How do I use my own custom extraction rules?

You can use the extract_custom_api capability. This allows your agent to bridge raw URLs to the custom rulesets you have already trained in your Diffbot dashboard.

Do I need to write code to scrape a website?

No. This MCP uses machine learning to identify page elements, so you can perform extraction using natural language commands through your AI agent.

Which AI clients are compatible with this MCP?

This MCP works with any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

Can I extract data from e-commerce sites?

Yes. The extract_product capability is specifically designed to pull pricing, SKUs, brands, and specifications from retail websites.

What kind of data format does it return?

The MCP returns structured JSON data, making it easy for your AI agent to process and use the information immediately.

Can my agent automatically identify what kind of page a URL points to?

Yes. Use the 'analyze_page' capability. Diffbot uses ML to classify the URL as an article, product, image, video, or list, and returns the appropriate structured JSON payload automatically.

How do I extract only the main text from a blog post without comments?

Use the 'extract_article' capability and set the 'discussion' parameter to 'false'. The agent will retrieve the clean text and HTML body while explicitly ignoring any forum threads or review blocks on the page.

Can I use custom extraction rules I've defined in my Diffbot dashboard?

Absolutely. Use the 'extract_custom_api' capability. Provide your trained 'api_name' and the target URL. Diffbot will extract the data according to your specific structural ruleset natively.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Diffbot to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Turn messy websites into clean, structured JSON data instantly.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Diffbot.

01
Extract article
This capability pulls news, blog, or article content into clean text or HTML. You can skip comments by setting the discussion parameter to false.
02
Extract custom API
This capability runs extraction based on your specific Diffbot rulesets. It applies your custom logic to any URL you provide.
03
Extract job
This capability pulls job postings from recruitment pages. It captures specific details like job titles, employers, and salary information.
04
Extract product
This capability scrapes e-commerce data. It captures structured details like price, brand, SKU, and technical specifications.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Diffbot.

05
Analyze page
This capability uses machine learning to classify a page as an article, product, list, or other type. It returns the appropriate structured JSON based on what it finds.
06
Extract discussion
This capability targets forum threads, reviews, or comment sections. It pulls the conversational data you need for sentiment or trend analysis.
07
Extract event
This capability pulls event schedules and details. It turns event pages into structured data points.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Diffbot.

08
Extract image
This capability identifies and extracts the primary images from a webpage.
09
Extract list
This capability identifies and extracts arrays of items from directories or search results. It focuses on grabbing titles and links from bounded lists.
10
Extract video
This capability pulls video content and its associated metadata from a page.

Real work

What teams actually run

Competitor Monitoring

Your agent tracks price changes and new product launches on retail sites.

News Aggregation

You instruct your agent to pull full article text and metadata from various news outlets.

Sentiment Analysis

The agent scrapes forum discussions and reviews to help you understand consumer feedback.

Job Market Tracking

You use the agent to monitor job titles and salary trends across recruitment platforms.

Automate a task

Put Diffbot to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Diffbot works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Diffbot to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

890ms average. Fast in production.

Diffbot is checked daily against the live service.

Daily averagePeak 1110ms

Oct 3Today

Fastest day: 824ms
Slowest day: 1110ms
14-day trend: Slowing+18%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Diffbot, so you can see the experience inside your AI.

It does not authenticate your account with Diffbot. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Diffbot Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_FiT28RroNiKkMcafLWUuAoeV2pbdaAk9JBpgecYE/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Diffbot capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "diffbot-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_FiT28RroNiKkMcafLWUuAoeV2pbdaAk9JBpgecYE/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Diffbot in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Diffbot owners hand off.

This MCP is built for professionals who need to turn the unstructured web into actionable datasets without writing code.

01
Data Analysts
They hand off the task of gathering structured data from thousands of sites to their AI agent.
02
Market Researchers
They use the agent to monitor competitor pricing and product changes across the web.
03
Content Marketers
They task their agent with summarizing articles and tracking brand mentions in forums.
04
Developers
They use the agent to test and debug web extraction pipelines using natural language.

FAQ

Questions Diffbot owners ask.

01
How do I use my own custom extraction rules?
You can use the extract_custom_api capability. This allows your agent to bridge raw URLs to the custom rulesets you have already trained in your Diffbot dashboard.
02
Do I need to write code to scrape a website?
No. This MCP uses machine learning to identify page elements, so you can perform extraction using natural language commands through your AI agent.
03
Which AI clients are compatible with this MCP?
This MCP works with any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.
04
Can I extract data from e-commerce sites?
Yes. The extract_product capability is specifically designed to pull pricing, SKUs, brands, and specifications from retail websites.
05
What kind of data format does it return?
The MCP returns structured JSON data, making it easy for your AI agent to process and use the information immediately.
06
Can my agent automatically identify what kind of page a URL points to?
Yes. Use the 'analyze_page' capability. Diffbot uses ML to classify the URL as an article, product, image, video, or list, and returns the appropriate structured JSON payload automatically.
07
How do I extract only the main text from a blog post without comments?
Use the 'extract_article' capability and set the 'discussion' parameter to 'false'. The agent will retrieve the clean text and HTML body while explicitly ignoring any forum threads or review blocks on the page.
08
Can I use custom extraction rules I've defined in my Diffbot dashboard?
Absolutely. Use the 'extract_custom_api' capability. Provide your trained 'api_name' and the target URL. Diffbot will extract the data according to your specific structural ruleset natively.

Explore

More in AI Frontier

Connect Diffbot to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Extract article

Extract custom API

Extract job

Extract product

05-07

Analyze page

Extract discussion

Extract event

08-10

Extract image

Extract list

Extract video

What teams actually run

Competitor Monitoring

News Aggregation

Sentiment Analysis

Job Market Tracking

Building your own app? The connector is yours to use.

Diffbot Connector

Claude Desktop

Data Analysts

Market Researchers

Content Marketers

Developers

How do I use my own custom extraction rules?

Do I need to write code to scrape a website?

Which AI clients are compatible with this MCP?

Can I extract data from e-commerce sites?

What kind of data format does it return?

Can my agent automatically identify what kind of page a URL points to?

How do I extract only the main text from a blog post without comments?

Can I use custom extraction rules I've defined in my Diffbot dashboard?

Diffbot AI Connector

Import.io (Web Data Extraction) AI Connector

Web Scraper AI Connector

Apify AI Connector

Suggestions

Apify AI Connector

Grepsr AI Connector

Octoparse AI Connector

Octoparse AI Connector