Pictify MCP Server
The Pictify MCP Server enables AI agents to programmatically generate images, animated GIFs, and PDFs, manage reusable templates, run batch operations, and conduct A/B experiments on image variants.
Image Generation
Create static images (PNG, JPEG, WebP) from HTML/CSS, URL screenshots, FabricJS canvas data, or saved templates
List and retrieve previously generated images
GIF Creation
Generate animated GIFs from HTML with CSS animations, URLs, or templates
Record GIFs from live web pages over a specified duration (up to 30 seconds)
PDF Rendering
Render single or multi-page PDFs (up to 100 pages) from templates with dynamic variable substitution
Support for page size presets (A4, Letter, Legal, etc.)
Template Management
Full CRUD operations on reusable HTML or FabricJS-based templates
Inspect variable definitions (types, defaults, descriptions) and render with 50+ expression functions for dynamic content
Batch Operations
Start async batch render jobs to generate up to 100 personalized images from a single template
Check job status, retrieve result URLs, or cancel running jobs
A/B Testing & Experiments
Create A/B tests with traffic splitting and Thompson Sampling auto-optimization
Create smart link experiments (conditional content by device, location, time, browser, referrer) and scheduled experiments
Start, pause, complete experiments, declare winners, and track impressions, views, clicks, and conversions
Integrations: Works with Claude Desktop, Claude Code, Cursor, Windsurf, and any MCP-compatible client via stdio or HTTP transport.
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., "@Pictify MCP ServerCreate a social media card for 'How to use MCP' with a blue gradient background"
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.
@pictify/mcp-server
An MCP (Model Context Protocol) server for Pictify — generate images, GIFs, videos, and PDFs from AI agents like Claude, Cursor, and Windsurf.
One-line install. No code required. Ask your AI assistant to create OG images, social media cards, screenshots, animated GIFs, PDF invoices, certificates, and more — all from natural language.
What can it do?
Generate images from HTML/CSS, URLs, or reusable templates (OG images, Twitter cards, banners, product screenshots)
Create animated GIFs from CSS animations or by recording live web pages
Render videos from templates, including agent-authored Remotion scenes
Render PDFs from templates — invoices, certificates, reports, shipping labels
Batch generate up to 100 personalized images in one request (team badges, event passes, product catalogs)
Template system with 50+ expression functions for dynamic content (conditionals, string manipulation, date formatting)
Works with Claude (claude.ai + Claude Code + Claude Desktop), Cursor, Windsurf, and any MCP-compatible client.
Quick Start
Prerequisites
Get your API key:
Sign up or log in at pictify.io
Go to API Tokens
Create a new token and copy it
Claude.ai (Web)
Use the hosted remote server — no install needed:
Go to claude.ai > Settings > Connectors
Click Add custom connector
URL:
https://mcp.pictify.ioClick Advanced Settings
Client ID:
pictifyClient Secret: paste your API token
Click Add
Claude Code
claude mcp add pictify -e PICTIFY_API_KEY=your_api_key -- npx -y @pictify/mcp-serverClaude Desktop
Add to your config file:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.jsonLinux:
~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"pictify": {
"command": "npx",
"args": ["-y", "@pictify/mcp-server"],
"env": {
"PICTIFY_API_KEY": "your_api_key"
}
}
}
}Restart Claude Desktop after saving.
Cursor
Add to Cursor's MCP settings (Settings > MCP Servers):
{
"mcpServers": {
"pictify": {
"command": "npx",
"args": ["-y", "@pictify/mcp-server"],
"env": {
"PICTIFY_API_KEY": "your_api_key"
}
}
}
}Windsurf
Add to Windsurf's MCP settings:
{
"mcpServers": {
"pictify": {
"command": "npx",
"args": ["-y", "@pictify/mcp-server"],
"env": {
"PICTIFY_API_KEY": "your_api_key"
}
}
}
}Related MCP server: PagePixels Screenshots MCP Server
Examples
Try these prompts after connecting:
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 team-badge template to generate images for these 10 team members: ..."
Create a PDF invoice:
"Render my invoice template as a PDF with company name 'Acme Inc', amount '$1,500', and date 'March 2026'."
Available Tools
Image Generation
Tool | Description |
| Generate an image from HTML/CSS, a URL screenshot, or a template |
| Generate an image from FabricJS canvas JSON data |
| List previously generated images |
| Get details of a specific image by ID |
GIF Creation
Tool | Description |
| Create animated GIF from HTML with CSS animations |
| Record a GIF from a live web page over time |
| List previously generated GIFs |
| Get details of a specific GIF by ID |
PDF Generation
Tool | Description |
| Generate single-page PDF from a template |
| Generate multi-page PDF from a template |
| List available PDF page size presets |
Template Management
Tool | Description |
| List saved templates with filtering and pagination |
| Get template details |
| Get template variable definitions and types |
| Render a template with variables (supports layout variants) |
| Create a new template (HTML or FabricJS) |
| Update an existing template |
| Delete a template |
Batch Operations
Tool | Description |
| Start batch render job (up to 100 items, async) |
| Check batch job status and get result URLs |
| Cancel a running batch job |
Configuration
Variable | Description | Default |
| Your Pictify API key (required for stdio mode) | — |
| Custom API base URL |
|
| Enable verbose logging to stderr |
|
| Slug identifying where this MCP server was installed from (e.g. |
|
Install attribution
When you submit @pictify/mcp-server to an MCP directory, set
PICTIFY_MCP_SOURCE in the install snippet so we can attribute signups
to that listing. Example for the mcp.so directory entry:
{
"mcpServers": {
"pictify": {
"command": "npx",
"args": ["-y", "@pictify/mcp-server"],
"env": {
"PICTIFY_API_KEY": "your_api_key",
"PICTIFY_MCP_SOURCE": "mcp.so"
}
}
}
}For the hosted remote (https://mcp.pictify.io), pass the slug as a
query param on the connector URL instead — the server persists it on
the OAuth session:
https://mcp.pictify.io?source=mcp.soAccepted slugs: lowercase letters, digits, ., -, _, up to 64
characters. Anything else is dropped to unknown.
Development
git clone https://github.com/pictify-io/pictify-mcp.git
cd pictify-mcp
npm install
npm run buildTest with MCP Inspector:
PICTIFY_API_KEY=your_key npm run inspectorLicense
MIT
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
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to capture webpage screenshots, generate PDFs from URLs or HTML, and extract rich metadata like Open Graph and JSON-LD data. It provides tools for web-to-image/PDF conversion and structured data extraction through the Junipr API.191MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to capture website screenshots, automate browser interactions, and manage recurring screenshot configurations across 150+ global locations. It also supports AI-powered domain research and visual change monitoring for any web page.15MIT
- AlicenseAqualityBmaintenanceCapture screenshots, generate PDFs, and render HTML to images via AI agents. Supports batch capture, geo-targeting, async webhooks, and CSS/JS injection.11907MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to generate images from HTML/CSS, capture URL screenshots, and manage reusable templates through the RendShot API. Provides tools for rendering visual content programmatically within AI workflows.14
Related MCP Connectors
Image + screenshot API for agents: HTML/CSS to images or PDF, screenshot any URL, verify text.
Screenshots, PDFs and Markdown from any URL or HTML for AI agents, via the SnapForge API
Render HTML, Markdown, or URLs to images, PDF, or branded artifacts; extract and watch pages.
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/pictify-io/mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server