io.github.pipeworx-io/oxylabs is an MCP server that oxylabs MCP — Oxylabs Web Scraper API (oxylabs.io). Its tool list has not been published yet over http, requires no API key, and scores 58/100 on MCPpedia's security, maintenance and efficiency rubric.
Config is the same across clients - only the file and path differ.
{
"mcpServers": {
"oxylabs": {
"url": "https://gateway.pipeworx.io/oxylabs/mcp"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Oxylabs MCP — Oxylabs Web Scraper API (oxylabs.io)
This server supports HTTP transport. Be the first to test it - help the community know if it works.
Five weighted categories - click any category to see the underlying evidence.
No known CVEs.
Checked @pipeworx/mcp-oxylabs against OSV.dev.
Be the first to review
Have you used this server?
Share your experience - it helps other developers decide.
Sign in to write a review.
Others in browser
Open-source web scraper for AI agents with scrape, crawl, and map tools
Search-first MCP server for JavaScript reverse engineering: 735 tools across 36 domains.
Extract data from any website with thousands of scrapers, crawlers, and automations on Apify Store ⚡
Firecrawl, the context API for AI agents: search, scrape, interact with the web, plus paper search.
MCP Security Weekly
Get CVE alerts and security updates for io.github.pipeworx-io/oxylabs and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
Oxylabs MCP — Oxylabs Web Scraper API (oxylabs.io)
Part of Pipeworx — an MCP gateway connecting AI agents to 1867+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.
| Tool | Description |
|---|---|
oxylabs_scrape | Scrape any URL via the Oxylabs Web Scraper API (rotating proxies, anti-bot handling) and return the page HTML with its upstream status code. Set render_js:true to load the page in a headless browser first — use for JS-heavy sites. Calls are synchronous proxying and can take 10-30 seconds. BYOK: _apiKey is "username:password" from the Oxylabs dashboard. Example: oxylabs_scrape({ url: "https://example.com", _apiKey: "myuser:mypass" }) |
oxylabs_google_search | Run a Google search through the Oxylabs Web Scraper API and return structured organic results (position, title, url, description) — Google structured scraping with geo-targeting. Calls are synchronous proxying and can take 10-30 seconds. BYOK: _apiKey is "username:password" from the Oxylabs dashboard. Example: oxylabs_google_search({ query: "best espresso machine", geo_location: "United States", _apiKey: "myuser:mypass" }) |
oxylabs_amazon_product | Fetch structured Amazon product data by ASIN via the Oxylabs Web Scraper API — Amazon structured scraping: title, price, currency, rating, reviews count, stock/availability. Calls are synchronous proxying and can take 10-30 seconds. BYOK: _apiKey is "username:password" from the Oxylabs dashboard. Example: oxylabs_amazon_product({ asin: "B08N5WRWNW", domain: "com", _apiKey: "myuser:mypass" }) |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"oxylabs": {
"url": "https://gateway.pipeworx.io/oxylabs/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/oxylabs/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1867+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
This pack takes your own API key (_apiKey) — we don't front one for it, so there's no curl here that would run without it. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/oxylabs_scrape. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
@pipeworx/mcp-oxylabs is a local stdio bridge to the Pipeworx gateway: your MCP client
starts it with npx, and it forwards every call to the same
https://gateway.pipeworx.io/oxylabs/mcp endpoint shown above. It needs network access;
there is no offline mode.
{
"mcpServers": {
"oxylabs": {
"command": "npx",
"args": ["-y"
... [View full README on GitHub](https://github.com/pipeworx-io/mcp-oxylabs#readme)