ScrapingBot: MCP server (Browser automation) in 2026
Public web data for AI agents: scrape any page, plus Google, TikTok, Instagram and Amazon as JSON.
Verified working on 2026-10-27 Rank 2 of 12 in Browser automation. Source: MCP Registry record, checked 2026-10-27.
Key facts
| Type | MCP server, remote (streamable HTTP) |
|---|---|
| Category | Browser automation |
| Endpoint | https://scrapingbot.io/api/mcp |
| Registry name | io.scrapingbot/scrapingbot |
| Version (registry) | 1.0.0 |
| Published in registry | 2026-10-03 |
| Registry record updated | 2026-10-03 |
| Repository | https://github.com/mike-scrapingbot/scrapingbot |
| Website | https://scrapingbot.io/mcp?utm_source=mcp_registry&utm_medium=registry&utm_campaign=server_json |
| Authentication | Custom header required: x-api-key |
| Latest check | Up on 2026-10-27, 185 ms to initialize |
| Tools listed | 23 |
| Checks passed | 1 of 1 daily checks |
| Last verified working | 2026-10-27 |
| Source | https://registry.modelcontextprotocol.io/v0/servers/io.scrapingbot%2Fscrapingbot/versions/latest (pulled 2026-10-27) |
Tools (23)
listCapabilities, scrapeWebsite, extractStructuredData, getScrapeJob, pollJobUntilDone, runBrowserScenario, googleSearch, googleReviews, instagramUser, instagramSearch, instagramMedia, instagramFollowers, tiktokVideo, tiktokUser, tiktokSearch, tiktokComments, tiktokFollowers, amazonSearch, amazonProduct, amazonProducts, amazonSuggestions, amazonRankings, providerRequest
Verification history
One probe a day: initialize, then tools/list, nothing else. Last 1 checks: 10-27 up
Install
Claude Code
claude mcp add --transport http scrapingbot https://scrapingbot.io/api/mcp --header "x-api-key: <your x-api-key>"Claude (claude.ai, Desktop) (not applicable)
Not applicable: this server needs a custom header (x-api-key) that custom connectors in claude.ai cannot send. Use Claude Code or a config file.
Cursor
{
"mcpServers": {
"scrapingbot": {
"url": "https://scrapingbot.io/api/mcp",
"headers": {
"x-api-key": "<your x-api-key>"
}
}
}
}Save as ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project).
ChatGPT (not applicable)
Not applicable: this server needs a custom header (x-api-key); ChatGPT connectors support no authentication or OAuth only.
Hermes Agent
mcp_servers:
scrapingbot:
url: "https://scrapingbot.io/api/mcp"
headers:
x-api-key: "<your x-api-key>"Add to ~/.hermes/config.yaml, then run /reload-mcp.
Other browser automation mcp servers
- browser-use Verified working on 2026-10-27 · #1 in Browser automation
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data. - Wavedash Verified working on 2026-10-27 · #3 in Browser automation
Wavedash docs and workflow guidance for building and publishing browser games. - No Niner Data Tools Verified working on 2026-10-27 · #4 in Browser automation
No-code web scraping & data-extraction Apify actors: scrape and enrich web data at scale. - SongUp AI Verified working on 2026-10-27 · #5 in Browser automation
Find AI songs in 24 languages, start a custom song on SongUp AI, and find browser audio tools. - Actionbook Reachable on 2026-10-27: sign-in required, tools not listed · #6 in Browser automation
Let your AI agent operate any website through a real, logged-in browser session.
Within a category, entries sort by (1) latest verification: verified working, then reachable but sign-in required, then failing; (2) share of daily checks that passed; (3) number of sourced facts attached to the entry; (4) median response time of passing checks; (5) name. Nothing else counts. Rankings are never for sale: sponsors and paid plans cannot change an entry's position. Markdown · JSON