How to integrate Diffbot MCP with OpenAI Agents SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Diffbot Logo
open-ai-agents-sdk Logo
divider

Introduction

This guide walks you through connecting Diffbot to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Diffbot agent that can extract specs and reviews from a product page, summarize key details from a news article url, list all bulk data extraction jobs for my account, get discussion threads from a forum post link through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Diffbot account through Composio's Diffbot MCP server.

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

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Diffbot
  • Configure an AI agent that can use Diffbot as a tool
  • Run a live chat session where you can ask the agent to perform Diffbot operations

What is open-ai-agents-sdk?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

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

The Diffbot MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Diffbot account. It provides structured and secure access to web data extraction and analysis, so your agent can extract structured data from web pages, analyze content types, retrieve product details, manage bulk jobs, and search extracted datasets on your behalf.

  • Automatic content analysis and extraction: Let your agent analyze any web page and automatically extract structured data such as articles, products, events, images, or videos using AI-powered tools.
  • Article and discussion thread extraction: Effortlessly pull detailed metadata, authors, publication dates, and full discussion threads from news sites, blogs, forums, and comment sections.
  • Product and event data gathering: Instantly extract comprehensive product specifications, pricing, reviews, and event information including venues, dates, and descriptions from e-commerce or event pages.
  • Bulk job management and search: Enable your agent to list, monitor, and search across large-scale crawl or extraction jobs, making it easy to work with massive web data collections.
  • Account and usage insights: Retrieve your Diffbot account details, plan information, and usage statistics to stay on top of quotas and manage your web data operations efficiently.

Supported Tools & Triggers

Tools
Diffbot SearchTool to search data extracted by crawl or bulk jobs using dql queries.
Get Diffbot Account DetailsTool to retrieve account details, including plan information and usage statistics.
Diffbot AnalyzeTool to automatically determine a page's content type and route it to the appropriate extraction api.
Get Article DataTool to extract information from articles, including authors, publication dates, and images.
Get Discussion ThreadTool to extract threads of content from forums, comment sections, and review pages.
Diffbot Get EventTool to extract event details from web pages.
Diffbot Get ImageTool to extract detailed information about images, including dimensions and recognition data.
Diffbot Get ProductTool to extract product information such as specifications, prices, availability, and reviews.
Get Video DataTool to extract information from videos, including titles, descriptions, and embedded html.
List Bulk JobsTool to list all bulk jobs associated with a specific token.
Resolve Lost IDTool to resolve lost ids in the knowledge graph.
Start Bulk JobTool to start a bulk extract job.
Start Crawl JobTool to spider a site for links and process them with the extract api into a single collection.
Stop Bulk JobTool to stop a running bulk job.

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

What is Tool Router?

Composio's Tool Router 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 Tool Router

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

How the Tool Router works

The Tool Router 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

Prerequisites

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Diffbot project
  • Some knowledge of Python or Typescript

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

Install dependencies

pip install composio_openai_agents openai-agents python-dotenv

Install the Composio SDK and the OpenAI Agents SDK.

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

Import dependencies

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Diffbot.

Set up the Composio instance

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())
What's happening:
  • load_dotenv() loads your .env file so OPENAI_API_KEY and COMPOSIO_API_KEY are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.

Create a Tool Router session

# Create a Diffbot Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["diffbot"]
)

mcp_url = session.mcp.url

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only diffbot.
  • The router checks the user's Diffbot connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Diffbot.
  • This approach keeps things lightweight and lets the agent request Diffbot tools only when needed during the conversation.

Configure the agent

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Diffbot. "
        "Help users perform Diffbot operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Diffbot and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a HostedMCPTool that connects to the MCP server URL we created earlier.
  • The headers dict includes the Composio API key for secure authentication with the MCP server.
  • require_approval: 'never' means the agent can execute Diffbot operations without asking for permission each time, making interactions smoother.

Start chat loop and handle conversation

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
What's happening:
  • The program prints a session URL that you visit to authorize Diffbot.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using Runner.run().
  • The responses are printed to the console, and conversations are saved locally using SQLite.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Diffbot and open-ai-agents-sdk:

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())

# Create Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["diffbot"]
)
mcp_url = session.mcp.url

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Diffbot. "
        "Help users perform Diffbot operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())

Conclusion

This was a starter code for integrating Diffbot MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Diffbot.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.

How to build Diffbot MCP Agent with another framework

Claude Agent SDK

Claude Agent SDK

Use Diffbot MCP with Claude Agent SDK

Google ADK

Google ADK

Use Diffbot MCP with Google ADK

LangChain

LangChain

Use Diffbot MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Diffbot MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Diffbot MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Diffbot MCP with LlamaIndex

CrewAI

CrewAI

Use Diffbot MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Diffbot MCP?

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

Can I use Tool Router MCP with OpenAI Agents SDK?

Yes, you can. OpenAI Agents SDK 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 Diffbot tools.

Can I manage the permissions and scopes for Diffbot while using Tool Router?

Yes, absolutely. You can configure which Diffbot 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.

How safe is my data with Composio Tool Router?

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 Diffbot data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free