Back to search
100
MCP live MCP 2025-06-18 http

oassis — web scraper, crawler and browser control

oassis/scraper-crawler

Scrape any page or document to **markdown**, map and crawl whole sites, and drive a **real browser** — all from one server. **Pay per call with a wallet. No API key, no signup, no monthly plan.** Keyless clients get a free daily allowance so the first call works before any account exists. **What it does that a scraper usually does not** - **A map of the controls** — every link, button and field with its role, its readable name and where it sits on screen. The map an agent needs to decide what to click. - **Browser sessions that stay open** — look, click, look again, without reloading and without losing state. - **Documents by url** — PDF, Word, Excel and CSV come back as markdown, no browser involved. - **Every output in one call** — markdown, html, links, controls, accessibility tree, elements by selector, screenshot, PDF, or AI-extracted JSON. **Tools:** `web_scrape` · `web_map` · `web_crawl` · `web_session_open` · `web_act` · `web_scrape_batch` · `web_search_exa` · and status, close and feedback. Prices start at $0.001 a page, quoted before the work and refunded when the work does not happen. More at [oassis.dev](https://oassis.dev).

Watch this dependency Share evidence report
Uptime
100.0%
5 direct probes · 30d
Response
829ms
last probe
Tools
14
callable
Resources
2
readable
Prompts
3
available
Primary URL
https://oassis.dev/mcp
Score: 100/100
Handshake verified by our own probe.
pass Answers the MCP handshake 50/50
The handshake and the list calls succeeded on the primary URL.
pass Lists tools, resources or prompts 30/30
14 tools, 2 resources, 3 prompts returned.
pass 3 or more catalogue items 10/10
19 items in total; 3 or more earns these points.
pass Describes itself 10/10
1159 characters; more than 30 earns these points.

Tools · 14

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…

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.…

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…

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

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 `include…

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 nee…

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. Th…

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 repr…

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,…

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 no…

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, i…

Resources · 2

openapi

The OpenAPI document for the whole API: each route, the fields it accepts, what it answers, and what the call costs. Read this before constructing a request by hand.

oassis://openapi.json
llms

The catalogue written for a model to read in one pass, without parsing a schema. Shorter than the OpenAPI document and enough to decide which route to call.

oassis://llms.txt

Prompts · 3

read-a-page

Turn a url into markdown, and get the map of what can be clicked at the same time.

research-a-site

List a site's urls first, decide what is worth reading, and only then read it.

fill-in-a-form

Open a browser session, act on it with the refs the control map gave you, and close it.

How to use

Claude Desktop or claude.ai: add a custom connector (Customize → Connectors; on Team and Enterprise plans an owner adds it under Organization settings → Connectors) with this server URL: https://oassis.dev/mcp

Cursor or Cline: add to your MCP config:

{
  "mcpServers": {
    "oassis_\u2014_web_scraper,_crawler_and_browser_control": {
      "url": "https://oassis.dev/mcp",
      "transport": "http"
    }
  }
}