oassis — web for agents is an MCP server with 14 tools an agent can call, among them web_act, web_batch_status, web_crawl. It answers at https://api.oassis.dev/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 29 September 2026; the last check, on 14 November 2026, succeeded.
Read, map and crawl the web, and drive a real browser. Pay per call, no key, no signup.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
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 a Inputs: sessionId, actions, url, formats, selectors, json |
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. Inputs: jobId, limit, cancel |
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 Inputs: formats, selectors, json, controls, links, wait |
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. Inputs: jobId, limit, cancel |
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 Inputs: verdict, route, reference, url, comment |
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 cr Inputs: url, limit, includePage, search, includeSubdomains, includePaths |
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 Inputs: url, html, formats, selectors, json, screenshot |
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. Inputs: formats, selectors, json, controls, links, wait |
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 E Inputs: query, limit, snippets, domains, excludeDomains, since |
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 u Inputs: sessionId |
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 Inputs: url, formats, selectors, json, screenshot, pdf |
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. Inputs: id, access_token |
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. Return Inputs: task, mode, urls, limits |
web_task_status | Returns a task's status, progress, sources, limitations, result and billing. Only your own tasks. Inputs: id, access_token |
Every block below points at https://api.oassis.dev/mcp. Pick your client and copy.
claude mcp add --transport http oassis-web-for-agents https://api.oassis.dev/mcp
{
"mcpServers": {
"oassis-web-for-agents": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.oassis.dev/mcp"]
}
}
}{
"mcpServers": {
"oassis-web-for-agents": {
"url": "https://api.oassis.dev/mcp"
}
}
}{
"servers": {
"oassis-web-for-agents": {
"type": "http",
"url": "https://api.oassis.dev/mcp"
}
}
}{
"context_servers": {
"oassis-web-for-agents": {
"url": "https://api.oassis.dev/mcp"
}
}
}{
"mcpServers": {
"oassis-web-for-agents": {
"serverUrl": "https://api.oassis.dev/mcp"
}
}
}{
"mcpServers": {
"oassis-web-for-agents": {
"url": "https://api.oassis.dev/mcp"
}
}
}name: oassis — web for agents
version: 0.0.1
schema: v1
mcpServers:
- name: oassis — web for agents
type: streamable-http
url: https://api.oassis.dev/mcp{
"mcpServers": {
"oassis-web-for-agents": {
"httpUrl": "https://api.oassis.dev/mcp"
}
}
}{
"mcpServers": {
"oassis-web-for-agents": {
"type": "http",
"url": "https://api.oassis.dev/mcp"
}
}
}{
"mcpServers": {
"oassis-web-for-agents": {
"url": "https://api.oassis.dev/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapi.oassis.dev%2Fmcp&type=streamable_http&id=oassis-web-for-agents&name=oassis%20%E2%80%94%20web%20for%20agents
It answered our last check on 14 November 2026 in 655 ms. Over 4 checks since 29 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by oassis.dev and served from api.oassis.dev, the vendor's own domain: https://api.oassis.dev/mcp.
14, as returned by the server's own tools/list on 17 November 2026: web_act, web_batch_status, web_crawl, web_crawl_status, web_feedback, web_map, web_scrape, web_scrape_batch, and 6 more.
It answered our last check on 14 November 2026 in 655 ms. Over 4 checks since 29 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.oassis.dev/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: dev.oassis. Endpoint host: api.oassis.dev. ARD identifier: urn:air:dev.oassis:mcp:web.
First indexed 29 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.