anew MCP server
page.anew/anewanew.pagestreamable-httpv1.0.0Scanned
Encode self-contained HTML pages into shareable URLs.
4 tools: 1 do something that can't be undone, 2 change things and 1 only read.
- Reads private data · 1
- Reads text others write · 2
- Can send data out · 2
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. 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 anew MCP server can do
The anew MCP server is published by anew.page, a domain the MCP Registry verified. It has 4 tools. It can do things that cannot be undone, such as sending, paying or publishing (anew_write) and create or change data (2 tools: anew_page and anew_editor), but cannot delete data. 1 tool only reads.
1 tool reads private data (anew_read); 2 tools bring in text other people can write (anew_write and anew_read); 2 tools can send data out of your system (anew_read and anew_page). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 18, 2026, version 1.0.0.
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.
4 tools
Can't be undone 1Claude Code: ask
anew_writePublish a web page: encode one self-contained HTML document (or fragment, or plain text) into an anew.page URL and return that URL.Reads text others writeNo findings
Why it is in this group
- The name "anew_write" says "write": a word for a change.
- The description's first verb is "publish": a word for a change that another call does not undo.
- The input takes a statement or command to run (input.javascript), which can change anything it can reach.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Publish a web page: encode one self-contained HTML document (or fragment, or plain text) into an anew.page URL and return that URL. Use it when the user asks for a page, a site or a link they can open and share. The page is carried in the URL itself — no account, and no copy of the page is kept — so anyone who has the URL can open it; each call also starts a screenshot of the page, cached publicly for link previews. Put markup and inline CSS in html and any JavaScript in javascript as plain source; the server inserts it before </body>. Inline the page's CSS, scripts and images so it renders on its own; a webfont may load from a CDN. Each encoding path is deterministic: the same input through the same path always produces the same URL. Different paths use different Brotli encoders, though, so the same HTML may mint different — equally valid — URLs; compare pages by their decoded HTML, never by slug. Limits: a page whose URL would pass 4000 bytes, or whose HTML passes 1048576 bytes decoded, is refused with an error that states the size and the overage; apps cut longer links short when they are shared. To revise an existing anew page, its URL is its source: read it, edit that HTML, write it again. The new URL is a separate page and the original keeps working. Read it with anew_read first, then call this with the edited HTML.
Annotations the server declares
- readOnlyHint: false
- idempotentHint: false
- destructiveHint: false
- openWorldHint: true
Changes things 2Claude Code: ask
anew_editorOpen anew from the sidebar: the editor, fullscreen, on a new blank page.1 finding
Why it is in this group
- The description's first verb is "open": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "anew_editor" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The description's first verb is "open": a word for a change.
Description, as the server wrote it Open anew from the sidebar: the editor, fullscreen, on a new blank page. Takes no arguments.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: false
- destructiveHint: false
- openWorldHint: false
anew_pageOpen a page in the anew editor beside the chat, so the user can edit it by hand: pass an anew.page URL to open that page, or nothing for a new blank page.Can send data out1 finding
Why it is in this group
- The description's first verb is "open": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "anew_page" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The description's first verb is "open": a word for a change.
Description, as the server wrote it Open a page in the anew editor beside the chat, so the user can edit it by hand: pass an anew.page URL to open that page, or nothing for a new blank page. The editor reports the page it holds back to the chat after every edit. Call it only when the user asks to open the editor or to edit a page themselves; anew_write and anew_read do everything else.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: false
- destructiveHint: false
- openWorldHint: false
Only reads 1Show 1 read-only tool
anew_readPass an anew.page URL, get back the HTML document encoded in it, plus its canonical URL and byte size.Reads private dataReads text others writeCan send data outNo findings
Why it is in this group
- The name "anew_read" says "read": a word for reading.
What it can reach
- private-dataThe description's first sentence says "document": it reads documents.
- untrusted-inputThe description's first sentence says "url": 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.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Pass an anew.page URL, get back the HTML document encoded in it, plus its canonical URL and byte size. (Two in-page tools share this name and take no arguments: the editor's reads the document open in the editor, and a rendered page's reads the page being viewed. This one takes a url and reads that page.) To revise an existing anew page, its URL is its source: read it, edit that HTML, write it again. The new URL is a separate page and the original keeps working. Read returns the author's exact bytes — no anew-injected tags, no proxied image srcs — so it re-encodes byte-for-byte. Never re-author from a rendered page, a scraped DOM, or a screenshot: each loses the author's markup, and none is faster than reading the slug. Decoding is local and exact, so any anew URL reads — the page needs no prior visit and no fetch.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: false
- destructiveHint: false
- 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.
4 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
{
"permissions": {
"deny": [
"mcp__anew__anew_read"
]
}
}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, 19:17 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
- 3
- Protocol version
- 2025-11-25
- 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 3 tools that change things (1 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://anew.page/mcp: tools/list returned 4 tools to an anonymous client, including anew_write (irreversible), anew_page (write), anew_editor (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnanew_page
The server marks "anew_page" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The description's first verb is "open": a word for a change.
- Warnanew_editor
The server marks "anew_editor" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The description's first verb is "open": a word for a change.
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 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http anew https://anew.page/mcpclaude mcp add --transport http anew https://anew.page/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": [],
"ask": [
"mcp__anew__anew_write",
"mcp__anew__anew_read",
"mcp__anew__anew_page",
"mcp__anew__anew_editor"
],
"deny": []
}
}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 anew. Review it before you use it.
Capability tags behind 3 rules
- mcp__anew__anew_write untrusted-input
- mcp__anew__anew_read private-data, untrusted-input, outbound
- mcp__anew__anew_page outbound
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/page.anew/anew/verify?hash=0bcd1c4f182969c027bf73c3e6a11e16772b60a371bf843752206f3bf8bedf81" | jq -e '.changed == false'Pinned hash 0bcd1c4f1829, from Nov 18, 2026, 05:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/page.anew/anew/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/page.anew/anew)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:54 UTC.
anew MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the anew MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 3 of which can change, send or delete something, and 2 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 anew MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the anew MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: anew_write.
What tools does the anew MCP server have?
- 4 tools: 1 irreversible, 2 write, 1 read. anew_write, anew_page, anew_editor and anew_read.
Does the anew MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the anew MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): anew_read and anew_page.
Has the anew MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.