Oxylabs MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OXYLABS_PASSWORD | Yes | Your Oxylabs account password | |
| OXYLABS_USERNAME | Yes | Your Oxylabs account username |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ai_crawlerC | 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. 'render_javascript' is used to render javascript heavy websites. 'return_sources_limit' is used to limit the number of sources to return, for example if you expect results from single source, you can set it to 1. |
| ai_scraperA | 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 used to render javascript heavy websites. |
| ai_browser_agentC | 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 navigating to any url, clicking on links, filling forms, scrolling, etc. Finally it returns the data in the specified format. Schema is required only if output_format is json, csv or toon. 'task_prompt' describes what browser agent should achieve |
| ai_searchA | 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 don't need to use ai_scraper to get the content of the search results urls, because it is already included in the search results. if 'return_content' is set to True, prefer lower 'limit' to reduce payload size. |
| generate_schemaC | Generate a json schema in openapi format. |
| ai_mapD | Tool useful for mapping website's URLs. |
| universal_scraperB | Get a content of any webpage. Supports browser rendering, parsing of certain webpages and different output formats. |
| google_search_scraperA | Scrape Google Search results. Supports content parsing, different user agent types, pagination, domain, geolocation, locale parameters and different output formats. |
| amazon_search_scraperB | Scrape Amazon search results. Supports content parsing, different user agent types, pagination, domain, geolocation, locale parameters and different output formats. Supports Amazon specific parameters such as category id, merchant id, currency. |
| amazon_product_scraperA | Scrape Amazon products. Supports content parsing, different user agent types, domain, geolocation, locale parameters and different output formats. Supports Amazon specific parameters such as currency and getting more accurate pricing data with auto select variant. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
Several tools have heavily overlapping purposes: ai_scraper and universal_scraper both claim to scrape any webpage content, while ai_crawler and ai_browser_agent both navigate websites and extract data. ai_search and google_search_scraper also cover similar territory, making selection ambiguous without very careful reading.
Names are descriptive and readable, but they follow two different conventions: an ai_ prefix group (ai_crawler, ai_scraper, ai_search, ai_map, ai_browser_agent) and a target_suffix group (google_search_scraper, amazon_search_scraper, amazon_product_scraper, universal_scraper). Only generate_schema stands apart with a clear verb_noun pattern.
Ten tools is well-scoped for a web scraping and search server covering generic scraping, search, browser automation, URL mapping, schema generation, and Amazon-specific extraction. Each tool represents a distinct product capability, even if some overlap exists.
The tool surface covers the core needs of the domain: general search, Google-specific search, generic page scraping, crawling, browser-driven interaction, site mapping, and Amazon search/product scraping. There are no obvious dead ends for common web data acquisition workflows.