MartechDB
MartechDB
Toggle sidebar

Diffbot MCP server

diffbot.com

Yes. Diffbot publishes an official MCP server at https://mcp.diffbot.com/mcp. It's hosted. It offers 12 tools. We last checked it on 22 Nov 2026.

Official MCP server
Hosted
Sign-in: see vendor docs

Official: answers MCP requests at mcp.diffbot.com, on Diffbot's own domain diffbot.com. Checked 22 Nov 2026. Maintained by Stuart Brameld.

Key facts

As of 22 Nov 2026, Diffbot's official MCP server scores 69/100 (provisional) on MartechDB's Agent Readiness Index (v1.1). It answered 56 of our 56 checks in the last 90 days and lists 12 tools.

How the Agent Readiness Index works · Wrong? Suggest a correction

Diffbot MCP server review

69/100

Diffbot's MCP server scores 69/100 on MartechDB's Agent Readiness Index: easy to connect an AI agent to, with a few gaps.

The good

  • Hosted by Diffbot: connect by URL, with nothing to install

  • Documented, with 12 tools known

  • Published to the official MCP Registry

  • Answered 100% of our checks in the last 90 days

  • Free plan or free quota

The bad

  • Nothing we've found.

Not checked yet: how you sign in. Anything not checked scores nothing.

Official MCP server

Diffbot MCP server

Address
https://mcp.diffbot.com/mcp
Runs
Hosted
Sign-in
Sign-in: see vendor docs
Vendor docs
Cost to use
Free to start
Official MCP Registry
Listed as io.github.diffbot/diffbot-mcp · published 10 Nov 2026
How we know it's official
  • Answers MCP requests at mcp.diffbot.com, on Diffbot's own domain diffbot.com.
Checked 22 Nov 2026.
Tools
12 tools · listed 19 Oct 2026
First seen
1 Oct 2026
Last checked
Reachable ·
16 Nov 2026: reachable
17 Nov 2026: reachable
18 Nov 2026: reachable
19 Nov 2026: reachable
20 Nov 2026: reachable
21 Nov 2026: reachable
22 Nov 2026: reachable
Uptime
100% · 56 of 56 checks reachable since 1 Oct 2026

Diffbot MCP server tools (12)

As the server lists them. Names and descriptions are the vendor's own.

  • extract Extract

    Fetches a URL live and extracts it into markdown or structured JSON, classifying the page type. Use when a search_web 'url:<URL>' lookup misses, when the page's current state (prices, status, versions) is the question, or when the typed JSON record is needed. Takes 1-10 seconds.

  • crawl Crawl

    Crawls a website from a seed URL and extracts every page into structured data, for tasks that need many pages of a site rather than one known URL (that is extract). Crawls are background jobs: 'start' returns a job name, poll 'status' until is_running is false, then read 'results' or 'urls'; 'list' and 'delete' manage jobs.

  • search_deals Search Deals

    Funding rounds, investments, and acquisitions in the Diffbot Knowledge Graph by company, investor, acquirer, round series, amount, date, or the company's industry. Rows are deals (target, counterparty, amount, currency, date), not companies: deal flow, a company's funding history, an investor's activity, the largest acquisitions of a year. Returns rows plus the DQL it ran.

  • dql Dql

    Runs a DQL query against the Diffbot Knowledge Graph for any entity type or shape the typed tools (search_organizations, search_people, search_news, search_deals, search_places) do not cover: products, patents, job posts, facets, cross-entity queries, or an id filter from resolve_entities. Each typed tool returns the DQL it ran, which can be refined here. Rules: conditions on one nested list object go inside one {} (employments.{employer.name:X isCurrent:true}); confirm field paths and taxonomy spellings with dql_ontology since an unknown path is silently ignored; probe variants with dql_probe before pulling rows; do not add a sort unless ordering is the question (articles excepted: sortBy:date). For a CSV file, do not page rows: GET https://kg.diffbot.com/kg/v3/dql?token=..&format=csv&size=<hits>&exportspec=<fields>&query=<DQL> straight to disk.

  • dql_ontology Dql Ontology

    Looks up the Knowledge Graph ontology: entity types, their fields, and taxonomy or enum values. Use before raw dql to confirm a field path exists and to get the exact spelling of a value (a guessed path is silently ignored, a guessed value returns zero). Results are ranked best match first.

  • dql_probe Dql Probe

    Hit counts for several DQL queries at once, to compare variants before pulling rows (co-constrained {} vs loose, category vs descriptors). Zero hits means a wrong value (check dql_ontology); a count equal to the bare type:X count means a field path was ignored. similarTo cannot be probed; never probe an unfiltered type:Article.

  • search_news Search News

    News and articles in the Diffbot Knowledge Graph by mentioned entity, topic, publisher, language, date range, or sentiment; dated, sourced, linkable rows, newest first. Use for all news including breaking stories (search_web is wrong for news). mentions is the strongest filter; if it returns nothing retry the words as text. Returns rows plus the DQL it ran.

