How do I install olostep-mcp-server?

Its README did not state an install command plainly enough for us to quote one, so we do not guess. The repository has the instructions: https://github.com/olostep/olostep-mcp-server

What does olostep-mcp-server connect to, and what does it need?

It reaches olostep. The credentials we found in its source are OLOSTEP_API_KEY.

Is olostep-mcp-server official and is it maintained?

We found nothing naming it as a vendor’s official server. Its repository has 24 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-10-21.

What licence does olostep-mcp-server use?

The repository declares the MIT licence.

InfratoApp / Resources / MCP servers / olostep-mcp-server

olostep-mcp-server

olostep-mcp-server is an MCP server, listed under browser & scraping. It reaches olostep. It needs OLOSTEP_API_KEY to authenticate. Its repository has 24 GitHub stars and is licensed under MIT; we last read it on 2026-10-22.

This server provides web scraping, crawling, and real-time search capabilities for MCP-compatible AI agents, connecting to Olostep's infrastructure.

Install

MCP servers are packaged differently from each other -- some run via npx, some as a Docker image, some as a plain script you clone and run. olostep-mcp-server’s own README did not state one plainly enough for this page to quote it rather than guess, so it will not guess. The repository below states it.

Read olostep-mcp-server’s own install instructions ↗

What it reaches, and what it needs

Reaches

olostep

Credential

OLOSTEP_API_KEY

Maintenance

Stars

State

listed

Licence

MIT

From the repository

MCP server for Olostep — the web scraping, crawling, and search infrastructure used by top AI companies. Gives any MCP-compatible AI agent the ability to scrape, crawl, batch-extract, and search the web in real time.

View on GitHub ↗2026-10-22

What olostep-mcp-server can do

9 tools documented in its README. An AI client calls these by name.

batch_scrape_urls: Scrape up to 10k URLs at the same time. Perfect for large-scale data extraction.
create_crawl: Start an async crawl that autonomously discovers and scrapes entire websites by following links. Returns a `crawl_id` — the crawl runs in the background and does **not** return content in this respons
create_map: Get all URLs on a website. Extract all URLs for discovery and analysis.
get_batch_results: Retrieve the results of a previously submitted batch scrape job using its `batch_id`.
get_crawl_results: Retrieve the status and scraped pages for an async crawl started with `create_crawl`. This is the required companion to `create_crawl` — `create_crawl` only kicks off the job and returns a `crawl_id`;
get_website_urls: Search and retrieve relevant URLs from a website, sorted by relevance to your query.
get_webpage_content: Retrieves webpage content in clean markdown format with support for JavaScript rendering.
search_web: Search the Web for a given query and get structured results (non-AI, parser-based).
answers: Search the web and return AI-powered answers in the JSON structure you want, with sources and citations.

Read from the README; names are kept only if the README contains them.