Pictify

Created By
Pictify2 months ago
Generate images, GIFs, and PDFs from AI agents — OG images, social cards, invoices, certificates, and more from natural language.
Overview

Pictify gives AI agents the ability to generate, manage, and A/B test visual content. No code required — just describe what you want.

31 tools across 6 categories

Image Generation

Create images from HTML/CSS, URL screenshots, or reusable templates. PNG, JPEG, WebP up to 4000x4000px. Perfect for OG images, Twitter cards, banners, and product screenshots.

GIF Creation

Generate animated GIFs from CSS animations or record live web pages. Ideal for product demos, animated banners, and loading animations.

PDF Rendering

Single or multi-page PDFs from templates. Invoices, certificates, reports, shipping labels, and ID cards with preset page sizes.

Template System

Create, manage, and render reusable templates with variable placeholders. 50+ expression functions for conditionals, string manipulation, and date formatting.

Batch Operations

Generate up to 100 personalized images in one request. Team badges, event passes, product catalogs, localized marketing assets.

A/B Testing

Built-in experiments with traffic splitting, Thompson Sampling auto-optimization, and event tracking for impressions, clicks, and conversions.

Quick Start

  1. Get your API key at https://pictify.io/dashboard/api-tokens
  2. Add the MCP server to your client
  3. Start generating — just ask your AI assistant to create images, GIFs, or PDFs

Works with Claude (claude.ai, Claude Code, Claude Desktop), Cursor, Windsurf, and any MCP-compatible client.

Note: For Github URL, I'd use the actual GitHub repo (https://github.com/pictify-io/pictify-mcp) instead of the npm link — mcp.so likely expects a GitHub URL for that field.

Server Config

{
  "mcpServers": {
    "pictify": {
      "command": "npx",
      "args": [
        "-y",
        "@pictify/mcp-server"
      ],
      "env": {
        "PICTIFY_API_KEY": "your_api_key"
      }
    }
  }
}
Project Info
Created At
2 months ago
Updated At
2 months ago
Author Name
Pictify
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

2 days ago