Diffbot
Web search, page extraction, crawling, and Knowledge Graph queries from Diffbot's web index.
- GitHub stars
- 3
- tools
- 12
- auth
- Secret needed
- transport
- STDIO, HTTP
- env var
- 1
- last updated
- Nov 10, 2026
Tools
12 toolsPublic tool metadata for what this MCP can expose to an agent.
extractWeb fetch tool alternative that classifies the page it fetches and extracts its content into a consistent JSON schema.
Web fetch tool alternative that classifies the page it fetches and extracts its content into a consistent JSON schema.
No parameter schema in public metadata yet.
search_webWeb search tool built on Diffbot's independent web index that ranks by accuracy, returning markdown content chunks for source citation.
Web search tool built on Diffbot's independent web index that ranks by accuracy, returning markdown content chunks for source citation.
No parameter schema in public metadata yet.
crawlFinds all links on a web page (the seed) and extracts them all as background jobs that can be polled for status.
Finds all links on a web page (the seed) and extracts them all as background jobs that can be polled for status.
No parameter schema in public metadata yet.
resolve_entitiesRecognizes and resolves entities in text using Diffbot NLP, returning entity IDs and a ready-made dql_filter.
Recognizes and resolves entities in text using Diffbot NLP, returning entity IDs and a ready-made dql_filter.
No parameter schema in public metadata yet.
search_newsNews and articles by mentioned entity, topic, publisher, language, date range, or sentiment.
News and articles by mentioned entity, topic, publisher, language, date range, or sentiment.
No parameter schema in public metadata yet.
search_organizationsCompanies by industry, headquarters, headcount, revenue, funding, ownership, or leadership, plus similar_to lookalike lists.
Companies by industry, headquarters, headcount, revenue, funding, ownership, or leadership, plus similar_to lookalike lists.
No parameter schema in public metadata yet.
search_peoplePeople by title, employer, employer industry, skills, education, location, or nationality.
People by title, employer, employer industry, skills, education, location, or nationality.
No parameter schema in public metadata yet.
search_placesCities, counties, states, countries, and points of interest by name, population, prominence, containing place, or proximity.
Cities, counties, states, countries, and points of interest by name, population, prominence, containing place, or proximity.
No parameter schema in public metadata yet.
search_dealsFunding rounds, investments, and acquisitions by date, size, series, investor, acquirer, or industry.
Funding rounds, investments, and acquisitions by date, size, series, investor, acquirer, or industry.
No parameter schema in public metadata yet.
dqlRaw querying of the Diffbot Knowledge Graph for any entity type or query shape the other tools do not cover.
Raw querying of the Diffbot Knowledge Graph for any entity type or query shape the other tools do not cover.
No parameter schema in public metadata yet.
dql_probeParallel hit counts for several candidate queries, to check that a query is neither too broad nor too narrow.
Parallel hit counts for several candidate queries, to check that a query is neither too broad nor too narrow.
No parameter schema in public metadata yet.
dql_ontologyHelper utility for accurate dql ontology navigation covering entity types, fields, taxonomies, and enums.
Helper utility for accurate dql ontology navigation covering entity types, fields, taxonomies, and enums.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
DIFFBOT_TOKENsecretOptional. Diffbot API token. Free token: https://app.diffbot.com/get-started. DIFFBOT_API_TOKEN or ~/.diffbot/credentials also work.
Readme
Details
- Repository
- github.com/diffbot/diffbot-mcp
- Website
- www.diffbot.com
- Categories
- Documents & Knowledge, Search & Web Crawling
- Package
diffbot-mcp- Transport
- STDIO, HTTP
- Auth
- Required
- Registry
- MCP registry, active
Related Documents & Knowledge MCP servers
View all
Skim402jessiejanie/skim402Clean markdown and structured web data. Free card API key; wallet/x402 pay-per-call optional.3stars
Anybrowsekc23go/anybrowseConverts any URL to clean, LLM-ready Markdown using real Chrome browsers3stars
mnemethegoatpsy/mnemeVault-native, accountable memory for Claude Code and MCP clients. Markdown is ground truth.3stars
Atlassian Extendedvish288/mcp-atlassian-extendedJira/Confluence MCP server (MCP 2026-07-28): sprints, boards, attachments; writes or read-only3stars
Slideshot06ketan/slideshotConvert HTML to PDF/PNG/WebP/PPTX slide carousels with 11 themes — for LinkedIn, decks, posts.2stars
Mcp Pickaxeaplaceforallmystuff/mcp-pickaxeMCP server for Pickaxe API - manage AI agents, knowledge bases, users, and analytics2stars