How do I use PanPan Image Generator MCP Server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@PanPan Image Generator MCP Server Generate a fantasy landscape in 4K" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

PanPan Image Generator MCP Server

by panda920

Overview Schema Source Related Servers Discussions Admin

JavaScript

Remote

Features

Multi-model support — Gemini Pro Image Preview (1K/2K/4K) and Gemini Flash Image Preview
Image editing — Edit existing images with text instructions, supports multi-image reference
Batch generation — High-concurrency worker pool for parallel image generation
Shared context — Generate series of images with consistent style (great for slides, tutorials, card sets)
Resolution control — 1K / 2K / 4K presets or custom WxH, plus aspect ratio selection
Format conversion — Convert images to PDF or PowerPoint (PPTX)
Smart file handling — Auto-fallback output directory, customizable per-request save paths

Related MCP server: ModelsLab Text2Image MCP Server

Supported Models

Model ID	Alias	Quality
`gemini-3-pro-image-preview`	`nanobananapro`	High quality, 1K
`gemini-3-pro-image-preview-2k`	—	High quality, 2K
`gemini-3-pro-image-preview-4k`	—	High quality, 4K
`gemini-3.1-flash-image-preview`	`nanobanana2`, `gemini-flash`	Fast

All models are accessed through any OpenAI-compatible API endpoint that supports Gemini image generation.

Demo

Quick Start

Install

git clone https://github.com/panda920/panpan-image-generator-mcp.git
cd panpan-image-generator-mcp
npm install

Configure

Copy the example env file and fill in your API key:

cp .env.example .env

Edit .env:

GEMINI_API_KEY=your_api_key_here
GEMINI_API_BASE=https://openrouter.ai/api/v1

Use with Claude Code

Add to ~/.claude.json:

{
  "mcpServers": {
    "panpan-image-generator": {
      "type": "stdio",
      "command": "node",
      "args": ["/path/to/panpan-image-generator-mcp/panpan-image-generator-mcp-server.js"],
      "env": {
        "GEMINI_API_KEY": "your_api_key",
        "GEMINI_API_BASE": "https://openrouter.ai/api/v1"
      }
    }
  }
}

Tools

Image Generation

Tool	Description
`generate_image_batch`	Generate one or more images with high concurrency. Supports all 4 models, custom resolution and aspect ratio.
`generate_image_with_shared_context`	Batch generate images with shared style context for visual consistency. Ideal for slides, tutorials, card sets.

Image Editing

Tool	Description
`edit_image_nano`	Edit images (single or batch). Supports all 4 models, multi-image reference, custom resolution and aspect ratio.

Format Conversion

Tool	Description
`images_to_pdf`	Convert multiple images to a PDF document (one image per page, full bleed).
`images_to_pptx`	Convert multiple images to a PowerPoint presentation.

Examples

In Claude Code, just ask naturally:

Generate a cyberpunk cityscape at night in 4K

Edit this image: change the background to blue

Batch generate 5 cat illustrations in different styles

Create a 10-slide presentation with consistent branding, then export to PPTX

Environment Variables

Variable	Default	Description
`GEMINI_API_KEY`	—	API key (required)
`GEMINI_API_BASE`	`https://openrouter.ai/api/v1`	OpenAI-compatible API base URL
`GEMINI_MODEL`	`gemini-3-pro-image-preview`	Default Pro model
`GEMINI_FLASH_MODEL`	`gemini-3.1-flash-image-preview`	Default Flash model
`OUTPUT_DIR`	Current working directory	Default output directory

Requirements

Node.js >= 18.0.0

License

MIT License

Available Tools

5 tools

edit_image_nanoA

编辑图像（单张或批量）。支持全部四款生图模型，支持多图参考，支持指定分辨率和宽高比。

Inputs: model, requests, imagePath, editPrompt, +6 more.

generate_image_batchA

批量生图（单张或多张，高并发）。支持全部四款模型：nanobananapro / gemini-3-pro-image-preview（高质量）、gemini-3-pro-image-preview-2k（2K）、gemini-3-pro-image-preview-4k（4K）、nanobanana2 / gemini-flash（快速）。支持指定分辨率和宽高比。

📁 路径规则：① 每条请求可单独指定 saveToFilePath；② 可用 outputDir 统一指定目录（默认当前工作目录）；③ 写入失败时自动 fallback 到 MCP 服务器目录。

Inputs: requests (required), model, outputDir, image_size, +3 more.

