Skip to content

x402 Web Tools MCP server

dev.workers.microtools-x402.x402-web-tools/web-toolsx402-web-tools.microtools-x402.workers.devstreamable-httpv0.2.2Scanned

Web/PDF to Markdown, papers, transcription via x402. Free sample: /v1/sample

9 tools: 3 change things and 6 only read.

Tools: 0 delete, 0 irreversible, 3 write, 6 read.
  • Reads private data · 1
  • Reads text others write · 4
  • Can send data out · 4
  • 1 finding, 1 high

Sign-in required, no OAuth metadata. Remote posture

Anlyon alternative

3 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

What the x402 Web Tools MCP server can do

The x402 Web Tools MCP server is published by x402-web-tools.microtools-x402.workers.dev, a domain the MCP Registry verified. It has 9 tools. It can create or change data (3 tools: transcribe_audio, check_citation and health), but cannot delete data. 6 tools only read.

1 tool reads private data (read_url_safe); 4 tools bring in text other people can write (read_url, read_url_safe, read_pdf and 1 more); 4 tools can send data out of your system (read_url, read_url_safe, read_pdf 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.

The fixed checks matched 1 finding, 1 of them high severity (model-directed-text). Each one comes with the text it matched.

Its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 17, 2026, version 0.2.2.

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.

9 tools

Changes things 3Claude Code: ask
  • check_citationCheck whether a cited paper exists (catch hallucinated or mistyped references) and whether it has been retracted.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Check whether a cited paper exists (catch hallucinated or mistyped references) and whether it has been retracted. Give a doi, or a title with optional year and first_author. Returns exists, verdict, confidence, is_retracted and the best match. Data: OpenAlex (CC0) and Crossref/Retraction Watch. Upstream errors are not charged. Costs $0.002 USDC per check via x402. Free sample: GET /v1/sample.
  • healthFree health check.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Free health check. Returns service status, version, tool prices, network and the plain-HTTP x402 endpoints. A free fixed-example sample is at GET /v1/sample.
  • transcribe_audioTranscribe a public direct audio file URL (mp3, wav, m4a, ogg/opus, flac; max 25 MB and 10 minutes, checked from the file header) with Whisper on Cloudflare Workers AI.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
    Transcribe a public direct audio file URL (mp3, wav, m4a, ogg/opus, flac; max 25 MB and 10 minutes, checked from the file header) with Whisper on Cloudflare Workers AI. Returns text, language, duration, timestamped segments, optional SRT/VTT. Page URLs (YouTube etc.) are rejected. Failed transcriptions and files with no speech are not charged. Costs $0.01 USDC per file via x402. Free sample: GET /v1/sample.
Only reads 6Show 6 read-only tools
  • get_paperLook up one scholarly work by DOI, doi.org URL, arXiv id or OpenAlex work id.Reads text others writeNo findings

    Why it is in this group

    • The name "get_paper" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Look up one scholarly work by DOI, doi.org URL, arXiv id or OpenAlex work id. Returns title, authors, year, venue, DOI, citation and references counts, open-access PDF, abstract, OpenAlex id and a retraction flag (OpenAlex + Crossref/Retraction Watch). Data: OpenAlex (CC0) and Crossref. Not-found and upstream errors are not charged. Costs $0.002 USDC per lookup via x402. Free sample: GET /v1/sample.
  • pingPaid connectivity test: returns ok and a server timestamp.No findings

    Why it is in this group

    • The name "ping" says "ping": a word for reading.
    Description, as the server wrote it
    Paid connectivity test: returns ok and a server timestamp. Use it to check that your x402 payment flow works end to end. Costs $0.001 USDC per call via x402. Free sample: GET /v1/sample.
  • read_pdfFetch a public PDF (max 10 MB) and convert it to Markdown with Cloudflare Workers AI toMarkdown.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "read_pdf" says "read": a word for reading.

    What it can reach

    • 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 PDF (max 10 MB) and convert it to Markdown with Cloudflare Workers AI toMarkdown. Returns title (if detected), url, markdown, word_count. Same URL safety rules as read_url. Failed conversions are not charged. Costs $0.006 USDC per call via x402. Free sample: GET /v1/sample.
  • read_urlFetch a public web page and return its main content as clean Markdown (readability extraction): title, url, final_url, markdown, word_count.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "read_url" says "read": a word for reading.

    What it can reach

    • untrusted-inputThe name "read_url" says "read" and "url": 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 and return its main content as clean Markdown (readability extraction): title, url, final_url, markdown, word_count. HTML, plain text, Markdown, JSON and XML. Static fetch only (no JavaScript rendering). Respects robots.txt, blocks private/loopback/metadata hosts, max 3 MB / 15 s, no logins or paywall bypass. For PDFs use read_pdf. Failed reads are not charged. Costs $0.002 USDC per call via x402. Free sample: GET /v1/sample.
  • read_url_safeSame as read_url plus a heuristic prompt-injection check: flags hidden/invisible text, instruction-like phrases ("ignore previous instructions", role reassignment, secret exfiltrat…Reads private dataReads text others writeCan send data out1 finding

    Why it is in this group

    • The name "read_url_safe" says "read": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "secret": it reads secrets.
    • untrusted-inputThe name "read_url_safe" says "read" and "url": it reads web pages, which anyone can write.
    • 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.

