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

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 $0.001 per output. A url pointing at a PDF, Word, Excel or CSV file is converted to markdown instead, with no browser, for $0.002. Refer

Opens a browser on a page and leaves it open, returning the map of controls. Use it when something has to be FILLED IN or CLICKED, not just read: inside the session the `controls` references keep working and you can act on the same state. $0.005 plus the outputs. Close it with web_session_close when you are done. Reference for the oassis API: https://oassis.dev/openapi.json

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 per action. Reference for the oassis API: https://oassis.dev/openapi.json

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. Free over MCP, without usage quotas. Poll it with web_batch_status.

Checks a batch of scrapes: status, how many are done, and the results. Free. Pass `cancel: true` to stop it. MCP calls are free.

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. $0.001 with `includePage: false` (no browser at all), $0.0015 with the page. Reference for the oassis API: https://oassis.dev/openapi.json

Follows a site's links and reads every page. Returns a jobId; poll it with web_crawl_status. Free over MCP; `limit` controls the size of this crawl, not a usage quota. Use web_map first if you only need the urls. Reference for the oassis API: https://oassis.dev/openapi.json

Checks a crawl: status, pages read, discovered and still queued, and the pages themselves. Free. Pass `cancel: true` to stop it. MCP calls are free.

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 payment challenge on every call — today $0.007 per search.

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 a page that is simply like that. Reference for the oassis API: https://oassis.dev/openapi.json

Starts a research task: a question answered by reading public pages, with sources, progress and cost. Free over MCP. No API key or account. The execution budget bounds the task, without charging the client. Returns a task id: check it with web_task_status.

Returns a task's status, progress, sources, limitations, result and billing. Only your own tasks.

Stops a task using its access_token. No new operations start. Free over MCP; there is no client charge or on-chain refund. Cancelling a finished task changes nothing.

Closes a session and stops billing browser time. Free. If you do not close it, it closes itself after a minute without use.