Spark
Sign In
MCP Connector

Generate images through MCP protocol integration

MCP server for AI image generation across OpenRouter, Together AI, Replicate, and fal.ai.

Connect
npm
Maintainer?
Updated 3 months ago
Version 1.0.0
Models
universal
Add to Favorites

Why it matters

Enable AI assistants and applications to create visual content on demand by providing a standardized Model Context Protocol interface for image generation capabilities.

Outcomes

What it gets done

01

Connect AI models to image generation services via MCP

02

Process natural language image descriptions into visual outputs

03

Return generated images in standard formats for downstream use

04

Handle image generation requests through protocol-compliant messaging

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/mcp-image-generator | bash

Overview

MCP Image Generator

An MCP server that generates AI images from text prompts across four providers - OpenRouter, Together AI, Replicate, and fal.ai. It exposes a generate_image tool with prompt, model, provider, aspect ratio, resolution, and seed parameters, plus a list_providers tool. Use when you want an AI agent to generate images on request without switching to a separate image-generation tool or UI.

What it does

This MCP server generates AI images from text prompts, giving Claude Code, Cursor, Claude Desktop, OpenCode, Charm (Crush/Mods), or any MCP-compatible agent access to four image-generation providers - OpenRouter (default), Together AI, Replicate, and fal.ai - through a single consistent tool interface.

When to use - and when NOT to

Use it when you want an AI agent to generate images on request - specifying a prompt, model, provider, aspect ratio, resolution, or seed - without switching to a separate image-generation UI. Requires at least one provider API key (OpenRouter, Together AI, Replicate, or fal.ai); with multiple keys set, you can pick a provider per request. It only supports image-generation models across its four providers - not general-purpose chat or text models from the same providers.

Capabilities

Two tools: generate_image (a required text prompt, plus optional model ID, provider selection, aspect_ratio - 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, or 2:3 - image_size - 1K default, 2K, or 4K - negative_prompt for exclusions on providers that support it, a seed for reproducibility, and a custom save_to file path) and list_providers (lists all configured providers and their available image models, optionally filtered by provider name). Supported provider and model combinations: OpenRouter (Gemini Flash Image, FLUX 2, Sourceful Riverflow, GPT-5 Image), Together AI (FLUX.1 Schnell/Dev/Pro, Stable Diffusion XL), Replicate (FLUX Schnell, FLUX 1.1 Pro, SDXL, Ideogram), and fal.ai (FLUX Dev/Schnell/2 Pro, Recraft V3).

How to install

No install step - run directly via npx with a provider API key:

OPENROUTER_API_KEY="sk-or-v1-..." npx -y mcpimg

Register it in your client's MCP config with command: "npx", args: ["-y", "mcpimg"], and the relevant provider key in env - Claude Code (claude mcp add or .mcp.json), Cursor (~/.cursor/mcp.json), Claude Desktop (platform-specific config path), OpenCode (opencode.json), Charm Crush (crush.json), or Charm Mods (mods.yml). It uses standard stdio transport, so any MCP-compatible agent can launch it the same way. At least one of OPENROUTER_API_KEY, TOGETHER_API_KEY, REPLICATE_API_TOKEN, or FAL_KEY is required; IMAGE_OUTPUT_DIR optionally overrides the default save location of ~/generated-images/. With multiple keys set, a specific call like generate_image(prompt="a cat", provider="together", model="black-forest-labs/FLUX.1-schnell") routes that one request to a chosen provider and model without changing the server configuration. The project is MIT-licensed.

Who it's for

Developers and AI-agent users who want on-demand image generation available as a tool call across multiple providers and models, without hardcoding a single provider or building separate image-generation tooling for each client.

Source README

MCP Image Generator Logo

MCP Image Generator

MCP server for AI image generation. Works with Claude Code, Cursor, Claude Desktop, OpenCode, Charm (Crush/Mods), and any MCP-compatible AI agent.

