
Olostep MCP Server
This server gives Claude web search, scraping, and crawling capabilities designed specifically for AI agent workflows. It handles batch scraping operations when you need to pull data from multiple URLs at once, and returns answers with proper source citations instead of just raw HTML. Reach for this when you're building automations that need to gather information from across the web, research topics with verifiable sources, or monitor multiple sites systematically. The citation feature makes it especially suited for research tasks where you need to track where information came from rather than dumping everything into context as unattributed text.
- GitHub stars
- 25
- tools
- 10
- auth
- Secret needed
- transport
- STDIO, HTTP
- last updated
- Nov 11, 2026
Tools
10 toolsPublic tool metadata for what this MCP can expose to an agent.
scrape_websiteExtract content from a single URL. Supports multiple formats and JavaScript rendering.
Extract content from a single URL. Supports multiple formats and JavaScript rendering.
No parameter schema in public metadata yet.
search_webSearch the Web for a given query and get structured results (non-AI, parser-based).
Search the Web for a given query and get structured results (non-AI, parser-based).
No parameter schema in public metadata yet.
answersSearch the web and return AI-powered answers in the JSON structure you want, with sources and citations.
Search the web and return AI-powered answers in the JSON structure you want, with sources and citations.
No parameter schema in public metadata yet.
batch_scrape_urlsScrape up to 100k URLs in one batch. Perfect for large-scale data extraction.
Scrape up to 100k URLs in one batch. Perfect for large-scale data extraction.
No parameter schema in public metadata yet.
create_crawlStart an async crawl that autonomously discovers and scrapes entire websites by following links.
Start an async crawl that autonomously discovers and scrapes entire websites by following links.
No parameter schema in public metadata yet.
create_mapGet all URLs on a website. Extract all URLs for discovery and analysis.
Get all URLs on a website. Extract all URLs for discovery and analysis.
No parameter schema in public metadata yet.
get_webpage_contentRetrieves webpage content in clean markdown format with support for JavaScript rendering.
Retrieves webpage content in clean markdown format with support for JavaScript rendering.
No parameter schema in public metadata yet.
get_website_urlsSearch and retrieve relevant URLs from a website, sorted by relevance to your query.
Search and retrieve relevant URLs from a website, sorted by relevance to your query.
No parameter schema in public metadata yet.
get_batch_resultsRetrieve the results of a previously submitted batch scrape job using its batch_id.
Retrieve the results of a previously submitted batch scrape job using its batch_id.
No parameter schema in public metadata yet.
get_crawl_resultsRetrieve the status and scraped pages for an async crawl started with create_crawl.
Retrieve the status and scraped pages for an async crawl started with create_crawl.
No parameter schema in public metadata yet.
Sponsors
Readme
Olostep MCP Server
Docker Hub npm version License: ISC
Live web search, scraping and crawling API for AI. Get structured, LLM-ready data from any site. Scale to 1M requests with 10 parallel batches at low cost.
Olostep is web data infrastructure for AI agents and enterprise AI workflows. Its APIs provide live web search, scraping and crawling to extract, clean and structure data from the web. This is the official Olostep Model Context Protocol (MCP) server, which gives any MCP-compatible AI agent those capabilities.
Use the hosted server at https://mcp.olostep.com/mcp (sign in with OAuth, or use an API key), or run it locally with an API key from the Olostep website.
Why Olostep
- Web data infrastructure for developers and enterprises
- Scales to hundreds of millions to billions of requests per customer per month
- The most performant, reliable and cost-effective API on the market
- Used by the fastest-growing AI companies
Details
- Repository
- github.com/olostep/olostep-mcp-server
- Website
- www.olostep.com
- Categories
- AI & LLM Tools, Search & Web Crawling, Data & Analytics
- Package
olostep-mcp- Transport
- STDIO, HTTP
- Auth
- Required
- Registry
- MCP registry, active