oassis — web scraping, crawling and browser control for AI agents MCP server
dev.oassis/scraper-crawleroassis.devstreamable-httpv1.0.2Scanned
Web Tools and Web Tasks for AI agents. 100-credit MCP trial; API-key credits or x402.
14 tools: 1 can delete or cancel things, 11 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 11
- Can send data out · 8
- 3 findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the oassis — web scraping, crawling and browser control for AI agents MCP server can do
The oassis — web scraping, crawling and browser control for AI agents MCP server is published by oassis.dev, a domain the MCP Registry verified. It has 14 tools. It can delete or cancel things (1 tool: web_task_cancel) and create or change data (11 tools: web_scrape, web_session_open, web_act, web_scrape_batch and 7 more). 2 tools only read.
11 tools bring in text other people can write (web_scrape, web_session_open, web_act and 8 more); 8 tools can send data out of your system (web_scrape, web_session_open, web_act and 5 more).
The fixed checks matched 3 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 8, 2026, version 1.0.2.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
14 tools
Deletes or cancels 1Claude Code: deny
web_task_cancelStops a task using its owning API key, or its legacy access_token.1 finding
Why it is in this group
- The name "web_task_cancel" says "cancel": a word for removing or ending something.
- The server marks it not destructive (destructiveHint: false), but an annotation never lowers a class.
Findings
- Warn
The server marks "web_task_cancel" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "web_task_cancel" says "cancel": a word for removing or ending something.
Description, as the server wrote it 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.
Annotations the server declares
- title: Cancel a research task
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Changes things 11Claude Code: ask
web_actRuns actions against an open session and returns the resulting state.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "run": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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
Annotations the server declares
- title: Act on an open page
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
web_batch_statusChecks a batch of scrapes: status, how many are done, and the results.Reads text others write1 finding
Why it is in this group
- The name "web_batch_status" says "status": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe name "web_batch_status" says "status" and "web": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "scrape": it reads web pages, which anyone can write.
Findings
- Warn
The server marks "web_batch_status" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "web_batch_status" says "status": a word for reading.
Description, as the server wrote it Checks a batch of scrapes: status, how many are done, and the results. Free for the owning account. Pass `cancel: true` to stop it.
Annotations the server declares
- title: Check or cancel a batch
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
web_crawlFollows a site's links and reads every page.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "web_crawl" says "crawl": it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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
Annotations the server declares
- title: Crawl a site
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
web_crawl_statusChecks a crawl: status, pages read, discovered and still queued, and the pages themselves.Reads text others write1 finding
Why it is in this group
- The name "web_crawl_status" says "status": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe name "web_crawl_status" says "crawl": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "crawl": it reads web pages, which anyone can write.
Findings
- Warn
The server marks "web_crawl_status" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "web_crawl_status" says "status": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- title: Check or cancel a crawl
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
web_feedbackTell us an answer was good or bad.Can send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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
Annotations the server declares
- title: Report a bad answer
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
web_mapEvery url of a site, fast and cheap: its sitemap plus, optionally, the links on the page.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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
Annotations the server declares
- title: List a site's urls
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
web_scrapeProcesses 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` …Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "web_scrape" says "scrape": it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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
Annotations the server declares
- title: Read a page or a document
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
web_scrape_batchA batch OF SCRAPES: reads a list of urls YOU give it (2 to 50, from any sites) and returns a jobId.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "web_scrape_batch" says "scrape": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "scrape": it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.urls): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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.
Annotations the server declares
- title: Read a list of urls
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
web_session_closeCloses the browser session and stops its time.No findings
Why it is in this group
- The name "web_session_close" says "close": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- title: Close a session
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
web_session_openOpens a browser session and returns the map of controls.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "web_session_open" says "open": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "web_session_open" says "open" and "web": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "open" and "browser": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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
Annotations the server declares
- title: Open a browser session
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
web_task_startStarts a research task: a question answered by reading public pages, with sources, progress and cost.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "web_task_start" says "start": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.urls): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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.
Annotations the server declares
- title: Start a research task
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 2Show 2 read-only tools
web_search_exaSearch the web with Exa's index: a query instead of a url, for when you do not know where to look.Reads text others writeNo findings
Why it is in this group
- The name "web_search_exa" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "web_search_exa" says "search" and "web": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "search" and "web": it reads web pages, which anyone can write.
Description, as the server wrote it 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.
