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

dev.oassisPublished by oassis.devOfficial publisherv1.0.2Updated Oct 24, 2026

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

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingBrowser Automation

Overview

AI-generated overview

Remote MCP server that lets an AI assistant scrape pages, crawl sites, search the web and drive a browser session, billed per credit.

What you can do
  • Scrape a page in one call for markdown, HTML, links, screenshots, PDF, accessibility tree, selector matches or AI-structured data
  • Map a site's URLs from its sitemap and page links, then crawl its pages and poll or cancel the job
  • Batch-scrape 2 to 50 URLs you supply and check, cancel or collect the results
  • Search the web through Exa's index and hand the result URLs to batch scraping
  • Open a browser session, act on it with navigate, click, type, select, press, scroll, wait and back, then close it
  • Start a research task that answers a question from public pages with sources, progress and cost, and check or cancel it
When to use it
Useful when an assistant needs live web content it cannot fetch itself: reading or extracting a page, discovering and crawling a site, running a multi-URL scrape, searching for unknown sources, or performing scripted browser interactions. It suits research and data-collection workflows where per-output credit billing is acceptable.
Requirements
Runs as a remote streamable HTTP endpoint; nothing to install locally. An API key and credits are required for sessions, batches, crawls, research tasks and most paid outputs; a 100-credit MCP trial is mentioned. Network access to the oassis endpoint is needed.
Before you install
Usage is metered in credits and paid per output, per started browser minute, per action and per crawl page, with Exa search priced by Exa; research tasks reserve a maximum budget. An API key is required and grants access to your own tasks and account. Scraping, crawling and browser actions send target URLs to a third-party service and can interact with live sites.

Installation

In SourceWeft

  1. Open oassis — web scraping, crawling and browser control for AI agents in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/dev.oassis%2Fscraper-crawler/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "oassis-web-scraping-crawling-and-browser": {
      "type": "http",
      "url": "https://api.oassis.dev/mcp"
    }
  }
}

Tools

14

web_scrape

Read a page or a document

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 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

ParameterspdfurlhtmljsonwaitblocklinksmaxAgeformatsrequestbinaryAscontrols+3 more

web_session_open

Open a browser session

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: https://oassis.dev/openapi.json

ParameterspdfurlrequiredjsonwaitblocklinksmaxAgeformatsrequestbinaryAscontrolsviewport+2 more

web_act

Act on an open page

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 credit) per action, plus requested outputs and any outstanding browser time. API key and credits required. Reference for the oassis API: https://oassis.dev/openapi.json

ParameterspdfurljsonwaitblocklinksmaxAgeactionsrequiredformatsrequestbinaryAscontrols+4 more

web_scrape_batch

Read a list of urls

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.

ParametersjsonurlsrequiredwaitblocklinksmaxAgeformatsrequestbinaryAscontrolsviewportselectors

web_batch_status

Check or cancel a batch

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

ParametersjobIdrequiredlimitcancel

web_map

List a site's urls

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: https://oassis.dev/openapi.json

ParametersurlrequiredlimitsearchincludePageexcludePathsincludePathsincludeSubdomains

web_crawl

Crawl a site

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

ParametersurlrequiredjsonwaitblocklimitlinksmaxAgeformatsrequestbinaryAscontrolsmaxDepth+5 more

web_crawl_status

Check or cancel a crawl

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.

ParametersjobIdrequiredlimitcancel

web_search_exa

Search the web

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 — the quote is read at execution time and is not a guaranteed fixed price. API key and credits required over MCP.

ParameterslimitqueryrequiredsincedomainssnippetsexcludeDomains

web_feedback

Report a bad answer

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

Parametersurlroutecommentverdictrequiredreference

web_task_start

Start a research task

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.

Parametersmodetaskrequiredurlslimits

web_task_status

Check a research task

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

Parametersidrequiredaccess_token

web_task_cancel

Cancel a research task

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.

Parametersidrequiredaccess_token

web_session_close

Close a session

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.

ParameterssessionIdrequired

Version history

3
  1. v1.0.2LatestOct 22, 2026
  2. v1.0.1Sep 30, 2026
  3. v1.0.0Sep 30, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.

Other Oassis integrations

oassis — web for agents

dev.oassis

A remote MCP endpoint that lets an assistant read, map and crawl the web and drive a real browser, paid per call without a key or signup.

Streamable HTTPWeb executable
Web Search & ScrapingNot indexed yetSep 29, 2026