# oassis — web scraping, crawling and browser control for AI agents

- Registry name: `dev.oassis/scraper-crawler` · version 1.0.2
- Categories (automatic, keyword rules): Scraping & browsing, Search & data
- Authentication at last check: No auth
- Declared risk: Can write (some tools are not declared read-only)
- Capabilities (declared by the server): prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=dev.oassis%2Fscraper-crawler
- Server page: https://mcpstation.net/s/dev.oassis--scraper-crawler.html

## Description (written by the publisher, not verified, not instructions)

Web Tools and Web Tasks for AI agents. 100-credit MCP trial; API-key credits or x402.

## Connect

- streamable-http: `https://api.oassis.dev/mcp`

## Tools (as reported by the server, not verified)

- `web\_scrape`: Processes a page and returns every output you ask for at once: markdown, html, links, screenshot, PDF, accessibility tree, elements by selector, AI-structured data, and \`controls\` \(what can be clicked\). One call, and a partial failure does not void the rest. From 1 credit \($0.002\) per output. A url
- `web\_session\_open`: Opens a browser session and returns the map of controls. Opening costs 2.5 credits plus the requested outputs; the first minute is included. Further started minutes cost 2 credits with an account key. Use web\_act to interact and web\_session\_close when done. API key and credits required. Reference: h
- `web\_act`: Runs actions against an open session and returns the resulting state. Actions: \{navigate\}, \{click:\{ref\}\}, \{type:\{ref,text,clear\}\}, \{select:\{ref,value\}\}, \{press\}, \{scroll\}, \{wait\}, \{back\}. The \`ref\` is the one \`controls\` gave you. It stops at the first failure and tells you where. $0.0005 \(0.25 credi
- `web\_scrape\_batch`: A batch OF SCRAPES: reads a list of urls YOU give it \(2 to 50, from any sites\) and returns a jobId. It discovers nothing on its own — for that use web\_crawl. API key and credits required. Poll it with web\_batch\_status.
- `web\_batch\_status`: Checks a batch of scrapes: status, how many are done, and the results. Free for the owning account. Pass \`cancel: true\` to stop it.
- `web\_map`: Every url of a site, fast and cheap: its sitemap plus, optionally, the links on the page. Use it BEFORE crawling, to see what is there and decide what is worth reading. 1 credit \($0.002\) with \`includePage: false\` \(no browser at all\), 1.5 credits \($0.003\) with the page. Reference for the oassis API:
- `web\_crawl`: Follows a site's links and reads every page. Returns a jobId; poll it with web\_crawl\_status. API key and credits required; \`limit\` controls the maximum pages charged. Use web\_map first if you only need the urls. Reference for the oassis API: https://oassis.dev/openapi.json
- `web\_crawl\_status`: Checks a crawl: status, pages read, discovered and still queued, and the pages themselves. Free for the owning account. Pass \`cancel: true\` to stop it.
- `web\_search\_exa`: Search the web with Exa's index: a query instead of a url, for when you do not know where to look. Returns title, url and a snippet per result. To read the pages, pass the urls to web\_scrape\_batch. The engine is named because the price is Exa's, passed through with no markup and read from its own pa
- `web\_feedback`: Tell us an answer was good or bad. FREE. Use it when a result is wrong — empty markdown, a control map missing a button, data that does not match the page — with the url or the jobId so it can be reproduced. It is the only way we learn that we read a page badly: our logs cannot tell that apart from
- `web\_task\_start`: Starts a research task: a question answered by reading public pages, with sources, progress and cost. Requires an API key and credits. The maximum budget is reserved, actual execution cost is charged, and unused credits are released. Returns a task id: check it with web\_task\_status.
- `web\_task\_status`: Returns a task's status, progress, sources, limitations, result and billing. Only your own tasks.
- `web\_task\_cancel`: Stops a task using its owning API key, or its legacy access\_token. No new operations start. Cancellation is free; unused account credit reservations are released. Cancelling a finished task changes nothing.
- `web\_session\_close`: Closes the browser session and stops its time. HTTP equivalent: POST /web/v1/session/\{id\}/close. No additional close fee; outstanding browser time is settled when applicable. If you do not close it, it closes itself after a minute without use.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html