Olostep MCP: live web search and scraping for your AI app

How to add Olostep to your AI app

1. 1Click Connect Olostep free and sign in to Olostep.
2. 2Searches, scrapes, maps, answers and crawls use credits; checking your balance and fetching stored results don't. Switch off crawling or the answer tool if you want to keep spending down.
3. 3Add ContextGate to your AI app as a connector or MCP server. The steps for each app are on the Works with page.
4. 4Ask your AI app to research a question with Olostep and cite its sources, then open Activity to see the call.

Web data from a chat

• Search the web for relevant links, optionally scraping each result.
• Scrape one page and get its content, links and metadata.
• Map a website's URLs, or crawl it and page through what was processed.
• Ask a research question and get an answer with sources, usually in 3 to 30 seconds.
• Fetch a stored result again without paying for the work twice.

Credits you can trace

• Switch off the crawl and answer tools and keep single-page scrapes and search.
• Policies check every call, so a secret pasted into a search query can be blocked.
• Activity records every Olostep call, so you can see which searches and crawls used credits.

What you get with Olostep and ContextGate

• Your AI apps can use OlostepClaude, Cursor, ChatGPT and other AI apps reach Olostep through the one ContextGate connection you add to them.
• You choose which tools they can useSwitch off any Olostep tool you don't want used. It's hidden from your AI apps and refused if called.
• Every call is checked and recordedYour policies check each call (for example, personal data is hidden and secrets are blocked), and Activity keeps a record of it.

ContextGate sees only the tool calls that go through it, not your AI app's built-in tools or your chats.

Olostep tools

Examples of what your AI apps can do in Olostep. You'll see the exact list of tools after you connect it.

• Answer QuestionSynchronously research a bounded task by searching and browsing the web, then return the completed answer and sources when available. This usage-metered operation usually takes 3-30 seconds and has no
• Get Credit BalanceReturn the connected team's remaining Olostep credits, credit lots, active subscription, and whether usage is enabled without consuming web-processing credits.
• Get Operation ResultRetrieve a stored scrape, search, map, answer, or crawl by its operation ID without repeating or rebilling the original work. Crawl results may still report in_progress.
• List Crawl PagesReturn one page of URLs and retrieve IDs processed by an asynchronous crawl, with a continuation cursor for additional pages. Use Retrieve Content for page bodies.
• Map WebsiteSynchronously discover and optionally rank URLs on a website, returning one response page and a continuation cursor. This usage-metered operation consumes Olostep credits.
• Retrieve ContentRetrieve stored page content by retrieve ID in selected live-supported formats, including hosted URLs for oversized output.
• Scrape PageSynchronously scrape one web page and return requested content, links, metadata, a retrieve ID, and billing usage. This usage-metered operation can consume credits even when cached content is returned
• Search WebSynchronously search the web for relevant deduplicated links. This usage-metered operation costs 5 base credits per search; supplying scrape_formats also charges for scraping each returned page. The r
• Start CrawlStart an asynchronous, usage-metered website crawl and immediately return its crawl ID and initial status. This action does not poll: use Get Operation Result to monitor status and List Crawl Pages to