Annotations the server declares
- title: Search the web
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
web_task_statusReturns a task's status, progress, sources, limitations, result and billing.Reads text others writeNo findings
Why it is in this group
- The name "web_task_status" says "status": a word for reading.
What it can reach
- untrusted-inputThe name "web_task_status" says "status" and "web": it reads web pages, which anyone can write.
Description, as the server wrote it Returns a task's status, progress, sources, limitations, result and billing. Only your own tasks.
Annotations the server declares
- title: Check a research task
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write11
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out8
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:52 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 12
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 12 tools that change things (1 destructive, 11 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.oassis.dev/mcp: tools/list returned 14 tools to an anonymous client, including web_task_cancel (destructive), web_scrape (write), web_session_open (write), web_act (write), web_scrape_batch (write) and 7 more
Findings
Matches of fixed checks, with the text they matched.
- Warnweb_batch_status
The server marks "web_batch_status" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "web_batch_status" says "status": a word for reading.
- Warnweb_crawl_status
The server marks "web_crawl_status" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "web_crawl_status" says "status": a word for reading.
- Warnweb_task_cancel
The server marks "web_task_cancel" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "web_task_cancel" says "cancel": a word for removing or ending something.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http scraper-crawler https://api.oassis.dev/mcpclaude mcp add --transport http scraper-crawler https://api.oassis.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__scraper-crawler__web_search_exa",
"mcp__scraper-crawler__web_task_status"
],
"ask": [
"mcp__scraper-crawler__web_scrape",
"mcp__scraper-crawler__web_session_open",
"mcp__scraper-crawler__web_act",
"mcp__scraper-crawler__web_scrape_batch",
"mcp__scraper-crawler__web_batch_status",
"mcp__scraper-crawler__web_map",
"mcp__scraper-crawler__web_crawl",
"mcp__scraper-crawler__web_crawl_status",
"mcp__scraper-crawler__web_feedback",
"mcp__scraper-crawler__web_task_start",
"mcp__scraper-crawler__web_session_close"
],
"deny": [
"mcp__scraper-crawler__web_task_cancel"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as scraper-crawler. Review it before you use it.
Capability tags behind 12 rules
- mcp__scraper-crawler__web_scrape untrusted-input, outbound
- mcp__scraper-crawler__web_session_open untrusted-input, outbound
- mcp__scraper-crawler__web_act untrusted-input, outbound
- mcp__scraper-crawler__web_scrape_batch untrusted-input, outbound
- mcp__scraper-crawler__web_batch_status untrusted-input
- mcp__scraper-crawler__web_map untrusted-input, outbound
- mcp__scraper-crawler__web_crawl untrusted-input, outbound
- mcp__scraper-crawler__web_crawl_status untrusted-input
- mcp__scraper-crawler__web_search_exa untrusted-input
- mcp__scraper-crawler__web_feedback outbound
- mcp__scraper-crawler__web_task_start untrusted-input, outbound
- mcp__scraper-crawler__web_task_status untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/dev.oassis/scraper-crawler/verify?hash=919aedca38968a73be073bcb28a6d35ee798fb0ab5fc5e8c12891875d7e870a8" | jq -e '.changed == false'Pinned hash 919aedca3896, from Nov 8, 2026, 17:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.oassis/scraper-crawler/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.oassis/scraper-crawler)Source: MCP Registry. Synced Oct 22, 2026, 22:17 UTC.
oassis — web scraping, crawling and browser control for AI agents MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the oassis — web scraping, crawling and browser control for AI agents MCP server safe?
- No scan can promise that. What its definitions show: 14 tools, 12 of which can change, send or delete something, and 3 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the oassis — web scraping, crawling and browser control for AI agents MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: web_task_cancel.
Can the oassis — web scraping, crawling and browser control for AI agents MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the oassis — web scraping, crawling and browser control for AI agents MCP server have?
- 14 tools: 1 destructive, 11 write, 2 read. web_task_cancel, web_scrape, web_session_open, web_act, web_scrape_batch, web_batch_status, web_map, web_crawl and 6 more.
Does the oassis — web scraping, crawling and browser control for AI agents MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the oassis — web scraping, crawling and browser control for AI agents MCP server send data to outside services?
- 8 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): web_scrape, web_session_open, web_act, web_scrape_batch, web_map, web_crawl and 2 more.
Has the oassis — web scraping, crawling and browser control for AI agents MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 8, 2026.