Diffbot

The vendor ships and maintains the server itself. A wrapper built by Zapier, Composio or a similar third party does not count as official. The status was established by hand on 2026-08-24. On 2026-09-04 the recorded URL was a reachable repository or package: a server you install and run on your own machine over stdio. Callable after an install, not a remote endpoint.

mcp_status, verbatim from the file:

official

mcp_url, verbatim from the file:

https://github.com/diffbot/diffbot-mcp

• https://github.com/diffbot/diffbot-mcp

A tool below is one the server NAMES. Nobody has called it. That is the same two tier honesty rule the rest of the directory runs on: a named tool is research, and BENCH-TESTED stays the only claim that anybody ran anything.

• crawl
  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:
  evidence: in the server source · calling it reads
• dql
  No description was recorded with the name.
  evidence: in the server source · calling it reads
• dql_ontology
  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
  evidence: in the server source · calling it reads
• enhance
  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.
  evidence: in the server source · calling it reads
• extract
  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
  evidence: in the server source · calling it reads
• resolve_entities
  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
  evidence: in the server source · calling it reads
• search_web
  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
  evidence: in the server source · calling it reads

141 of the 741 entries that record an official or community MCP server carry a harvested tool list. The other 600 are unmeasured, which is not the same as empty. Harvest last run 2026-09-27. Every name across every server is on the tools index.

This is a third party's CLI. It was published by somebody other than the vendor, so it is that author's surface for the vendor's API and not the vendor's published surface. The two must not be read as the same thing.

Install, as the source shows it:

pip install diffbot

quoted from https://pypi.org/project/diffbot/ on 2026-09-27, via pypi, a third party source

Packages seen, with the version on 2026-09-27:

• pypi: diffbot 2.0.0, third party

A CLI being listed means the harvest found an install command or a package on a stated date. Nobody has run it. Every command is quoted verbatim from the URL beneath it. Harvest date 2026-09-27.

api_gate, verbatim from the file:

free

No documentation URL recorded.

727 of 1252 entries are in the same position. Blank is legal and it is published as blank.

Not measured. github_url, github_stars, github_last_commit and github_archived are null on every entry in this build.

The refresh rail specced in SPEC section 7.2 has not been run. An unstamped star count is a lie, so nothing is shown rather than something stale.

A github.com URL already appears somewhere in this entry, which is a seed for that rail and not a measurement of repo health:

• https://github.com/diffbot/diffbot-mcp

github.com/diffbot tied to the vendor by rule 1, account website https://www.diffbot.com has the vendor's domain, confidence strong

The five most recently pushed, on 2026-09-08:

Kind is a heuristic guessed from the repository name, topics and description, not a fact the vendor stated. A repository count is activity, not a verdict. Read 2026-09-08.

• Enrich a company from a domain
• Detect a funding or news event
• Scrape a web page for facts

A job tag means the vendor says the tool does this. It is not a test result, not proof the capability is reachable through the tool's MCP server, and not proof it is available on the gate this entry records.

Tagged by machine-pass on 2026-08-25 against the closed 56 job vocabulary. 271 of 1,252 entries carry at least one tag; 849 tags are assigned in total.

• https://github.com/diffbot/diffbot-mcp
• https://www.diffbot.com/pricing
• https://www.diffbot.com/products/knowledge-graph

3 source URLs. Raw sources field, verbatim:

https://github.com/diffbot/diffbot-mcp, https://www.diffbot.com/pricing, https://www.diffbot.com/products/knowledge-graph

Every field above is rendered from directory.json exactly as the build produced it. Nothing is summarised and nothing is dropped. The one change made at render time is typographic and it is disclosed on the methodology page.