    Findings

    • High

      The description contains "ignore previous instructions", an instruction to set earlier instructions aside.

      Matched text

      description: "...isible text, instruction-like phrases ("ignore previous instructions", role reassignment, secret exfiltratio..."

      What this check looks for
    Description, as the server wrote it
    Same as read_url plus a heuristic prompt-injection check: flags hidden/invisible text, instruction-like phrases ("ignore previous instructions", role reassignment, secret exfiltration, chat-template tokens), suspicious HTML comments and zero-width/Unicode-tag characters. Returns injection_check {flagged, risk none|low|medium|high, signals}. Heuristic, not a guarantee. Failed reads are not charged. Costs $0.003 USDC per call via x402. Free sample: GET /v1/sample.
  • search_papersSearch scholarly papers (OpenAlex, 250M+ works).No findings

    Why it is in this group

    • The name "search_papers" says "search": a word for reading.
    Description, as the server wrote it
    Search scholarly papers (OpenAlex, 250M+ works). Returns up to 25 results: title, authors, year, venue, DOI, citation count, open-access PDF, abstract and OpenAlex id. Optional from_year, to_year, open_access_only. Data: OpenAlex (CC0) with Crossref as fallback. Upstream errors are not charged. Costs $0.005 USDC per search via x402. Free sample: GET /v1/sample.

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.

16 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 write4
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__web-tools__read_url_safe"
    ]
  }
}

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.

Sign-in required, no OAuth metadata

Looked at Nov 20, 2026, 19:22 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
500
tools/list served without credentials
no
Tools that change things, listed without credentials
0
Protocol version
not observed
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

The probe stopped: initialize answered HTTP 500.

Posture changes

  1. Nov 20, 2026
    • HTTP status of an anonymous initialize: 200 to 500
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 3 to 0
    • Protocol version: 2025-06-18 to none

Findings

Matches of fixed checks, with the text they matched.

1 high
  • The description contains "ignore previous instructions", an instruction to set earlier instructions aside.

    Matched text

    description: "...isible text, instruction-like phrases ("ignore previous instructions", role reassignment, secret exfiltratio..."

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 500; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 3 -> 0 (and 1 more).View diff
    • HTTP status of an anonymous initialize: 200 to 500
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 3 to 0
    • Protocol version: 2025-06-18 to none
  2. Tools9 changed.~9 changedView diff

Install

Pinned to version 0.2.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http web-tools https://x402-web-tools.microtools-x402.workers.dev/mcp
claude mcp add --transport http web-tools https://x402-web-tools.microtools-x402.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__web-tools__search_papers",
      "mcp__web-tools__get_paper",
      "mcp__web-tools__ping"
    ],
    "ask": [
      "mcp__web-tools__read_url",
      "mcp__web-tools__read_url_safe",
      "mcp__web-tools__read_pdf",
      "mcp__web-tools__transcribe_audio",
      "mcp__web-tools__check_citation",
      "mcp__web-tools__health"
    ],
    "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-tools. Review it before you use it.

Capability tags behind 5 rules
  • mcp__web-tools__read_url untrusted-input, outbound
  • mcp__web-tools__read_url_safe private-data, untrusted-input, outbound
  • mcp__web-tools__read_pdf untrusted-input, outbound
  • mcp__web-tools__transcribe_audio outbound
  • mcp__web-tools__get_paper 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.workers.microtools-x402.x402-web-tools/web-tools/verify?hash=851001880a457f5929bfeb03f68cb43bd5f665e0e140a59505648190aed9ed83" | jq -e '.changed == false'

Pinned hash 851001880a45, from Nov 17, 2026, 04:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/dev.workers.microtools-x402.x402-web-tools/web-tools/changes.xml

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

Badge

Anlyon Radar badge for dev.workers.microtools-x402.x402-web-tools/web-tools
[![Anlyon Radar](https://radar.anlyon.com/badge/dev.workers.microtools-x402.x402-web-tools/web-tools.svg)](https://radar.anlyon.com/servers/dev.workers.microtools-x402.x402-web-tools/web-tools)

Source: MCP Registry. Synced Nov 18, 2026, 12:17 UTC.

x402 Web Tools MCP server: questions and answers

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

Is the x402 Web Tools MCP server safe?

No scan can promise that. What its definitions show: 9 tools, 3 of which can change, send or delete something, and 1 finding (1 high) from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the x402 Web 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 x402 Web 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 x402 Web Tools MCP server have?

9 tools: 3 write, 6 read. transcribe_audio, check_citation, health, read_url, read_url_safe, read_pdf, search_papers, get_paper and 1 more.

Does the x402 Web Tools MCP server need sign-in or OAuth?

Its remote endpoint did not answer the last anonymous look.

Does the x402 Web 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): read_url, read_url_safe, read_pdf and transcribe_audio.

Has the x402 Web Tools MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 17, 2026. Every change is on this page and in its Atom feed.