← Back to directory

Oxylabs MCP Server

Official

Archived

The missing link between AI models and the real-world web: one API that delivers clean, structured data from any site.

How to install ↓ Compare GitHub source repository ↗

Category: Other
Stars: ★ 104 Popular
Transport: stdio (local process)
Runtime: Python · Hosted (no local runtime)
Credentials: API key / credential required
License: MIT
Last commit: 34 days ago
Tools: 8

59FMRS · C

Oxylabs MCP Server offers powerful scraping and AI data extraction capabilities, suitable for developers needing efficient web data access. Strengths include support for many target sites, automatic JavaScript rendering, built-in CAPTCHA management, and AI-driven tools. Beware of credential configuration and costs.

Strongest · Maintenance 14/20 Weakest · Reliability 8/20

Reliability

8/20

Security and permissions

13/20

Maintenance

14/20

Documentation

13/20

Setup experience

11/20

Why each score

Reliability 8/20: The server manifest indicates stdio transport but lacks explicit command arguments (e.g., uvx or python), threatening reproducible startup. Environment variables are marked as not required in the manifest, but the README warns that exposed tools won't work without corresponding credentials, suggesting poor error handling. No tests or CI workflows (e.g., GitHub Actions) are provided; no commit history. Thus the reliability score is capped at 8.
Security and permissions 13/20: Credential handling is secure: environment variables are marked as secret, and no real tokens are in the example configs. However, external network access is expected (calling Oxylabs API), but no mention of data retention or third-party processing. Tools perform remote operations (scraping), but that is core functionality, not overreach. No obvious red flags, but data boundaries and confirmation mechanisms are not fully disclosed, so capped at 13.
Maintenance 14/20: The repository shows 101 stars, only 1 open issue, and is not archived. MIT license present, version 0.7.2 suggests active releases. But no detailed information on commit frequency or release cadence, and no security response channel. These governance gaps cap the score at 14.
Documentation 13/20: README covers configuration (uvx, uv, Smithery), environment variables, tool list, and logging. However, it lacks detailed tool parameter descriptions, rate limits, pricing, and troubleshooting guide. The warning about credentials is important, but overall depth is insufficient. Hence 13.
Setup experience 11/20: Install steps are provided via uvx and uv, with client config examples (Claude Desktop, Cursor). But the config examples for main clients use placeholders rather than actual values, and the user needs accounts. Multiple setup paths may confuse, and no runtime validation is given. Thus capped at 11.

Static review · not runListed 2026-08-07

Read the FMRS scoring method →

Fit and risk

What it can accessUses the networkControls a browser

Best for

Developers and data scientists needing to extract structured data from websites
Building AI-powered web content analysis tools
Scenarios requiring CAPTCHA and geo-restriction bypass

Not for

Users without an Oxylabs account or credentials
Those needing to handle extremely complex or heavily anti-scraped sites (may require professional support)
Cost-sensitive users who need unlimited free usage

Required permissions

Requires network access to call Oxylabs APIs
Credentials stored in environment variables (OXYLABS_USERNAME, OXYLABS_PASSWORD, OXYLABS_AI_STUDIO_API_KEY)

Risks and side effects

Credential leakage risk: avoid hardcoding or committing credentials to public repositories
API keys may be misused; rotate them regularly
Scraping may violate website terms of service; assess compliance yourself
Dependency on external API; failures may occur due to network or service issues

Setup

Before you start

Runtime：Python · Hosted (no local runtime)

OXYLABS_USERNAME optionalsecret Oxylabs Web Scraper API username from dashboard.oxylabs.io (1-week free trial available).

OXYLABS_PASSWORD optionalsecret Oxylabs Web Scraper API password, paired with the username.

OXYLABS_AI_STUDIO_API_KEY optionalsecret Oxylabs AI Studio API key from aistudio.oxylabs.io/settings/api-key (1000 free credits).

Other optional settings (1)

LOG_LEVEL optional Optional log level for logs returned to the client, defaults to INFO.

