How to Use the Diffbot MCP in AutoGen

Q: How do I add the Diffbot MCP Server to an AutoGen agent conversation?

Use mcpservertools with your server URL to retrieve the tool definitions. Pass this list to your AutoGen AssistantAgent constructor to give it access to the extraction tools.

Q: Can AutoGen agents debate which Diffbot tool to use on a page?

Yes, your agents can call analyzepage first to get the layout classification. They then discuss the result in the conversation thread to decide if they should call extractarticle or extractproduct.

Q: Can I use custom extraction rules in my AutoGen team?

Yes, extractcustomapi allows your agents to extract specific data fields based on custom rules. The agents can then debate the extracted custom fields in their conversation loop.

Coordinate multi-agent debates in AutoGen using structured, real-time web data extracted by Diffbot.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Diffbot MCP to AutoGen

Create your Vinkius account to connect Diffbot to AutoGen and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Diffbot with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-Driven Web Analysis in AutoGen

`analyze_page` lets your AutoGen agents debate the nature of a webpage before extracting its contents. A researcher agent can run this tool to classify a URL, then debate with a writer agent on whether to extract it as an article or a product. The AutoGen agents use the classified layout type from Diffbot to agree on the next tool call, ensuring the conversation moves forward with high-quality structured data.

Multi-Agent Product Evaluation with this MCP Server

`extract_product` feeds clean pricing and specifications directly into your AutoGen multi-agent workflows. A buyer agent can extract details from a competitor's page, while an analyst agent evaluates the offer and flags risks. This MCP Server eliminates the need for manual data cleaning between AutoGen agent handoffs. The structured JSON output is immediately readable by all agents in the group conversation.

Debating Job Postings and Events in AutoGen

`extract_job` and `extract_event` pull out structured details from hiring boards and schedule pages for your AutoGen recruiting agents. In AutoGen, a recruiting agent can extract a job posting, and a screening agent can immediately match it against candidate profiles. Because Diffbot handles the messy web parsing, your AutoGen agents can focus entirely on comparing schedules and analyzing requirements in their chat. The agents discuss the extraction results in real time to reach a consensus.

Setup guide

Set up Diffbot MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Diffbot tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Diffbot_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Diffbot data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

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

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Diffbot_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Diffbot data")
    print(result.messages[-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Diffbot. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Diffbot now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Diffbot MCP in AutoGen

Use mcp_server_tools with your server URL to retrieve the tool definitions. Pass this list to your AutoGen AssistantAgent constructor to give it access to the extraction tools.

Yes, your agents can call analyze_page first to get the layout classification. They then discuss the result in the conversation thread to decide if they should call extract_article or extract_product.

The MCP tool adapter automatically translates the server schemas into the format AutoGen expects. Your agents can call tools like extract_discussion and receive structured JSON directly in the chat.

Yes, extract_custom_api allows your agents to extract specific data fields based on custom rules. The agents can then debate the extracted custom fields in their conversation loop.

All web extraction is handled in an ephemeral, secure sandbox on Vinkius. The MCP Server processes the target URLs, returns the structured JSON to your AutoGen agents, and completely purges the session data.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript