OpenGraph MCP Server

Give your AI assistant the power to fetch link previews, capture screenshots, scrape web content, and extract structured data—all through the secure Model Context Protocol.

What You Get

The OpenGraph MCP Server (opengraph-io-mcp) exposes every OpenGraph.io API endpoint to AI assistants through the MCP standard. This means your AI can:

Unfurl URLs – Extract OpenGraph metadata, Twitter Cards, and page information from any website
Capture Screenshots – Take high-quality screenshots at various viewport sizes
Scrape HTML – Fetch raw page content with JavaScript rendering and bot detection bypass
Extract Content – Pull specific HTML elements (headings, paragraphs) in structured format
Query Pages – Ask questions about webpage content and get AI-powered answers
Generate Images – Create illustrations, diagrams, icons, and social cards with AI

How It Works

The MCP server acts as a secure bridge between your AI assistant and the OpenGraph.io API:

Architecture

┌─────────────────┐     MCP (JSON-RPC)     ┌──────────────────┐
│  AI Assistant   │ ──────────────────────▶ │  opengraph-io-mcp │
│  (Claude, etc.) │                         │    (local)        │
└─────────────────┘                         └────────┬──────────┘
                                                     │ REST API
                                                     ▼
                                           ┌──────────────────────┐
                                           │  api.opengraph.io    │
                                           └──────────────────────┘

Key benefits of this architecture:

API key stays local – Your App ID is stored in your config file, never sent to the AI model
No code changes – The AI naturally calls the tools when relevant
Works offline – The MCP server runs locally on your machine

Available Tools

Tool Name	API Endpoint	Description
Get OG Data	`/api/1.1/site`	Extract OpenGraph metadata from a URL
Scrape	`/api/1.1/scrape`	Fetch raw HTML with JS rendering
Screenshot	`/api/1.1/screenshot`	Capture webpage screenshot
Query	`/api/1.1/query`	Ask questions about page content
Generate Image	`AI Image Generation`	Create illustrations, diagrams, and social cards
Iterate Image	`AI Image Generation`	Refine and modify generated images
Export Image	`Local Filesystem`	Save generated images to your project

New: Image generation tools are now available! Learn more about AI image generation →

Supported Clients

The OpenGraph MCP Server works with any client that supports the Model Context Protocol:

Claude Desktop

Anthropic's desktop application for Claude.

Cursor

The AI-first code editor with MCP support.

VS Code

Visual Studio Code with Copilot Chat MCP.

Windsurf

Codeium's AI-powered IDE.

JetBrains

JetBrains AI Assistant integration.

Zed

High-performance code editor with AI features.

Get started quickly: Visit the Install Hub for copy-paste configurations for all supported clients.

Security Model

The MCP architecture keeps your credentials secure:

Local execution – The MCP server runs on your machine, not in the cloud
Environment variables – Your App ID is stored in a config file, never transmitted to AI models
Stdio transport – Communication happens through standard input/output, not over the network
No persistent state – The server doesn't store any request data

Transport Options

Stdio (Recommended)

The default and recommended transport. The MCP server runs as a subprocess of your AI client, communicating through stdin/stdout:

Stdio transport

npx -y opengraph-io-mcp

HTTP/SSE (Advanced)

For advanced use cases, you can run the server over HTTP with Server-Sent Events:

HTTP transport

# Start the server on port 3010
npm start

# Connect via SSE
http://localhost:3010/sse?app_id=YOUR_APP_ID