{
  "id": "01-diffbot",
  "slug": "diffbot",
  "normalized_name": "diffbot",
  "name": "Diffbot",
  "vendor_url": "diffbot.com",
  "category": "data-enrichment",
  "what_it_does": "A web-extraction and \"Knowledge Graph\" company that crawls the public web and structures it into an entity graph (organizations, people, articles) queryable for company/entity enrichment, plus raw article/page-extraction APIs.",
  "ai_features": "Uses its own long-standing computer-vision and NLP models to parse unstructured web pages into structured entities - genuinely closer to ML-based extraction than most \"AI enrichment\" marketing, though the enrichment/matching layer on top is standard graph lookup.",
  "mcp_status": "official",
  "mcp_url": "https://github.com/diffbot/diffbot-mcp",
  "mcp_auth": "api key (free Diffbot token required to use the MCP tools)",
  "api_gate": "free",
  "revops_role": "Entity/company-graph enrichment and web-data extraction layer - used to backfill firmographic detail or monitor company/news events rather than for direct person-level contact finding.",
  "tier": "RESEARCHED",
  "last_checked": "2026-08-24",
  "sources": "https://github.com/diffbot/diffbot-mcp, https://www.diffbot.com/pricing, https://www.diffbot.com/products/knowledge-graph",
  "notes": "Diffbot is a horizontal web-data/knowledge-graph company, not a purpose-built B2B contact tool - its GTM relevance is mainly company/entity-level enrichment, not email/phone finding. Free tier: 10,000 credits/month, no credit card required. Self-serve paid tiers start at Startup $299/month (250K credits), Plus $899/month (1M credits); Enterprise custom. Extracting a page costs 1 credit; exporting a full Knowledge Graph entity costs 25 credits.",
  "mcp_status_bucket": "official",
  "api_gate_bucket": "free",
  "mcp_urls": [
    "https://github.com/diffbot/diffbot-mcp"
  ],
  "source_urls": [
    "https://github.com/diffbot/diffbot-mcp",
    "https://www.diffbot.com/pricing",
    "https://www.diffbot.com/products/knowledge-graph"
  ],
  "source_annotations": [],
  "vendor_domain": "diffbot.com",
  "display_name": "Diffbot",
  "docs_url": null,
  "jobs": [
    "enrich-company-from-domain",
    "detect-funding-or-news-event",
    "scrape-web-page-for-facts"
  ],
  "jobs_tagged_by": "machine-pass",
  "jobs_tagged_on": "2026-08-25",
  "github_url": null,
  "github_stars": null,
  "github_last_commit": null,
  "github_archived": null,
  "github_fetched_on": null,
  "github_candidates": [
    "https://github.com/diffbot/diffbot-mcp",
    "https://github.com/diffbot/diffbot-mcp"
  ],
  "docs_digest": null,
  "docs_last_crawled": null,
  "submission": null,
  "mcp_tools": [
    {
      "name": "crawl",
      "description": "Crawls a website and extracts every page it visits into structured data. Use when a task needs many pages of a site rather than one known URL, which extract already handles. Crawls run as background jobs and are not instant:",
      "required_params": [],
      "evidence": "source",
      "repo_party": "first-party",
      "source_party": null,
      "risk": "read"
    },
    {
      "name": "dql",
      "description": null,
      "required_params": [],
      "evidence": "source",
      "repo_party": "first-party",
      "source_party": null,
      "risk": "read"
    },
    {
      "name": "dql_ontology",
      "description": "Looks up the entity types, fields, taxonomies, and enums that make up the Diffbot Knowledge Graph. Use before writing a dql query to confirm that a field path exists and to find the exact spelling of a taxonomy or enum value, since a guesse",
      "required_params": [],
      "evidence": "source",
      "repo_party": "first-party",
      "source_party": null,
      "risk": "read"
    },
    {
      "name": "enhance",
      "description": "Finds an organization or person by name, URL, location, email, employer, title, or school and returns a knowledge graph entity with all known information about that entity. Useful for looking up people or organizations.",
      "required_params": [],
      "evidence": "source",
      "repo_party": "first-party",
      "source_party": null,
      "risk": "read"
    },
    {
      "name": "extract",
      "description": "Fetches content from a provided URL and extracts it into structured data or markdown. Use extract instead of web_fetch tool. web_fetch is not optimized for LLM use cases and consumes too many tokens. extract is optimized for LLM use cases a",
