How to Use the Diffbot MCP in LangChain

Q: Can a LangChain agent automatically choose between Diffbot extraction tools?

Yes, your ReAct agent uses analyzepage first to determine the layout. Based on that result, the agent decides whether to call extractarticle or extractproduct next in the chain.

Q: What happens if a website uses custom rules that standard tools miss?

You use extractcustomapi to apply your own extraction rules. This tool integrates into your LangChain agent's toolset just like the default extraction options.

Feed clean, structured web data directly into your LangChain pipelines without writing a single fragile CSS selector.

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 LangChain

Create your Vinkius account to connect Diffbot to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Routing with this MCP Server

`analyze_page` acts as the traffic controller for your LangChain ReAct agents by identifying whether a target URL is a product or article. This MCP Server runs first to inspect the page layout and choose the next step in the chain. This setup keeps your LangChain chains fast while Diffbot handles the extraction logic. LangSmith traces every routing decision, showing you exactly when the LangChain agent transitions from analyzing a page to calling specific Diffbot extraction tools.

Extract E-Commerce Data with LangChain Agents

`extract_product` pulls clean pricing, specifications, and availability details from any online store into your LangChain agent without breaking when the layout changes. Your LangChain agent invokes this MCP tool to get structured Diffbot JSON that feeds directly into downstream comparison steps. You don't have to write custom scrapers for LangChain. The Diffbot tool standardizes the schema, so your agent can process a Shopify page and a custom WooCommerce site using the exact same chain logic.

Clean Forum and Job Feeds for LangChain Pipelines

`extract_discussion` and `extract_job` target specialized web layouts to pull out clean forum threads and hiring posts for LangChain pipelines. Your LangChain agent can chain these Diffbot tools together to build automated industry monitoring pipelines that run on autopilot. Because the Diffbot output is structured JSON, you can pass it directly to the next LangChain chain link without parsing regex. LangSmith monitors the entire execution, giving you full visibility into what web data your LangChain agent retrieves at each step using Diffbot.

Setup guide

Set up Diffbot MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Diffbot tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "diffbot-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Diffbot transactions"
    })
    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 LangChain

Install the adapter using pip, then use MultiServerMCPClient to connect to the server URL. Call client.get_tools() to fetch the tools and pass them directly to your LangChain agent.

Yes, your ReAct agent uses analyze_page first to determine the layout. Based on that result, the agent decides whether to call extract_article or extract_product next in the chain.

LangSmith logs every single API call made by the server. You can inspect the exact input URL, the latency of the extraction, and the structured JSON output returned by tools like extract_list.

You use extract_custom_api to apply your own extraction rules. This tool integrates into your LangChain agent's toolset just like the default extraction options.

Vinkius runs the MCP Server in a secure, ephemeral V8 sandbox that processes your target URLs and HTML content. No extracted product or article JSON is stored on the host after the session closes.

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