Integration

Diffbot integration

AI-powered web data extraction APIs. Automatically extract structured data from any web page using machine learning. Includes Article, Product, Image, Video, Discussion, List, and Analyze APIs for extracting articles, e-commerce products, images, videos, forum threads, list pages, and auto-classified pages. Also provides Crawl API to spider entire websites, Knowledge Graph APIs for entity search and enrichment, Custom API for user-defined extraction rules, and Account API for usage monitoring. Returns clean, structured JSON with entities, sentiment, tags, and metadata.

Connect Diffbot How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Diffbot.Built from the 14 Diffbot tools below, on the connection you add once.

Common Diffbot use cases

media monitoring
content archiving
catalog building
competitive intelligence
CRM enrichment
lead generation
news monitoring
crawl monitoring
forum monitoring
price monitoring

What you can do with Diffbot

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Crawl, 2 operations

create_crawlCreate crawlPOSTCreates and starts a crawl job to spider an entire website and extract structured data from each page using a Diffbot Extract API.
get_crawlGet crawlGETRetrieves status and details of crawl jobs, or manages them (pause, resume, restart, delete).

Custom api, 2 operations

create_custom_apiCreate custom apiPOSTCreates or updates a Custom API with user-defined extraction rules for specific URL patterns.
get_custom_apisGet custom apisGETRetrieves all Custom APIs and their extraction rulesets defined on your account token.

Knowledge graph, 2 operations

kg_enhanceKg enhanceGETEnriches partial entity data by matching against the Diffbot Knowledge Graph and returning the best match with full structured details.
kg_searchKg searchGETSearches the Diffbot Knowledge Graph using DQL queries to find organizations, people, articles, and other entities.

Account, 1 operation

get_accountGet accountGETRetrieves account details including plan type, API usage statistics, child tokens, and optional invoice history.

Article, 1 operation

extract_articleExtract articleGETExtracts structured article data including title, body text, author, date, images, tags, sentiment, and categories from news and blog pages.

Discussion, 1 operation

extract_discussionExtract discussionGETExtracts structured discussion thread data including posts, authors, dates, nested replies, tags, and participant counts from forums and comment sections.

Image, 1 operation

extract_imageExtract imageGETExtracts primary images from a web page with dimensions, URLs, titles, and metadata.

List, 1 operation

extract_listExtract listGETExtracts structured list items from news index pages, product listings, search results, and other list-like pages.

Page, 1 operation

analyze_pageAnalyze pageGETAutomatically classifies a web page and extracts structured data based on its detected type (article, product, discussion, image, etc.).

Product, 1 operation

extract_productExtract productGETExtracts structured product data including title, price, availability, brand, images, specifications, and SKU from e-commerce product pages.

Video, 1 operation

extract_videoExtract videoGETExtracts video metadata including title, direct URL, embed code, duration, thumbnail images, and author from video pages.

Diffbot API rate limits

5 requests per second

Free: 5/min & 10,000/month. Startup: 5/sec. Plus: 25/sec.

These are the limits Diffbot documents, not ones LiveContext measured. They can change and often depend on your plan, so check the Diffbot documentation for current values.

Use Diffbot from Claude Code, Cursor or Codex

Connect Diffbot in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Diffbot operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Diffbot

Create your workspace
Sign up free. Nothing to install.
Connect Diffbot once
Add your Diffbot connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Diffbot integration FAQ

What can you do with the Diffbot integration?

LiveContext exposes 14 operations on Diffbot, covering crawl, custom api, knowledge graph and account. Common uses include media monitoring, content archiving and catalog building.

What are the Diffbot API rate limits?

Diffbot documents 5 requests per second. Free: 5/min & 10,000/month. Startup: 5/sec. Plus: 25/sec. Limits are set by Diffbot and can depend on your plan.