Skip to content

Adam Hale Tools: Web Research and Open Data MCP server

dev.workers.adamhaleworks.tools/web-researchtools.adamhaleworks.workers.devstreamable-httpv1.1.0Scanned

Free web lookups; PDF to Markdown, audio transcripts, screenshots, WHOIS/DNS paid per call via x402.

12 tools: 5 change things and 7 only read.

Tools: 0 delete, 0 irreversible, 5 write, 7 read.
  • Reads private data · 2
  • Reads text others write · 12
  • Can send data out · 9
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

5 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 Adam Hale Tools: Web Research and Open Data MCP server can do

The Adam Hale Tools: Web Research and Open Data MCP server is published by tools.adamhaleworks.workers.dev, a domain the MCP Registry verified. It has 12 tools. It can create or change data (5 tools: seo_meta_tags_check, domain_intel, robots_txt_check, document_to_markdown and 1 more), but cannot delete data. 7 tools only read.

2 tools read private data (tech_stack_lookup and page_to_markdown); 12 tools bring in text other people can write (tech_stack_lookup, seo_meta_tags_check, url_status_check and 9 more); 9 tools can send data out of your system (seo_meta_tags_check, url_status_check, sitemap_urls and 6 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 (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 15, 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.

12 tools

Changes things 5Claude Code: ask
  • document_to_markdownConvert one document at a public URL to Markdown from its text layer: PDF, Word DOCX, Excel XLSX/XLSM/XLSB/XLS, OpenDocument ODS/ODT, CSV, HTML, XML or Apple Numbers, up to 10 MB, …Reads text others writeCan send data out1 finding

    Why it is in this group

    • The description's first verb is "convert": a word for a change.
    • 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.

    Findings

    • Warn

      The server marks "document_to_markdown" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "convert": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Convert one document at a public URL to Markdown from its text layer: PDF, Word DOCX, Excel XLSX/XLSM/XLSB/XLS, OpenDocument ODS/ODT, CSV, HTML, XML or Apple Numbers, up to 10 MB, Markdown up to 250,000 characters. Not OCR: scanned PDFs, images, PPTX and encrypted files are refused and not charged. Paid only: $0.004 USDC per file. Paid calls made without a payment return isError with the x402 v2 PaymentRequired object (amount in USDC atomic units, network, payTo, HTTP endpoint); retry with the signed PaymentPayload in params._meta["x402/payment"]. Invalid input and calls where every item fails are never charged. Fetches follow robots.txt, use the User-Agent AdamHaleTools/1.0 and refuse private or internal addresses.

    Annotations the server declares

    • title: PDF and document to Markdown
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • domain_intelWho a domain is registered with and since when (RDAP: registrar, created, expires, age, status, nameservers, DNSSEC), its DNS records (A, AAAA, MX, NS, TXT, CAA) and email setup (p…Reads text others writeNo 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.
    Description, as the server wrote it
    Who a domain is registered with and since when (RDAP: registrar, created, expires, age, status, nameservers, DNSSEC), its DNS records (A, AAAA, MX, NS, TXT, CAA) and email setup (provider, SPF and DMARC policy). No registrant personal data. Paid only: up to 3 domains per call for $0.003 USDC. Paid calls made without a payment return isError with the x402 v2 PaymentRequired object (amount in USDC atomic units, network, payTo, HTTP endpoint); retry with the signed PaymentPayload in params._meta["x402/payment"]. Invalid input and calls where every item fails are never charged. Fetches follow robots.txt, use the User-Agent AdamHaleTools/1.0 and refuse private or internal addresses.

    Annotations the server declares

    • title: Domain WHOIS (RDAP), DNS and email security
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • robots_txt_checkCrawl preflight: whether each user agent may fetch each URL under the site's robots.txt (RFC 9309, longest match, '*' fallback), with crawl-delay, the sitemaps robots.txt lists and…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 description's first sentence says "crawl": 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
    Crawl preflight: whether each user agent may fetch each URL under the site's robots.txt (RFC 9309, longest match, '*' fallback), with crawl-delay, the sitemaps robots.txt lists and whether the site publishes /llms.txt. Default agents: GPTBot, ChatGPT-User, OAI-SearchBot, ClaudeBot, Claude-User, PerplexityBot, Google-Extended, Googlebot, Bingbot, CCBot, Applebot-Extended, Bytespider and *. Paid only: up to 5 URLs per call for $0.001 USDC. Paid calls made without a payment return isError with the x402 v2 PaymentRequired object (amount in USDC atomic units, network, payTo, HTTP endpoint); retry with the signed PaymentPayload in params._meta["x402/payment"]. Invalid input and calls where every item fails are never charged. Fetches follow robots.txt, use the User-Agent AdamHaleTools/1.0 and refuse private or internal addresses.