Providers supported (image models only):

  • OpenRouter (default) - Gemini Flash Image, FLUX 2, Sourceful Riverflow, GPT-5 Image
  • Together AI - FLUX.1 Schnell/Dev/Pro, Stable Diffusion XL
  • Replicate - FLUX Schnell, FLUX 1.1 Pro, SDXL, Ideogram
  • fal.ai - FLUX Dev/Schnell/2 Pro, Recraft V3

Quick Start

No install needed - just use npx:

OPENROUTER_API_KEY="sk-or-v1-..." npx -y mcpimg

Tools

generate_image

Generate an image from a text prompt.

Parameter Type Description
prompt string (required) Text description of the image
model string Model ID (e.g. google/gemini-2.5-flash-image)
provider string openrouter (default), together, replicate, fal
aspect_ratio string 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3
image_size string 1K (default), 2K, 4K
negative_prompt string What to exclude (not all providers support this)
seed number Random seed for reproducibility
save_to string Custom file path to save the image

list_providers

List all configured providers and their available image models.

Parameter Type Description
provider string Filter by provider name

Setup for AI Agents / IDEs

Claude Code

claude mcp add --scope user --transport stdio image-gen \
  --env OPENROUTER_API_KEY=sk-or-v1-xxx \
  -- npx -y mcpimg

Or create .mcp.json in your project root:

{
  "mcpServers": {
    "image-gen": {
      "command": "npx",
      "args": ["-y", "mcpimg"],
      "env": {
        "OPENROUTER_API_KEY": "sk-or-v1-..."
      }
    }
  }
}

Cursor

Edit ~/.cursor/mcp.json:

{
  "mcpServers": {
    "image-gen": {
      "command": "npx",
      "args": ["-y", "mcpimg"],
      "env": {
        "OPENROUTER_API_KEY": "sk-or-v1-..."
      }
    }
  }
}

Claude Desktop

Edit the config file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "image-gen": {
      "command": "npx",
      "args": ["-y", "mcpimg"],
      "env": {
        "OPENROUTER_API_KEY": "sk-or-v1-..."
      }
    }
  }
}

OpenCode (by SST)

Edit ~/.config/opencode/opencode.json or opencode.json in project root:

{
  "mcp": {
    "image-gen": {
      "type": "local",
      "command": ["npx", "-y", "mcpimg"],
      "environment": {
        "OPENROUTER_API_KEY": "sk-or-v1-..."
      },
      "enabled": true,
      "timeout": 120000
    }
  }
}

Charm Crush

Add to crush.json in your project root:

{
  "mcp": {
    "image-gen": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "mcpimg"],
      "env": {
        "OPENROUTER_API_KEY": "sk-or-v1-..."
      }
    }
  }
}

Charm Mods

Edit mods.yml (mods --settings):

mcp-servers:
  image-gen:
    command: [npx]
    args:
      - -y
      - mcpimg
    env:
      - OPENROUTER_API_KEY=sk-or-v1-...

Any MCP-compatible agent

This server uses stdio transport (JSON-RPC over stdin/stdout). Any agent that supports MCP stdio can use it:

npx -y mcpimg

# Required environment variables (at least one)
OPENROUTER_API_KEY=...    # OpenRouter (default)
TOGETHER_API_KEY=...      # Together AI
REPLICATE_API_TOKEN=...   # Replicate
FAL_KEY=...               # fal.ai

Using Multiple Providers

Set multiple API keys to use different providers:

export OPENROUTER_API_KEY="sk-or-v1-..."
export TOGETHER_API_KEY="..."
export FAL_KEY="..."

Then specify the provider when generating:

generate_image(prompt="a cat", provider="together", model="black-forest-labs/FLUX.1-schnell")

Environment Variables

Variable Provider Required
OPENROUTER_API_KEY OpenRouter At least one
TOGETHER_API_KEY Together AI provider key
REPLICATE_API_TOKEN Replicate is required
FAL_KEY fal.ai
IMAGE_OUTPUT_DIR - Optional. Default: ~/generated-images/

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.