Log inSubmit server
MCP Image logo

MCP Image

Generate and edit images through Gemini, OpenAI, or BytePlus Seedream with prompt enhancement and configurable quality presets.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install MCP Image

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "mcp-image": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-image"
      ],
      "env": {
        "GEMINI_API_KEY": "YOUR_VALUE_HERE",
        "OPENAI_API_KEY": "YOUR_VALUE_HERE",
        "ARK_API_KEY": "YOUR_VALUE_HERE",
        "IMAGE_PROVIDER": "YOUR_VALUE_HERE",
        "IMAGE_OUTPUT_DIR": "YOUR_VALUE_HERE",
        "IMAGE_QUALITY": "YOUR_VALUE_HERE",
        "SKIP_PROMPT_ENHANCEMENT": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

mcp-image MCP server generates and edits images through Gemini, OpenAI, or BytePlus Seedream, then saves the result locally and returns it as an MCP resource. Its `generate_image` tool can expand short prompts with visual details such as composition, lighting, and camera angle, or send prompts unchanged. Use it from Codex, Cursor, Claude Code, or another MCP-compatible client when an agent needs image creation, editing, or controlled output settings.

Use cases

  • Generate product photography for a catalog or campaign
  • Edit an existing image using an absolute file path
  • Create illustrations with a chosen aspect ratio and quality preset
  • Maintain a character’s appearance across generated images
  • Ground Gemini image requests in current information

Key features

  • Text-to-image generation and image editing
  • Gemini, OpenAI, and BytePlus Seedream support
  • Automatic prompt enhancement with an opt-out
  • Quality presets for fast, balanced, and quality output
  • Aspect ratio, size, format, and provider controls
  • Local file output returned as an MCP resource

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

8/8 checks healthy over the last 39d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 10d ago via OSV.dev · mcp-image (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars181Stargazers on the source repository.
npm downloads14kPackage downloads in the last 30 days.
Last commit1d agoMost recent push to the default branch.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How MCP Image works

What mcp-image does

mcp-image gives MCP-compatible assistants a single tool for creating new images and modifying existing ones. Requests can describe a new scene, provide an absolute path to one or more source images, or combine both approaches for an edit. The generated file is written to a local output directory and returned to the assistant as an MCP resource.

The server supports three image providers: Gemini, OpenAI, and BytePlus Seedream. Gemini is the default provider. Provider selection affects both prompt enhancement and image generation, while the way an assistant requests an image remains the same. Gemini supports 1K, 2K, and 4K output; OpenAI supports those sizes with PNG or JPEG output; Seedream supports 1K and 2K with PNG or JPEG output.

How it works

Before generation, mcp-image normally expands a short request into a more detailed visual prompt. The enhancement can add direction for composition, lighting, camera angle, and related image details while retaining the user's intent. More detailed input generally leaves less for the enhancement step to infer. Set SKIP_PROMPT_ENHANCEMENT=true when the original prompt should be sent to the image provider without rewriting.

The generate_image tool accepts a required prompt and optional controls for provider, quality, input files, filename, aspect ratio, image size, blending, character consistency, world knowledge, Google Search grounding, and intended purpose. A request-level provider or quality value overrides the corresponding server default. Google Search grounding is available with Gemini only.

Setup and configuration

Node.js 22 or later, an MCP-compatible client, and an API key for one image provider are required. Run the published package with npx -y mcp-image, or build a local checkout with pnpm install followed by pnpm run build, then launch dist/index.js with Node.

Set IMAGE_PROVIDER to gemini, openai, or seedream when choosing a default provider. Supply its corresponding key through GEMINI_API_KEY, OPENAI_API_KEY, or ARK_API_KEY. IMAGE_OUTPUT_DIR controls where files are saved and defaults to ./output; an absolute path is recommended in MCP client configuration because the client's working directory determines how relative paths resolve.

IMAGE_QUALITY accepts fast, balanced, or quality, with fast as the default. The setting applies to generation and editing and can be overridden for an individual request. Higher settings may take longer and cost more. Restart the MCP client after changing its configuration. API keys should not be committed to version control.

Tools and capabilities

The server exposes the generate_image tool. Its main capabilities include:

  • Generate images from text prompts.
  • Edit images referenced by absolute file paths.
  • Select Gemini, OpenAI, or BytePlus Seedream per request.
  • Choose fast, balanced, or quality processing presets.
  • Set aspect ratios from square, portrait, landscape, and panoramic options.
  • Request supported 1K, 2K, or 4K image sizes.
  • Select PNG or JPEG through the output filename where supported.
  • Blend visual elements and preserve character appearance across images.
  • Add world knowledge context or Gemini Google Search grounding.
  • Save results to a configured directory and return them to the assistant.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about MCP Image

mcp-image is an MCP server that connects AI assistants to Gemini, OpenAI, and BytePlus Seedream for image generation and editing. Its main `generate_image` tool accepts prompts, optional input image paths, provider and quality settings, aspect ratios, image sizes, and other controls, then saves and returns the resulting file.

Install it by configuring your MCP client to run `npx -y mcp-image`. You need Node.js 22 or later, an MCP-compatible client, and an API key for Gemini, OpenAI, or BytePlus Seedream. A local checkout can be built with `pnpm install` and `pnpm run build`.

Set the environment variable matching the selected provider: `GEMINI_API_KEY` for Gemini, `OPENAI_API_KEY` for OpenAI, or `ARK_API_KEY` for BytePlus Seedream. Set `IMAGE_PROVIDER` when the default Gemini provider should change, and restart the MCP client after updating its environment.

Yes, mcp-image works with Cursor through its MCP configuration. Add a server entry that runs `npx -y mcp-image`, provide the selected provider key and an `IMAGE_OUTPUT_DIR`, then restart Cursor. The configuration can be placed in the user-level or project-level Cursor MCP file.

Provide the assistant with an absolute path to the source image and describe the requested change. The `generate_image` tool accepts source paths through `inputImagePaths`, and the edited result is saved in the configured output directory and returned to the assistant.

Related MCP servers

All in Multimedia Process All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewMCP Image AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/mcp-image?style=directory)](https://allmcps.com/mcp/mcp-image)
HTML Embed
<a href="https://allmcps.com/mcp/mcp-image"><img src="https://allmcps.com/api/badge/mcp-image?style=directory" alt="MCP Image on AllMCPs" /></a>