PageWire MCP server
dev.pagewire/webpagewire.devstreamable-httpv1.0.1Scanned
Web pages to Markdown, metadata and small crawls for agents. Free daily calls, then USDC x402/MPP.
3 tools: 3 only read.
- Reads private data · 0
- Reads text others write · 3
- Can send data out · 3
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- 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 PageWire MCP server can do
The PageWire MCP server is published by pagewire.dev, a domain the MCP Registry verified. It has 3 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
3 tools bring in text other people can write (page_to_markdown, page_metadata and crawl_site); 3 tools can send data out of your system (page_to_markdown, page_metadata and crawl_site).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 15, 2026, version 1.0.1.
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.
3 tools
Only reads 3Show 3 read-only tools
crawl_siteFetch a public web page plus up to 4 pages on the same host that it links to (in link order, or only those whose path starts with `prefix`), and return each one as title + clean Ma…Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "fetch": 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 "crawl_site" says "crawl": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "fetch" and "web": 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 Fetch a public web page plus up to 4 pages on the same host that it links to (in link order, or only those whose path starts with `prefix`), and return each one as title + clean Markdown. Good for reading a docs section or a small site in one call. No model call, deterministic. For a single page use page_to_markdown (cheaper), for metadata only use page_metadata. Plain HTTP fetch (no JavaScript rendering, 15 s timeout, only the first 2 MB is read). Errors (non-public URL, upstream HTTP error, timeout, non-text content) return isError with the reason and are never charged. Price: $0.03 USDC per call via x402 (USDC on Base or Solana, no account; nothing is charged for a bad input). First $0.1 of calls per day per client are free (no payment needed).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
page_metadataFetch a public web page and return its metadata: title, description, canonical URL, language, OpenGraph and Twitter card tags, icons and parsed JSON-LD blocks.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "fetch": 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 description's first sentence says "fetch" and "web": 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 Fetch a public web page and return its metadata: title, description, canonical URL, language, OpenGraph and Twitter card tags, icons and parsed JSON-LD blocks. Use it for link previews, SEO checks or structured data (JSON-LD) without the page body; use page_to_markdown when you need the readable text and links. Plain HTTP fetch (no JavaScript rendering, 15 s timeout, only the first 2 MB is read). Errors (non-public URL, upstream HTTP error, timeout, non-text content) return isError with the reason and are never charged. Price: $0.005 USDC per call via x402 (USDC on Base or Solana, no account; nothing is charged for a bad input). First $0.1 of calls per day per client are free (no payment needed).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
page_to_markdownFetch a public web page and return its title, description, clean Markdown (scripts, styles, nav chrome removed) and the list of links.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "fetch": 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 description's first sentence says "fetch" and "web": 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 Fetch a public web page and return its title, description, clean Markdown (scripts, styles, nav chrome removed) and the list of links. No model call, deterministic. Use it to read the content of one page; use page_metadata if you only need title/OpenGraph/JSON-LD (cheaper), or crawl_site to read the page plus the pages it links to in one call. Plain HTTP fetch (no JavaScript rendering, 15 s timeout, only the first 2 MB is read). Errors (non-public URL, upstream HTTP error, timeout, non-text content) return isError with the reason and are never charged. Price: $0.01 USDC per call via x402 (USDC on Base or Solana, no account; nothing is charged for a bad input). First $0.1 of calls per day per client are free (no payment needed).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
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 write3
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out3
- 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
- 0
- 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
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
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 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http web https://pagewire.dev/mcpclaude mcp add --transport http web https://pagewire.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": [],
"ask": [
"mcp__web__page_to_markdown",
"mcp__web__page_metadata",
"mcp__web__crawl_site"
],
"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 web. Review it before you use it.
Capability tags behind 3 rules
- mcp__web__page_to_markdown untrusted-input, outbound
- mcp__web__page_metadata untrusted-input, outbound
- mcp__web__crawl_site untrusted-input, 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/dev.pagewire/web/verify?hash=cdbf2a28f611e0db9672626b6ff015f24402189f4852cb0183135049936ca727" | jq -e '.changed == false'Pinned hash cdbf2a28f611, from Nov 15, 2026, 03:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.pagewire/web/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.pagewire/web)Source: MCP Registry. Synced Oct 21, 2026, 18:12 UTC.
PageWire MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the PageWire MCP server safe?
- No scan can promise that. What its definitions show: 3 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the PageWire MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the PageWire 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 PageWire MCP server have?
- 3 tools: 3 read. page_to_markdown, page_metadata and crawl_site.
Does the PageWire MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the PageWire MCP server send data to outside services?
- 3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): page_to_markdown, page_metadata and crawl_site.
Has the PageWire MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 15, 2026.