  • search_organizations Search Organizations

    Companies in the Diffbot Knowledge Graph by industry, location, headcount, revenue, founding date, founder, investor, acquirer, or lookalikes of a named company. Use when the answer is a list of companies or one company's record (not deals or people). Returns rows plus the DQL it ran.

  • search_people Search People

    People in the Diffbot Knowledge Graph by job title, employer, employer industry or size, job category or location, school, major, skills, language, residence, nationality, or gender; leadership_of answers who runs a named company. Use when the answer is a list of people or one person's record (not companies). Covers people with a public professional presence only, so an empty result means undocumented, not nonexistent. Returns rows plus the DQL it ran.

  • search_places Search Places

    Cities, counties, states, provinces, countries, and points of interest in the Diffbot Knowledge Graph by name, population, containing place, or proximity. Use when the answer is a list of places or a sourced fact about one such as population. Set kind to the narrowest type that fits. Returns rows plus the DQL it ran.

  • resolve_entities Resolve Entities

    Finds the people, organizations, places, and products mentioned in text and resolves each to a Knowledge Graph entity with confidence, salience, and sentiment. The response includes dql_filter, an id:or(...) clause for dql to fetch the full records. Entities without an id were recognized but not matched.

  • search_web Search Web

    Web search over Diffbot's index: ranked results with relevance scores, publication dates, and the matching chunks of each page, so one call usually answers with a citable source. Also a page cache reader: 'url:<URL>' alone returns the full stored page, 'url:<URL> <what you need>' returns only its matching chunks; both take ~300ms (one result on a hit, zero on a miss) and work on pages that block fetchers. Use extract when the lookup misses or the page's current state is the question. Not for news (search_news).

Connect your AI to Diffbot

Add the official Diffbot MCP server to Claude, ChatGPT or your editor.

Connect Diffbot MCP to Claude

Claude.ai and Claude Desktop

  1. Open Customize, then Connectors.

  2. Click +, then Add custom connector.

  3. Name it Diffbot, paste the address below and click Add.

Claude Code

Diffbot MCP server questions

Does Diffbot have an official MCP server?

Yes. Diffbot publishes its MCP server itself. Its address is on Diffbot's own domain (mcp.diffbot.com). MartechDB only lists servers a vendor publishes, never community copies.

What is the Diffbot MCP server URL?

The address is https://mcp.diffbot.com/mcp.

How do I connect Diffbot MCP to Claude, ChatGPT or Cursor?

In Claude, add https://mcp.diffbot.com/mcp as a custom connector (Customize, Connectors, Add custom connector). In Cursor, use the Add to Cursor link on MartechDB's page, or paste the JSON settings into your mcp.json. In Claude Code, run: claude mcp add --transport http diffbot https://mcp.diffbot.com/mcp

What can the Diffbot MCP server do?

It offers 12 tools, including extract, crawl, search_deals, dql and dql_ontology (as listed on 19 Oct 2026).

Is the Diffbot MCP server in the official MCP Registry?

Yes, as io.github.diffbot/diffbot-mcp.

Is the Diffbot MCP server free to use?

Yes, on a free plan or free quota. From Diffbot's own pages, checked on 7 Oct 2026.

Is the Diffbot MCP server working?

Yes. It answered our most recent check. We last checked it on 22 Nov 2026.

What are the alternatives to Diffbot's MCP server?

In Data integration, the most agent-friendly alternatives with an official MCP server are Needle (97/100), Supermetrics (97/100), Activepieces (97/100), IFTTT (92/100) and import.io (92/100). Diffbot scores 69/100 on the same index.

Alternatives to Diffbot's MCP server

Vendors in Data integration with an official MCP server, the most agent-friendly first. Diffbot scores 69/100.

Compare all 52 Data integration vendors →

Change history

What we've seen change for Diffbot, newest first.

  1. Diffbot: Diffbot MCP server added to the official MCP Registry

  2. Diffbot: Diffbot MCP server: 6 tools added, 1 removed (now 12)

Use with AI

Connect your AI to MartechDB

Then ask it about Diffbot, or any of the 1,850 marketing tools with an official MCP server. Free, no sign-in.

Claude.ai and Claude Desktop

  1. Open Customize, then Connectors.

  2. Click +, then Add custom connector.

  3. Name it MartechDB, paste the address below and click Add. There's no sign-in.

The free plan allows one custom connector. On Team and Enterprise plans, an owner adds the connector first.

Show that your MCP server is verified

If you work at Diffbot, add this badge to your MCP docs or README. It's free, it's the same for every vendor, and it updates from our daily checks: it shows uptime while the server responds, and says so if it stops.

Official MCP server, verified by MartechDB
HTML
Markdown

Something wrong or out of date? Suggest a correction or email us, and we'll check it against the evidence. Every correction we make is listed on Corrections.