Diffbot
Search the web, extract pages and query a knowledge graph through Diffbot's index
- Pricing
- Freemium
- Platforms
- API, CLI
- Runs
- Locally or Remotely
- Version
- 0.2.1
- Listing updated
- 3 days ago
About Diffbot
Diffbot is a freemium MCP server for web search and scraping. It can run locally on your machine or as a hosted remote server.
Diffbot's server swaps raw HTML or markdown for classified, structured JSON. Its extract tool identifies what kind of page it is fetching and returns a consistent schema tuned for low token use. search_web runs on Diffbot's own index and favours primary sources over coverage of them, with num_results and max_tokens controls and a page-cache reader that returns an already parsed copy for url: queries.
Beyond the web tools, it reaches a knowledge graph the page puts at over 10 billion entities. News can be searched by entity, topic, publisher, language, date or sentiment, organizations by industry and size, and resolve_entities maps names in text to graph IDs, returning a ready filter for fetching full records. Crawls run as background jobs you poll.
It runs as a local pypi package or a hosted endpoint with a Diffbot account; a free token exists.
Install
Run in a terminal
claude mcp add --transport http diffbot-mcp https://mcp.diffbot.com/mcpAdd to Settings → Connectors → Add custom connector
https://mcp.diffbot.com/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"diffbot-mcp": {
"url": "https://mcp.diffbot.com/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"diffbot-mcp": {
"type": "http",
"url": "https://mcp.diffbot.com/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"diffbot-mcp": {
"serverUrl": "https://mcp.diffbot.com/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"diffbot-mcp": {
"type": "http",
"url": "https://mcp.diffbot.com/mcp"
}
}
}Configuration
DIFFBOT_TOKENOptional. Diffbot API token. Free token: https://app.diffbot.com/get-started. DIFFBOT_API_TOKEN or ~/.diffbot/credentials also work.
Tools this server provides (6)
Taken from the project documentation; the running server may differ.
- extract
- Classify a page and extract structured JSON
- search_web
- Search Diffbot's web index with source-ranked results
- crawl
- Crawl a site from a seed URL as a background job
- resolve_entities
- Recognize entities in text and resolve them to Knowledge Graph IDs
- search_news
- Search news and articles by entity, topic, publisher, language, date or sentiment
- search_organizations
- Search companies by industry and other attributes
What it does
- Classified extraction
- Returns structured JSON by page type instead of raw HTML.
- Source-ranked search
- Favours primary sources and supports result and token limits.
- Page cache reader
- Gets Diffbot's parsed copy of a URL quickly.
- Background crawls
- Walks a site from a seed URL as pollable jobs.
- Entity resolution
- Links names in text to Knowledge Graph IDs.
- Knowledge Graph search
- Queries news and organizations.
Good for
- Ground an agent answer in current web sources
- Archive documentation by crawling a site
- Research companies by industry or size
- Link entities in a document to graph records
Pricing
Freemium, from $299 a month
Free 10,000 credits a month; Startup $299/mo, Plus $899/mo, Enterprise custom
Prices change. Check diffbot.com before you buy.
Diffbot FAQ
Is there a free plan?
Yes, 10,000 credits a month with no credit card.
What do paid plans cost?
Startup is $299 a month and Plus is $899 a month; Enterprise is custom.
How is usage billed?
In credits; extracting a page costs 1 credit and exporting a graph entity costs 25.
How do I sign in?
The hosted server signs in with a Diffbot account; the local package can use DIFFBOT_TOKEN.
Is Diffbot free?
Diffbot has a free plan, with paid plans for more usage or features. Paid plans start at $299 a month.
How do I add Diffbot to Claude Code?
Run this command in your terminal: claude mcp add --transport http diffbot-mcp https://mcp.diffbot.com/mcp
What are the best alternatives to Diffbot?
The closest alternatives to Diffbot are Scrapling MCP Server, Firecrawl MCP Server, Agent-Native Analytics, Google Ads + Meta Ads + SEO/GEO MCP and SearXNG Search.
Alternatives to Diffbot

Scrapling MCP Server
MCP serverMCP server for AI clients to scrape sites with HTTP and stealth browser sessions
Runs locally- 17 tools
- Open source
- 104K GitHub stars
- Web search and scraping

Firecrawl MCP Server
MCP serverMCP server that lets AI agents search, scrape and interact with web pages
- 3 tools
- Remote
- Freemium
- 7.8K GitHub stars
- Web search and scraping

Agent-Native Analytics
MCP serverOpen-source analytics app where an AI agent builds charts and dashboards from your data
- Remote
- Open source
- 7.7K GitHub stars
- Analytics and data

Google Ads + Meta Ads + SEO/GEO MCP
MCP serverHosted MCP connector for managing Google Ads, Meta Ads, GA4 and Search Console from chat
- 8 tools
- Remote
- Freemium
- 8.1K GitHub stars
- Marketing and SEO

SearXNG Search
MCP serverMCP server for web search and page reading through a SearXNG instance
Runs locally- 3 tools
- Open source
- 1.4K GitHub stars
- Web search and scraping

Tapetide - Indian Stock Market MCP
MCP serverIndian NSE and BSE stock market data for AI assistants through 48 MCP tools
- 17 tools
- Remote
- Freemium
- 150 GitHub stars
- Finance and payments