Diffbot
io.github.diffbot/diffbot-mcp
Web search, page extraction, crawling, and Knowledge Graph queries from Diffbot's web index.
Connect this server
Add this to your MCP client config — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor).Suits: Claude Desktop · Cursor.
{
"mcpServers": {
"diffbot-mcp": {
"command": "uvx",
"args": [
"diffbot-mcp"
],
"env": {
"DIFFBOT_TOKEN": "<your DIFFBOT_TOKEN>"
}
}
}
}- DIFFBOT_TOKENsecretOptional. Diffbot API token. Free token: https://app.diffbot.com/get-started. DIFFBOT_API_TOKEN or ~/.diffbot/credentials also work.
A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.
- Category
- Search & Web
- Version
- 0.2.1
- Registry
- active
- Published
- 11/10/2026
On GitHub
read Nov 13, 2026- Stars
- 3
- Forks
- 2
- Last push
- Nov 11, 2026
- License
- MIT
Pythoncrawlercrawlingentity-resolutiongemini-cli-extensionknowledge-graphmcpmcp-serverweb-extractionweb-scrapingweb-searchwebfetchwebsearchwebsearch-agentwebsearch-api
From the README
Diffbot MCP Server Web knowledge fetching tools for your agent. One click adds the hosted server and signs you in with a Diffbot account, no token to paste. For the local uvx diffbot-mcp server instead: Cursor · VS Code. What is Diffbot? Diffbot is an applied AI lab building models that structure all of human knowledge. Our commercial product suite make it possible to fetch and structure knowledge at the scale of the entire public web. This is the MCP counterpart to diffbot-skills without requiring bash access. Tools Web 🧬 extract Web fetch tool alternative. Conventional fetch tools return either 500k+ tokens of HTML or a markdown approximation of the page's content. Extract classifies the page it is fetching and extracts content into a meaningful and consistent JSON schema. Responses are optimized for minimal token usage while maintaining data fidelity. Learn more.. 🔎 search_web Web search tool that ranks accuracy, not popularity. Built on Diffbot's independent web index. Ranking model heavily favors primary sources over secondary sources (e.g. press release > news piece on said press release). Returns markdown formatted content chunks for source citation, with numresults and maxtokens controls. Learn more. Also includes a page cache reader. Query url: and it returns Diffbot's already-parsed copy of that page from the index in a fraction of the time for live fetch.…
Read the full README on GitHub →Remotes
- streamable-http
https://mcp.diffbot.com/mcp
More Search & Web servers
Browse all Search & Web →
MCP x402 - Evidence-Backed Web Verification
Diogoup26
Evidence-backed pre-purchase checks for offer terms, seller trust and policy compliance.
Voyager
dir-ai
Cited, OSV-gated, injection-hardened web briefs for coding agents. Verified, never raw web.
Cogfall
Disseveru
On-demand human cognitive fallback & CAPTCHA solver for AI agents with x402 micropayments.
Groundhog
dmytrome
Search, read and research the web, with hidden text stripped by default and sources hashed
Dns Aid
dns-aid
Discover and publish AI agents via DNS using SVCB records (RFC 9460)
DoboCache
dobo123123
Local proxy + MCP server: keeps LLM prompt-cache prefixes stable so caching hits.
Add the badge to your site
Show visitors that Diffbot is listed here — it’s also the link we check for a free listing.
HTML — for your website
<a href="https://serverdex.io/server/io-github-diffbot-diffbot-mcp?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="Diffbot — listed on Serverdex" width="123" height="40" loading="lazy"></a>Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.
Markdown — for your README
[](https://serverdex.io/server/io-github-diffbot-diffbot-mcp?utm_source=badge)Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.