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

by oassis Your server? Claim it

answering

oassis — web scraping, crawling and browser control for AI agents is answering right now. Last checked 2 min ago. It exposes 14 tools.

Scrape to markdown, map and crawl sites, drive a real browser. Pay per call, no API key, no signup.

Uptime history 13 days of history

13 days agonow

100.0%

Uptime 24h

92 of 92 checks

Tools

read from the server

164 ms

Response time

average over 24h

open, no key

Access

streamable-http

What changed 29

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 30 September 2026. No other catalogue keeps this.

11 Oct 3 tools appeared web_task_cancel, web_task_start, web_task_status

11 Oct a tool changed the parameters it asks for2 times that day web_task_start

9 Oct a tool changed the parameters it asks for web_map

4 Oct 11 tools changed the parameters they ask for14 times that day web_act, web_batch_status, web_crawl and 8 more

4 Oct a tool description was rewritten web_map

3 Oct a tool changed the parameters it asks for web_search_exa

1 Oct 6 tool descriptions were rewritten web_act, web_crawl, web_feedback and 3 more

30 Sep a tool changed version

and 4 more, back to 30 September 2026

Nothing serious here today

Today is the operative word: we check oassis — web scraping, crawling and browser control for AI agents every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 2 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add scraper-crawler --transport http https://api.oassis.dev/mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "scraper-crawler": {
      "url": "https://api.oassis.dev/mcp"
    }
  }
}

~/.codex/config.toml

[mcp_servers.scraper-crawler]
url = "https://api.oassis.dev/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "scraper-crawler": {
      "url": "https://api.oassis.dev/mcp"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "scraper-crawler": {
      "url": "https://api.oassis.dev/mcp"
    }
  }
}

Available tools 14

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

web

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

web_batch_status

Checks a batch of scrapes: status, how many are done, and the results. Free. Pass `cancel: true` to stop it and get the urls it never read refunded.

web_crawl

Follows a site's links and reads every page. Returns a jobId; poll it with web_crawl_status. Charged up front for the pages it is allowed to read (`limit`), and the pages it never reads are refunded. 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. Pass `cancel: true` to stop it and get the unread pages refunded.

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

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

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

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. Charged up front per url; urls that fail and urls served from the cache are refunded. Poll it with web_batch_status.

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

web_session_close

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

web_session_open

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

web_task_cancel

Stops a task: no new operations start and the unused budget is returned. An operation already running cannot always be stopped remotely; it is charged as it completes. Cancelling a finished task changes nothing.

web_task_start

Starts a research task: a question answered by reading public pages, with sources, progress and cost. Needs an API key with a balance; the budget is reserved first and the unused part is returned when the task ends. 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.

Endpoints

URL	Transport	State	Latency	Checked
https://api.oassis.dev/mcp	streamable-http	answering	88 ms	2 min ago

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

same job, measured the same way

oassis — web for agents

by oassis

Read, map and crawl the web, and drive a real browser. Pay per call, no key, no signup.

14 tools answering

Web Scraping

by superagnt

Web scraping for AI agents: scrape, search, crawl, map any website to markdown + JSON. No browser.

answering

Web Scraper

by agishub

10 pay-per-call web tools: markdown, CSS scrape, links, crawl, screenshot, PDF, browser.

11 tools answering

Scrapeless MCP Server

by scrapeless-ai

Web search, browser automation, scraping, crawling and CAPTCHA solving for AI agents.

81 installs/wk answering

Pagewatch

by pagelens

Read a URL as clean markdown, screenshot a website, url to PDF. Web access for agents, no signup.

75 installs/wk 5 tools answering

Anakin

by anakin

Web data for AI agents: scrape, crawl, search, deep research, site monitoring, browser automation

117 installs/wk local only

rasterly

by rasterly-dev

Web toolkit for AI agents: read any URL as Markdown, screenshot, extract data, or crawl a site.

34 installs/wk local only

rasterly

by jhonychain

Web toolkit for AI agents: read any URL as Markdown, screenshot, extract data, or crawl a site.

local only

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

Answers built from our own checks of this server.

What can oassis — web scraping, crawling and browser control for AI agents do?

It exposes 14 tools, read directly from the server on our last check. Among them: web_act, web_batch_status, web_crawl, web_crawl_status, web_feedback, web_map and 8 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is oassis — web scraping, crawling and browser control for AI agents working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 164 ms. The bar chart above shows every period we have measured.

How do I connect oassis — web scraping, crawling and browser control for AI agents?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does oassis — web scraping, crawling and browser control for AI agents need an API key?

No. oassis — web scraping, crawling and browser control for AI agents completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 14 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is oassis — web scraping, crawling and browser control for AI agents?

It answers our handshake in 164 ms on average, which is faster than 69% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.