Install the uv package manager: macOS/Linux: curl -LsSf https://astral.sh/uv/install.sh | sh; Windows: powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex".
Add the following JSON configuration to your MCP client config: {"mcpServers":{"oxylabs":{"command":"uvx","args":["oxylabs-mcp"],"env":{"OXYLABS_USERNAME":"YOUR_USERNAME","OXYLABS_PASSWORD":"YOUR_PASSWORD","OXYLABS_AI_STUDIO_API_KEY":"YOUR_API_KEY"}}}}.
Ensure you provide at least one set of valid credentials: either OXYLABS_USERNAME and OXYLABS_PASSWORD for the Web Scraper API, or OXYLABS_AI_STUDIO_API_KEY for AI Studio.

claude_desktop_config.json

{
  "mcpServers": {
    "oxylabs": {
      "command": "uvx",
      "args": ["oxylabs-mcp"],
      "env": {
        "OXYLABS_USERNAME": "YOUR_USERNAME",
        "OXYLABS_PASSWORD": "YOUR_PASSWORD",
        "OXYLABS_AI_STUDIO_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.

.vscode/mcp.json

{
  "servers": {
    "oxylabs": {
      "command": "uvx",
      "args": [
        "oxylabs-mcp"
      ],
      "env": {
        "OXYLABS_USERNAME": "YOUR_USERNAME",
        "OXYLABS_PASSWORD": "YOUR_PASSWORD",
        "OXYLABS_AI_STUDIO_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).

Terminal

claude mcp add oxylabs -e OXYLABS_USERNAME=YOUR_USERNAME -e OXYLABS_PASSWORD=YOUR_PASSWORD -e OXYLABS_AI_STUDIO_API_KEY=YOUR_API_KEY -- uvx oxylabs-mcp

Run it in a terminal; replace any <…> placeholders with your own values first.

Generate and validate client config

Check that it works

Check that tools like universal_scraper or ai_search appear in your client's tool list, then ask it to scrape https://ip.oxylabs.io — returned page content confirms the setup. Note: leaving placeholder credentials exposes tools that do not work; delete unused env var placeholders.

Troubleshooting

1. Confirm environment variables are set correctly and no placeholder values remain (placeholders will expose tools that do not work).
2. Check network connectivity to ensure access to Oxylabs APIs.
3. Inspect logs in notification/message events, e.g., 'Create job' and 'Job info', to diagnose issues.
4. If tools are missing, verify the correct credential combination: only Web Scraper credentials expose the first four tools, only AI Studio key exposes the last four, and both expose all tools.

Things to try

Once connected, you can ask your AI assistant things like:

Scrape the page at https://ip.oxylabs.io with universal_scraper and show me the content
Search Google for the latest news about the MCP protocol and summarize the results
Extract price and reviews from an Amazon product page
Use ai_crawler to crawl multiple pages of a website based on my prompt and return Markdown

Tools 8

universal_scraper read-only

Uses Oxylabs Web Scraper API for general website scraping.

google_search_scraper read-only

Uses Oxylabs Web Scraper API to extract results from Google Search.

amazon_search_scraper read-only

Uses Oxylabs Web Scraper API to scrape Amazon search result pages.

amazon_product_scraper read-only

Uses Oxylabs Web Scraper API to extract data from individual Amazon product pages.

ai_scraper read-only

Scrape content from any URL in JSON or Markdown format with AI-powered data extraction.

ai_crawler read-only

Based on a prompt, crawls a website and collects data in Markdown or JSON format across multiple pages.

ai_browser_agent read-only

Based on prompt, controls a browser and returns data in Markdown, JSON, HTML, or screenshot formats.

ai_search read-only

Search the web for URLs and their contents with AI-powered content extraction.

Use cases

Scrape dynamic websites and extract data for AI analysis

Obtain search results from Google, Amazon, and other targets

Automate browser operations via AI agents

Collect structured data from web pages for LLM training or content generation

Supported clients

Claude Desktop

Listed from the project's documentation, not tested by this site.

Overview

The Oxylabs MCP server provides a bridge between AI models and the web. It enables them to scrape any URL, render JavaScript-heavy pages, extract and format content for AI use, manage CAPTCHA, and access geo-restricted web data from 195+ countries.

Similar servers

DuckDuckGo Search MCP Server 74 · B

MCP server providing web search and content fetching via DuckDuckGo

★ 1.5k · Tools 2 Compare with this →

Basic Memory 72 · B

Your AI never forgets again.

★ 4.1k · Tools 21 Compare with this →

Telegram MCP Server 70 · B

Telegram MCP server powered by Telethon to let MCP clients read chats, manage groups, and send/modify messages, media, contacts, and settings.

★ 1.8k · Tools 76 Compare with this →

Hostinger API MCP Server 70 · B

Official MCP server for Hostinger API.

★ 160 · Tools 100 Compare with this →

Compare with other MCP servers

Source revision e161e7b2c641 Data synced 2026-10-11 Read the FMRS scoring method