laozhang-image MCP
Provides tools for generating and editing images via OpenAI's image API through the laozhang.ai proxy, allowing text-to-image and image-to-image transformations.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@laozhang-image MCPGenerate a 2k landscape image of a mountain lake at sunrise"
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.
laozhang-image MCP
An MCP server that exposes image generation
and editing through laozhang.ai — an
OpenAI-compatible API proxy/aggregator. Default model: gpt-image-2-vip
(flat ~$0.03 per image).
Works with any MCP client (Claude Code, Claude Desktop, etc.). The API key is read from the environment and never stored in code.
What it does
laozhang.ai mirrors the OpenAI Image API (/v1/images/generations,
/v1/images/edits) but with its own models and pricing. This server wraps those
endpoints as two MCP tools:
Tool | Description |
| Text → image. Saves PNG(s), returns file path and source URL. |
| Image → image. Edits an existing picture from a prompt (optional mask). |
size accepts presets 1k / 2k / 4k, square / landscape / portrait,
auto, or an explicit WxH like 1024x1536.
Related MCP server: openai-gpt-image-1-mcp
Install
git clone https://github.com/agentseo/laozhang-image-mcp.git
cd laozhang-image-mcp
python3 -m venv .venv
.venv/bin/pip install -r requirements.txtConfigure
Env var | Default | Purpose |
| — (required) | your laozhang.ai key |
|
| API base URL |
|
| model id |
|
| where PNGs are saved |
Connect to Claude Code
claude mcp add laozhang-image -s user \
-e LAOZHANG_API_KEY=sk-your-key \
-e LAOZHANG_MODEL=gpt-image-2-vip \
-- /path/to/laozhang-image-mcp/.venv/bin/python \
/path/to/laozhang-image-mcp/server.pyOr edit your config manually — see mcp.example.json.
Verify with claude mcp list (expect ✓ connected).
Sanity check (plain curl)
curl https://api.laozhang.ai/v1/images/generations \
-H "Authorization: Bearer $LAOZHANG_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-image-2-vip","prompt":"a red fox","n":1,"size":"1024x1024"}'Русский
MCP-сервер для генерации и редактирования картинок через
laozhang.ai — OpenAI-совместимый прокси-агрегатор.
Модель по умолчанию gpt-image-2-vip (~$0.03 за картинку). Подходит для
любого MCP-клиента (Claude Code, Claude Desktop).
Что делает. laozhang.ai повторяет формат OpenAI Image API, но со своими моделями и ценами. Сервер оборачивает это в два инструмента:
generate_image(prompt, size, quality, n)— текст → картинка. Сохраняет PNG, возвращает путь к файлу и URL.edit_image(image_path, prompt, size, mask_path)— картинка → картинка. Редактирует существующее изображение по описанию (можно с маской).
size: пресеты 1k / 2k / 4k, square / landscape / portrait, auto,
либо явно 1024x1536.
Ключ не хранится в коде — берётся из переменной окружения LAOZHANG_API_KEY
(см. таблицу выше). Установка и подключение — в английской секции.
License
MIT — see LICENSE.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables image generation and editing using OpenAI's GPT Image API (gpt-image-1, 1.5, 2) with support for multi-image generation, history management, and batch processing.Last updated12591MIT
- Flicense-qualityDmaintenanceProvides AI agents and coding assistants with image generation and editing capabilities using OpenAI's GPT-image-1 model, with support for local or Supabase storage.Last updated3
- AlicenseAqualityDmaintenanceEnables image generation and editing using Volcengine Ark Doubao-Seedream models, with tools for text-to-image, image-to-image, editing, and result polling.Last updated425MIT
- Alicense-qualityDmaintenanceEnables image and video generation from text, image editing, and text-to-video workflows using AI models via OpenRouter and fal.ai.Last updatedMIT
Related MCP Connectors
Generate, edit and upscale AI video and images from any agent via VicSee.
Generate on-brand images from your AI agent: design, edit, and render templates over MCP.
Generate images, GIFs, and PDFs from HTML, URLs, or templates — from your AI agent.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/agentseo/laozhang-image-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server