Skip to content

AgentPay (all tools) MCP server

io.github.noah-silver/agentpay-bundlenoah-silverstreamable-httpv1.1.0Scanned

Pay-per-call web extract, DNS/WHOIS/IP lookup, PDF/RSS/sitemap tools. x402 USDC on Base/Algorand.

8 tools: 2 change things and 6 only read.

Tools: 0 delete, 0 irreversible, 2 write, 6 read.
  • Reads private data · 1
  • Reads text others write · 8
  • Can send data out · 4
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 AgentPay (all tools) MCP server can do

The AgentPay (all tools) MCP server is published by the GitHub account noah-silver. It has 8 tools. It can create or change data (2 tools: tools_pdf_text and tools_feed), but cannot delete data. 6 tools only read.

1 tool reads private data (lookup_domain_report); 8 tools bring in text other people can write (extract_page, lookup_dns, lookup_whois and 5 more); 4 tools can send data out of your system (extract_page, tools_pdf_text, tools_feed and 1 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

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 20, 2026, version 1.1.0.

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.

8 tools

Changes things 2Claude Code: ask
  • tools_feedParse an RSS, Atom or JSON Feed into normalized JSON items.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
    Parse an RSS, Atom or JSON Feed into normalized JSON items. Costs $0.005 USDC per call (x402 or credits).

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • tools_pdf_textExtract per-page text from a PDF URL (up to 20MB).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
    Extract per-page text from a PDF URL (up to 20MB). Costs $0.01 USDC per call (x402 or credits).

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
Only reads 6Show 6 read-only tools
  • extract_pageFetch a URL and return markdown, metadata and 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 "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
    Fetch a URL and return markdown, metadata and links. Costs $0.005 USDC per call (x402 or credits).

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • lookup_dnsResolve DNS records (A, AAAA, CNAME, MX, NS, TXT, SOA, CAA, PTR, SRV).Reads text others writeNo findings

    Why it is in this group

    • The name "lookup_dns" says "lookup": a word for reading.

    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
    Resolve DNS records (A, AAAA, CNAME, MX, NS, TXT, SOA, CAA, PTR, SRV). Costs $0.005 USDC per call (x402 or credits).

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • lookup_domain_reportOne-call domain report: registration, DNS, email provider, SPF/DMARC, hosting.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "lookup_domain_report" says "lookup": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "email": it reads mail.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "email": it reads inbound email, which other people can write.
    Description, as the server wrote it
    One-call domain report: registration, DNS, email provider, SPF/DMARC, hosting. Costs $0.02 USDC per call (x402 or credits).

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • lookup_ipIP network owner, range, country and reverse DNS.Reads text others writeNo findings

    Why it is in this group

    • The name "lookup_ip" says "lookup": a word for reading.

    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
    IP network owner, range, country and reverse DNS. Costs $0.01 USDC per call (x402 or credits).

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • lookup_whoisDomain registration data (registrar, created/expires, status, nameservers) via RDAP.Reads text others writeNo findings

    Why it is in this group

    • The name "lookup_whois" says "lookup": a word for reading.

    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
    Domain registration data (registrar, created/expires, status, nameservers) via RDAP. Costs $0.01 USDC per call (x402 or credits).

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • tools_sitemapList a site's URLs from its sitemaps (follows robots.txt and sitemap indexes).Reads text others writeCan send data outNo findings

    Why it is in this group

    • The description's first verb is "list": 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 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
    List a site's URLs from its sitemaps (follows robots.txt and sitemap indexes). Costs $0.005 USDC per call (x402 or credits).

    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.

32 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 write8
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out4
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__agentpay-bundle__lookup_domain_report"
    ]
  }
}

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.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:08 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
2
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
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://agentpay.agentpay-apis.workers.dev/mcp: tools/list returned 8 tools to an anonymous client, including tools_pdf_text (write), tools_feed (write)

    What this check looks for

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 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agentpay-bundle https://agentpay.agentpay-apis.workers.dev/mcp
claude mcp add --transport http agentpay-bundle https://agentpay.agentpay-apis.workers.dev/mcp

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__agentpay-bundle__lookup_dns",
      "mcp__agentpay-bundle__lookup_whois",
      "mcp__agentpay-bundle__lookup_ip",
      "mcp__agentpay-bundle__lookup_domain_report"
    ],
    "ask": [
      "mcp__agentpay-bundle__extract_page",
      "mcp__agentpay-bundle__tools_pdf_text",
      "mcp__agentpay-bundle__tools_feed",
      "mcp__agentpay-bundle__tools_sitemap"
    ],
    "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 agentpay-bundle. Review it before you use it.

Capability tags behind 8 rules
  • mcp__agentpay-bundle__extract_page untrusted-input, outbound
  • mcp__agentpay-bundle__lookup_dns untrusted-input
  • mcp__agentpay-bundle__lookup_whois untrusted-input
  • mcp__agentpay-bundle__lookup_ip untrusted-input
  • mcp__agentpay-bundle__lookup_domain_report private-data, untrusted-input
  • mcp__agentpay-bundle__tools_pdf_text untrusted-input, outbound
  • mcp__agentpay-bundle__tools_feed untrusted-input, outbound
  • mcp__agentpay-bundle__tools_sitemap 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/io.github.noah-silver/agentpay-bundle/verify?hash=a95a7d9fbaae27b1f5a389e245cd29526db81b011e61903ee026af53fc041c0b" | jq -e '.changed == false'

Pinned hash a95a7d9fbaae, from Nov 20, 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/io.github.noah-silver/agentpay-bundle/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.noah-silver/agentpay-bundle
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.noah-silver/agentpay-bundle.svg)](https://radar.anlyon.com/servers/io.github.noah-silver/agentpay-bundle)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:42 UTC.

AgentPay (all tools) MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the AgentPay (all tools) MCP server safe?

No scan can promise that. What its definitions show: 8 tools, 2 of which can change, send or delete something, and 0 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 AgentPay (all tools) MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the AgentPay (all tools) 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 AgentPay (all tools) MCP server have?

8 tools: 2 write, 6 read. tools_pdf_text, tools_feed, extract_page, lookup_dns, lookup_whois, lookup_ip, lookup_domain_report and tools_sitemap.

Does the AgentPay (all tools) MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the AgentPay (all tools) MCP server send data to outside services?

4 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): extract_page, tools_pdf_text, tools_feed and tools_sitemap.

Has the AgentPay (all tools) MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.