Pictify MCP Server
Enables AI assistants to programmatically generate images, GIFs, and PDFs from HTML/CSS or web screenshots using the Pictify API. It also supports template management, batch rendering jobs, and A/B test experiment controls.
README
@pictify/mcp-server
Generate images, GIFs, and PDFs with AI agents using Pictify.
An MCP (Model Context Protocol) server that wraps the Pictify API, enabling AI assistants to create visual content programmatically.
Installation
Claude Desktop
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"pictify": {
"command": "npx",
"args": ["-y", "@pictify/mcp-server"],
"env": {
"PICTIFY_API_KEY": "pk_live_your_api_key"
}
}
}
}
Restart Claude Desktop after saving.
Claude Code
claude mcp add pictify -- npx -y @pictify/mcp-server
Set your API key:
export PICTIFY_API_KEY=pk_live_your_api_key
Cursor
Add to your Cursor MCP settings:
{
"mcpServers": {
"pictify": {
"command": "npx",
"args": ["-y", "@pictify/mcp-server"],
"env": {
"PICTIFY_API_KEY": "pk_live_your_api_key"
}
}
}
}
Available Tools
Image Generation
| Tool | Description |
|---|---|
pictify_create_image |
Generate an image from HTML/CSS content |
pictify_screenshot |
Capture a screenshot of a web page |
pictify_list_images |
List previously generated images |
GIF Creation
| Tool | Description |
|---|---|
pictify_create_gif |
Create animated GIF from HTML with CSS animations |
pictify_capture_gif |
Capture GIF from a live web page |
pictify_list_gifs |
List previously generated GIFs |
PDF Generation
| Tool | Description |
|---|---|
pictify_render_pdf |
Generate single-page PDF from template |
pictify_render_multi_page_pdf |
Generate multi-page PDF from template |
pictify_list_pdf_presets |
List available PDF size presets |
Template Management
| Tool | Description |
|---|---|
pictify_list_templates |
List saved templates |
pictify_get_template |
Get template details |
pictify_get_template_variables |
Get template variable definitions |
pictify_render_template |
Render template with variables |
pictify_create_template |
Create a new template |
pictify_update_template |
Update an existing template |
pictify_delete_template |
Delete a template |
Batch Operations
| Tool | Description |
|---|---|
pictify_batch_render |
Start batch render job (up to 100 items) |
pictify_get_batch_results |
Check batch job status and results |
pictify_cancel_batch |
Cancel a running batch job |
Experiments
| Tool | Description |
|---|---|
pictify_list_experiments |
List A/B test experiments |
pictify_create_experiment |
Create a new experiment |
pictify_get_experiment |
Get experiment details |
pictify_update_experiment |
Update an experiment |
pictify_delete_experiment |
Delete an experiment |
pictify_start_experiment |
Start a draft/paused experiment |
pictify_pause_experiment |
Pause a running experiment |
pictify_complete_experiment |
Complete experiment with winner |
Configuration
| Variable | Description | Default |
|---|---|---|
PICTIFY_API_KEY |
Your Pictify API key (required) | — |
PICTIFY_BASE_URL |
Custom API base URL | https://api.pictify.io |
PICTIFY_DEBUG |
Enable verbose logging to stderr | false |
Get your API key at pictify.io/dashboard.
Examples
Create a social media card:
"Create a Twitter card image for my blog post titled 'Getting Started with MCP' with a blue gradient background, 1200x630."
Screenshot a website:
"Take a screenshot of stripe.com at 1440x900."
Render a template:
"List my templates and render the blog-header template with title 'Hello World'."
Batch generate images:
"Use my invoice template to generate PDFs for these 5 customers: ..."
Development
git clone https://github.com/pictify-io/pictify-mcp.git
cd pictify-mcp
npm install
npm run build
Test with MCP Inspector:
PICTIFY_API_KEY=pk_test_... npm run inspector
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。