# Oxylabs MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.oxylabs%2Foxylabs-mcp
Registry id: `mcp-registry/io.oxylabs/oxylabs-mcp`
Status: live (checked 2026-10-27T02:47:28.043Z)

## Verdict

Oxylabs MCP server answered 100% of Glimind's liveness checks over 30 days, better than 42% of MCP servers, with 1138 ms median handshake and 2 outages in 90 days. Its agent-readiness grade is A (97/100) across 10 tools, costing an agent about 5,698 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 100% | 42% of MCP servers |
| Median handshake latency | 1138 ms | 16% of MCP servers |
| p95 handshake latency | 3526 ms | — |
| Checks in 30 days | 4,913 | — |
| Outages, 90 days | 2 | — |
| Median recovery | 13 min | — |
| Agent-readiness score | 97/100 (A) | 91% of MCP servers |
| Tools | 10 | — |
| Tool-list size for an agent | ~5,698 tokens | 37% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "oxylabs-mcp-server": {
      "type": "http",
      "url": "https://mcp.oxylabs.io/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http oxylabs-mcp-server https://mcp.oxylabs.io/mcp
```

## Tools (10)

- `ai_browser_agent`: Run the browser agent and return the data in the specified format. This tool is useful if you need navigate around the website and do some actions. It allows na
- `ai_crawler`: Tool useful for crawling a website from starting url and returning data in a specified format. Schema is required only if output_format is json, csv or toon. 'r
- `ai_map`: Tool useful for mapping website's URLs.
- `ai_scraper`: Scrape the contents of the web page and return the data in the specified format. Schema is required only if output_format is json or csv. 'render_javascript' is
- `ai_search`: Search the web based on a provided query. 'return_content' is used to return markdown content for each search result. If 'return_content' is set to True, you do
- `amazon_product_scraper`: Scrape Amazon products. Supports content parsing, different user agent types, domain, geolocation, locale parameters and different output formats. Supports Amaz
- `amazon_search_scraper`: Scrape Amazon search results. Supports content parsing, different user agent types, pagination, domain, geolocation, locale parameters and different output form
- `generate_schema`: Generate a json schema in openapi format.
- `google_search_scraper`: Scrape Google Search results. Supports content parsing, different user agent types, pagination, domain, geolocation, locale parameters and different output form
- `universal_scraper`: Get a content of any webpage. Supports browser rendering, parsing of certain webpages and different output formats.

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.