SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Opengraph io MCP with Autogen

Connect Autogen to Opengraph io MCP. Extract title and description from a news article url, get preview image for a shared blog post, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Opengraph io logoOpengraph io
Api Key

Opengraph io is an API for retrieving Open Graph metadata from any website. It helps you extract social preview and summary data, even from sites that don’t define their own tags.

4 Tools

Introduction

This guide walks you through connecting Opengraph io to AutoGen using the Composio tool router. By the end, you'll have a working Opengraph io agent that can extract Open Graph metadata, scrape site HTML, and capture website screenshots through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Opengraph io account through Composio's Opengraph io MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Opengraph io with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIPydantic AI

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Opengraph io
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Opengraph io tools
  • Run a live chat loop where you ask the agent to perform Opengraph io operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

What is the Opengraph io MCP server, and what's possible with it?

The Opengraph io MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Opengraph io account. It provides structured and secure access to website metadata, so your agent can extract Open Graph data, gather site previews, capture screenshots, and scrape raw HTML content automatically on your behalf.

  • Extract Open Graph and site metadata: Instantly pull a website's title, description, images, and social previews—even from pages without standard tags.
  • Generate rich link previews: Have your agent create accurate, attractive link previews for any site by retrieving and summarizing page metadata.
  • Scrape raw HTML and metadata: Fetch the full HTML content of a web page along with all available social and Open Graph signals for deeper analysis.
  • Capture website screenshots: Request up-to-date visual snapshots of any web page, perfect for documentation or content review workflows.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Opengraph io account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Opengraph io via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Opengraph io connections to use
5

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Opengraph io session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["opengraph_io"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Opengraph io tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed
7

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Opengraph io assistant agent with MCP tools
    agent = AssistantAgent(
        name="opengraph_io_assistant",
        description="An AI assistant that helps with Opengraph io operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Opengraph io tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Opengraph io related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Opengraph io tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Opengraph io and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Opengraph io session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["opengraph_io"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Opengraph io assistant agent with MCP tools
        agent = AssistantAgent(
            name="opengraph_io_assistant",
            description="An AI assistant that helps with Opengraph io operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Opengraph io related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into Opengraph io through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Opengraph io, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every Opengraph io action and event your agent gets out of the box.

Capture Screenshot

Capture screenshots of webpages with full-page or element-specific captures, device viewport presets, and quality settings.

Extract Site Metadata

Tool to extract site metadata.

Scrape Site

Retrieve a site's social and OpenGraph metadata, including inferred HTML metadata when available.

Scrape URL for HTML

Tool to scrape raw HTML content from a website with anti-bot protection and optional JavaScript rendering.

FRAMEWORKS

How to build Opengraph io MCP Agent with another framework

Claude Code logo

Claude Code

Use Opengraph io MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Opengraph io MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Opengraph io MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Opengraph io MCP with Claude Agent SDK

Codex logo

Codex

Use Opengraph io MCP with Codex

OpenClaw logo

OpenClaw

Use Opengraph io MCP with OpenClaw

Hermes logo

Hermes

Use Opengraph io MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Opengraph io MCP with Atomic Agent

Google ADK logo

Google ADK

Use Opengraph io MCP with Google ADK

LangChain logo

LangChain

Use Opengraph io MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Opengraph io MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Opengraph io MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Opengraph io MCP with LlamaIndex

CrewAI logo

CrewAI

Use Opengraph io MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Opengraph io MCP with Pydantic AI

FAQ

Frequently asked questions

With a standalone Opengraph io MCP server, the agents and LLMs can only access a fixed set of Opengraph io tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Opengraph io and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Autogen fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Opengraph io tools.

Yes, absolutely. You can configure which Opengraph io scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Opengraph io data and credentials are handled as safely as possible.

Start with Opengraph io.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Opengraph io tool your agent needs.Free to start.

Start building