "generate_image",
"arguments": {
"prompt": "Cyberpunk cityscape with neon lights reflecting on wet streets, futuristic",
"model": "black-forest-labs/flux.2-pro"
}
}Portrait: "Professional headshot of a confident business executive, studio lighting, neutral gray background, sharp focus"
Landscape: "Alpine lake at golden hour with snow-capped mountains, oil painting style, peaceful atmosphere"
Product: "Minimalist wireless earbuds floating on gradient background, soft shadows, product photography, clean aesthetic"
Fantasy: "Ancient dragon with crystalline scales perched on a mountain, bioluminescent details, epic fantasy art"
| Error | Cause | Solution |
|---|---|---|
| No image URL found | Model failed to generate | Try a different model or simplify prompt |
| API error: 429 | Rate limited | Wait and retry |
| API error: 500 | Model service issue | Try a different model |