Use Diffbot with your AI.
Connect your account once and let the AI you already use work with it, without building another integration. Automate web data extraction via Diffbot. turn any website into structured JSON data for articles, products, discussions, and more directly from any AI agent.
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.
Complete set · 10 capabilities
The complete Diffbot capability set.
These are the exact actions your AI can choose when you ask it to work with Diffbot.
01-04
4 capabilities in this set.
Part of 10 available through Diffbot.
- 01
Analyze page
Diffbot uses ML to determine if the page is an article, product, image, video, event, list, or job, and returns the appropriate structured JSON. Excellent generalized entry point. Automatically classify and extract page data using Diffbot Analyze API
- 02
Extract article
Pass optional discussion=false to skip extracting comments. Extract news, blog, or article content using Diffbot Article API
- 03
Extract custom API
Diffbot will extract data according to your custom ruleset. Extract using a user-defined custom Diffbot API
- 04
Extract discussion
Extract forum threads, reviews, or comments using Diffbot Discussion API
05-07
3 capabilities in this set.
Part of 10 available through Diffbot.
- 05
Extract job
Extract job postings using Diffbot Job API
- 06
Extract list
Extract lists or search results using Diffbot List API
- 07
Extract product
Extract e-commerce product details using Diffbot Product API
08-10
3 capabilities in this set.
Part of 10 available through Diffbot.
- 08
Extract event
Extract event schedules and details using Diffbot Event API
- 09
Extract image
Extract main images from a page using Diffbot Image API
- 10
Extract video
Extract video content and metadata using Diffbot Video API
Observed, not estimated
889ms average. Fast in production.
Diffbot is checked daily against the live service.
- Fastest day
- 757ms
- Slowest day
- 1079ms
- 14-day trend
- Slowing+14%
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.
https://edge.vinkius.com/vk_preview_FiT28RroNiKkMcafLWUuAoeV2pbdaAk9JBpgecYE/mcpClaude 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.
{
"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
FAQ
Questions Diffbot owners ask.
- 01
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.
- 02
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.
- 03
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
JigsawStack AI Connector
Access a suite of AI utility APIs for web scraping, translation, OCR, and sentiment analysis in one developer-
ViewDiffbot AI Connector
Extract structured data from any web page using AI that understands content like a human and builds knowledge
ViewTavily AI Connector
Search the web for AI — audit search context, answers, and extracted content via AI.
ViewAlgoDocs AI Connector
AI document extraction orchestration — parse PDFs, images, and Word docs via AI.
View
Suggestions
ScrapingAnt AI Connector
Extract web data reliably with rotating proxies, headless Chrome rendering, and CAPTCHA solving built into eve
ViewWeb Scraper AI Connector
Equip your AI agent with the ability to search the web, read pages, extract metadata, and crawl sites as clean
ViewScrapfly AI Connector
Scrape web data at scale with a managed API that handles proxies, browser rendering, and anti-bot bypassing au
ViewNimbleway AI Connector
Web data collection and scraping via Nimbleway — extract content and search the web directly from your AI agen
View