generate_image_with_shared_contextB

🎯【推荐】共享上下文批量生图（保持风格一致性）。适合 PPT、教程、卡片组等系列图片。支持全部四款模型，支持指定分辨率。

Inputs: requests (required), styleContext (required), model, image_size, +3 more.

images_to_pdfA

将多张图片转换为 PDF（每页一张，完美填充无空白）。

Inputs: imagePaths (required), outputPath (required).

images_to_pptxC

将多张图片转换为 PowerPoint (PPTX) 文件。

Inputs: imagePaths (required), outputPath (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.4/5.0

Scored 2026-08-09 23:35 across 5 tools

Disambiguation4/5

The two generation tools (generate_image_with_shared_context and generate_image_batch) overlap somewhat, but their descriptions clarify different use cases: one for style-consistent series, the other for high-concurrency generic batch generation. The editing and conversion tools are clearly distinct from each other and from the generation tools.

Naming Consistency3/5

The naming is mixed: the first three tools use a verb_noun pattern (generate_image_*, edit_image_*), but the last two use a noun_to_noun pattern (images_to_pdf, images_to_pptx). The suffix 'nano' in edit_image_nano is also inconsistent with the other names. The pattern is readable but not uniform.

Tool Count5/5

With 5 tools, the server is well-scoped for its purpose of image generation, editing, and conversion to common presentation formats. Each tool serves a distinct purpose without unnecessary bloat.

Completeness4/5

The server covers the core lifecycle of creating, editing, and converting images. Minor gaps exist, such as lack of explicit format conversion beyond PDF/PPTX or model listing, but the primary workflows are supported.

Maintenance

ActivityInactive

ResponsivenessOutdated data

Resources

Related MCP Connectors

TastepixA
io.github.paablobello
Generate images from Claude, ChatGPT, Cursor and Codex with 12 top AI image models. Up to 4 images per call, SVG vectorization, background removal, upscaling and image-to-video. Remote MCP with OAuth, no API keys.
AI & Machine Learning Image & Video Processing Multimedia Processing
101
https://mcp.tastepix.com/mcp
TastepixA
com.tastepix.mcp
Generate images from Claude, ChatGPT, Cursor and Codex with 12 top AI image models and 10 tools: up to 4 images per call, SVG vectorization, editing and more. Remote MCP with OAuth, no API keys. Pay per image, no subscription.
AI & Machine Learning Image & Video Processing
101
https://mcp.tastepix.com/mcp
Apatero Studio
ai.apatero
AI image and video generation, talking avatars, consistent characters and photo packs from Claude.
Image & Video Processing AI & Machine Learning
1
https://mcp.apatero.ai/mcp
HyperFrames
net.hyperframes
Generate images and video from Claude with one API key.
Image & Video Processing AI & Machine Learning
1
https://hyperframes.net/api/mcp

Related MCP Servers

Image Toolkit MCP Server
Image & Video Processing Multimedia Processing
Kira-Pgr
A
license
Not graded
quality
D
maintenance
A server that provides AI-powered image generation, modification, and processing capabilities through the Model Context Protocol, leveraging Google Gemini models and other image services.
Updated 2 years ago (2025-03-19 22:49 UTC)
19
MIT
ModelsLab Text2Image MCP
shimizu
A
license
Not graded
quality
D
maintenance
A Model Context Protocol server that enables Claude Code to generate high-quality AI images using ModelsLab API with support for multiple image generation models including Flux, Stable Diffusion, and Midjourney.
Updated 5 months ago (2026-06-05 10:27 UTC)
MIT
Imagenx MCP Server
Image & Video Processing Multimedia Processing
NewToolAI
A
license
Not graded
quality
D
maintenance
AI-powered image and video generation and processing server that supports text-to-image, image-to-image, text/image-to-video generation, image analysis, and comprehensive editing operations (crop, resize, convert, adjust) through providers like Doubao and Aliyun.
Updated a year ago (2025-11-26 13:26 UTC)
6
MIT
NanoBanana MCP
Image & Video Processing Multimedia Processing
pistachiomatt
A
license
A
quality
D
maintenance
An MCP server that brings Google Gemini's image generation and editing capabilities to Claude Desktop, Claude Code, and Cursor. It supports 2K image creation, natural language image transformations, and session consistency to maintain styles across generations.
Updated 7 months ago (2026-04-17 04:16 UTC)
7
704 npm
MIT