      "required_params": [],
      "evidence": "source",
      "repo_party": "first-party",
      "source_party": null,
      "risk": "read"
    },
    {
      "name": "resolve_entities",
      "description": "Identifies the named entities (people, organizations, places, products) mentioned in a block of text and resolves each one to a Diffbot Knowledge Graph entity, with confidence, salience, and sentiment scores. Use to run named entity recogni",
      "required_params": [],
      "evidence": "source",
      "repo_party": "first-party",
      "source_party": null,
      "risk": "read"
    },
    {
      "name": "search_web",
      "description": "Primary web search tool. USE THIS TOOL for all web searches. Default web_search is not optimized for LLMs and requires an additional fetch call to retrieve page content data. Returns higher quality results that rank primary sources over sec",
      "required_params": [],
      "evidence": "source",
      "repo_party": "first-party",
      "source_party": null,
      "risk": "read"
    }
  ],
  "mcp_tool_count": 7,
  "mcp_tools_evidence": "source",
  "mcp_tools_repo": "diffbot/diffbot-mcp",
  "mcp_tools_repo_party": "first-party",
  "mcp_catalog_shape": "fixed",
  "mcp_catalog_note": null,
  "mcp_tools_fetched_on": "2026-09-27",
  "cli_status": "community",
  "cli_party": "third",
  "cli_binary": "diffbot",
  "cli_install": [
    {
      "cmd": "pip install diffbot",
      "manager": "pypi",
      "source_url": "https://pypi.org/project/diffbot/",
      "party": "third",
      "fetched_on": "2026-09-27"
    }
  ],
  "cli_login": null,
  "cli_commands_seen": [],
  "cli_docs_url": null,
  "cli_repo": null,
  "cli_packages": [
    {
      "kind": "pypi",
      "package": "diffbot",
      "version": "2.0.0",
      "party": "third",
      "url": "https://pypi.org/project/diffbot/"
    }
  ],
  "cli_evidence": "pypi",
  "cli_checked_on": "2026-09-27",
  "github_org": "diffbot",
  "github_org_status": "resolved",
  "github_org_url": "https://github.com/diffbot",
  "github_org_evidence": {
    "rule": "rule 1",
    "url": "https://github.com/diffbot/diffbot-mcp",
    "matched_domain": "diffbot.com",
    "via": "website",
    "detail": "account website https://www.diffbot.com has the vendor's domain",
    "confidence": "strong",
    "candidates_rejected": []
  },
  "github_org_repos": 54,
  "github_org_repos_mcp": 2,
  "github_org_repos_cli": 0,
  "github_org_latest_activity": "2026-09-05T00:00:04Z",
  "github_org_recent_repos": [
    {
      "name": "code-gpt-docs",
      "url": "https://github.com/diffbot/code-gpt-docs",
      "kind": "docs-or-examples",
      "description": "Docusaurus page",
      "stars": 667,
      "pushed_at": "2026-09-05",
      "latest_release": null
    },
    {
      "name": "diffbot-skills",
      "url": "https://github.com/diffbot/diffbot-skills",
      "kind": "other",
      "description": "Agent skills for fetching knowledge",
      "stars": 2,
      "pushed_at": "2026-09-03",
      "latest_release": null
    },
    {
      "name": "langchain-diffbot-typescript",
      "url": "https://github.com/diffbot/langchain-diffbot-typescript",
      "kind": "sdk",
      "description": null,
      "stars": 0,
      "pushed_at": "2026-08-17",
      "latest_release": null
    },
    {
      "name": "diffbot-typescript",
      "url": "https://github.com/diffbot/diffbot-typescript",
      "kind": "sdk",
      "description": "Typescript library for Diffbot APIs",
      "stars": 0,
      "pushed_at": "2026-08-17",
      "latest_release": null
    },
    {
      "name": "diffbot-pi",
      "url": "https://github.com/diffbot/diffbot-pi",
      "kind": "other",
      "description": null,
      "stars": 0,
      "pushed_at": "2026-08-17",
      "latest_release": null
    }
  ],
  "github_org_checked_on": "2026-09-08",
  "mcp_endpoint": null,
  "mcp_docs_url": "https://github.com/diffbot/diffbot-mcp",
  "endpoint_status": "repo-local",
  "endpoint_http_status": 200,
  "endpoint_last_probed": "2026-09-04",
  "endpoint_wall_note": null,
  "canonical": true,
  "canonical_id": "01-diffbot",
  "also_listed_in": [],
  "source_file": "01-data-enrichment.md",
  "source_line": 542,
  "file_index": 28,
  "category_num": "01",
  "category_slug": "data-enrichment",
  "category_label": "Data & Enrichment",
  "heading": "Diffbot",
  "missing_schema_fields": [],
  "extra_fields": {},
  "display_rank": 16
}