olostep-mcp

[ { "name": "scrape_website", "description": "Extract content from a single URL. Supports multiple formats and JavaScript rendering.", "arguments": [ { "name": "url_to_scrape", "type": "string", "desc": "The URL of the website you want to scrape" }, { "name": "output_format", "type": "string", "desc": "Choose format: html, markdown, json, or text. Default: markdown", "optional": true }, { "name": "country", "type": "string", "desc": "Optional country code (e.g., US, GB, CA) for location-specific scraping", "optional": true }, { "name": "wait_before_scraping", "type": "number", "desc": "Wait time in milliseconds before scraping (0-10000)", "optional": true }, { "name": "parser", "type": "string", "desc": "Optional parser ID for specialized extraction (e.g., @olostep/amazon-product)", "optional": true } ] }, { "name": "search_web", "description": "Search the web for a given query and return structured results (non-AI, parser-based)", "arguments": [ { "name": "query", "type": "string", "desc": "Search query" }, { "name": "country", "type": "string", "desc": "Optional country code for localized results (e.g., US, GB)", "optional": true } ] }, { "name": "answers", "description": "Search the web and return AI-powered answers in the JSON structure you want, with sources and citations", "arguments": [ { "name": "task", "type": "string", "desc": "Question or task to answer using web data" }, { "name": "json", "type": "string", "desc": "Optional JSON schema/object or description of desired output shape", "optional": true } ] }, { "name": "batch_scrape_urls", "description": "Scrape up to 10k URLs at the same time. Perfect for large-scale data extraction", "arguments": [ { "name": "urls_to_scrape", "type": "array", "desc": "JSON array of objects with url and optional custom_id" }, { "name": "output_format", "type": "string", "desc": "Choose format for all URLs. Default: markdown", "optional": true }, { "name": "country", "type": "string", "desc": "Optional country code for location-specific scraping", "optional": true }, { "name": "wait_before_scraping", "type": "number", "desc": "Wait time in milliseconds before scraping each URL", "optional": true }, { "name": "parser", "type": "string", "desc": "Optional parser ID for specialized extraction", "optional": true } ] }, { "name": "create_crawl", "description": "Autonomously discover and scrape entire websites by following links from a start URL", "arguments": [ { "name": "start_url", "type": "string", "desc": "Starting URL for the crawl" }, { "name": "max_pages", "type": "number", "desc": "Maximum number of pages to crawl", "optional": true }, { "name": "follow_links", "type": "boolean", "desc": "Whether to follow links found on pages", "optional": true }, { "name": "output_format", "type": "string", "desc": "Format for scraped content. Default: markdown", "optional": true }, { "name": "country", "type": "string", "desc": "Optional country code for location-specific crawling", "optional": true }, { "name": "parser", "type": "string", "desc": "Optional parser ID for specialized content extraction", "optional": true } ] }, { "name": "create_map", "description": "Get all URLs on a website. Extract URLs for discovery and site analysis", "arguments": [ { "name": "website_url", "type": "string", "desc": "Website URL to extract links from" }, { "name": "search_query", "type": "string", "desc": "Optional search query to filter URLs", "optional": true }, { "name": "top_n", "type": "number", "desc": "Optional limit for number of URLs returned", "optional": true }, { "name": "include_url_patterns", "type": "array", "desc": "Optional glob patterns to include (e.g., /blog/**)", "optional": true }, { "name": "exclude_url_patterns", "type": "array", "desc": "Optional glob patterns to exclude (e.g., /admin/**)", "optional": true } ] }, { "name": "get_webpage_content", "description": "Retrieve content of a webpage in markdown format", "arguments": [ { "name": "url_to_scrape", "type": "string", "desc": "The URL of the webpage to scrape" }, { "name": "wait_before_scraping", "type": "number", "desc": "Time to wait in milliseconds before starting the scrape", "optional": true }, { "name": "country", "type": "string", "desc": "Residential country to load the request from (e.g., US, CA, GB)", "optional": true } ] }, { "name": "get_website_urls", "description": "Search and retrieve relevant URLs from a website", "arguments": [ { "name": "url", "type": "string", "desc": "The URL of the website to map" }, { "name": "search_query", "type": "string", "desc": "The search query to sort URLs by" } ] }, { "name": "google_search", "description": "Retrieve structured data from Google search results", "arguments": [ { "name": "query", "type": "string", "desc": "The search query to perform" }, { "name": "country", "type": "string", "desc": "Country code for localized results (e.g., US, GB)", "optional": true } ] } ]