    Annotations the server declares

    • title: robots.txt crawl permission check
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • seo_meta_tags_checkOn-page SEO audit of web pages: title and meta description lengths, canonical, robots/noindex and X-Robots-Tag, H1/H2, hreflang, Open Graph, Twitter card and JSON-LD rich-result ch…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.urls): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    On-page SEO audit of web pages: title and meta description lengths, canonical, robots/noindex and X-Robots-Tag, H1/H2, hreflang, Open Graph, Twitter card and JSON-LD rich-result checks, with machine-readable issue codes. Free for 1 URL when the free web tool is enabled; up to 3 URLs per call cost $0.004 USDC. Paid calls made without a payment return isError with the x402 v2 PaymentRequired object (amount in USDC atomic units, network, payTo, HTTP endpoint); retry with the signed PaymentPayload in params._meta["x402/payment"]. Invalid input and calls where every item fails are never charged. Fetches follow robots.txt, use the User-Agent AdamHaleTools/1.0 and refuse private or internal addresses.

    Annotations the server declares

    • title: SEO meta tag and schema.org check
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • transcribe_short_audioTranscribe one short audio file (direct public URL to MP3, WAV, M4A, OGG, FLAC or WebM; one file up to 2 MB and 20 minutes) with Whisper large-v3-turbo, or translate it to English:…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
    Transcribe one short audio file (direct public URL to MP3, WAV, M4A, OGG, FLAC or WebM; one file up to 2 MB and 20 minutes) with Whisper large-v3-turbo, or translate it to English: text, timed segments, WebVTT and detected language. No YouTube or social media pages. Paid only: $0.01 USDC per file. Paid calls made without a payment return isError with the x402 v2 PaymentRequired object (amount in USDC atomic units, network, payTo, HTTP endpoint); retry with the signed PaymentPayload in params._meta["x402/payment"]. Invalid input and calls where every item fails are never charged. Fetches follow robots.txt, use the User-Agent AdamHaleTools/1.0 and refuse private or internal addresses.

    Annotations the server declares

    • title: Short audio transcription (Whisper)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 7Show 7 read-only tools
  • page_to_markdownRead web pages: returns each page's main content as clean Markdown without navigation, scripts or ads (headings, lists, absolute links, tables, code blocks), plus title, descriptio…Reads private dataReads text others writeCan send data outNo findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "read" and "table": it reads databases.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "read" and "web": it reads web pages, which anyone can write.
    • untrusted-inputThe input takes a URL (input.urls), and the tool reads it: 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.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Read web pages: returns each page's main content as clean Markdown without navigation, scripts or ads (headings, lists, absolute links, tables, code blocks), plus title, description, language, canonical URL and word count; up to 100,000 characters per page. Does not get past bot walls. Paid only: up to 3 URLs per call for $0.002 USDC. Paid calls made without a payment return isError with the x402 v2 PaymentRequired object (amount in USDC atomic units, network, payTo, HTTP endpoint); retry with the signed PaymentPayload in params._meta["x402/payment"]. Invalid input and calls where every item fails are never charged. Fetches follow robots.txt, use the User-Agent AdamHaleTools/1.0 and refuse private or internal addresses.

    Annotations the server declares

    • title: Web page to clean Markdown
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • rss_to_jsonRead news feeds or blogs as clean JSON: accepts feed URLs or plain site URLs (finds the feed via <link rel=alternate>), normalises RSS 0.9x/2.0, RDF, Atom and JSON Feed to one item…Reads text others writeCan send data outNo findings

    Why it is in this group

    • The description's first verb is "read": 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 "rss_to_json" says "rss": it reads web pages, which anyone can write.
    • untrusted-inputThe description's first sentence says "read" and "rss": it reads web pages, which anyone can write.
    • untrusted-inputThe input takes a URL (input.urls), and the tool reads it: 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.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Read news feeds or blogs as clean JSON: accepts feed URLs or plain site URLs (finds the feed via <link rel=alternate>), normalises RSS 0.9x/2.0, RDF, Atom and JSON Feed to one item schema (title, url, publishedAt, author, categories, summary), up to 100 items per feed. Free for 1 feed; up to 5 feeds per call cost $0.003 USDC. Paid calls made without a payment return isError with the x402 v2 PaymentRequired object (amount in USDC atomic units, network, payTo, HTTP endpoint); retry with the signed PaymentPayload in params._meta["x402/payment"]. Invalid input and calls where every item fails are never charged. Fetches follow robots.txt, use the User-Agent AdamHaleTools/1.0 and refuse private or internal addresses.

    Annotations the server declares

    • title: RSS, Atom and JSON Feed to JSON
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • sitemap_urlsList the pages of a website from its sitemaps: finds them via robots.txt or common paths, follows sitemap indexes, reads gzip, text and feed sitemaps, returns URLs with lastmod.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 name "sitemap_urls" says "url": it reads web pages, which anyone can write.
    • untrusted-inputThe description's first sentence says "list" and "website": 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
    List the pages of a website from its sitemaps: finds them via robots.txt or common paths, follows sitemap indexes, reads gzip, text and feed sitemaps, returns URLs with lastmod. Free: up to 2,000 URLs from 12 sitemap files. With bulk=true: up to 5,000 URLs from 20 files for $0.004 USDC. Paid calls made without a payment return isError with the x402 v2 PaymentRequired object (amount in USDC atomic units, network, payTo, HTTP endpoint); retry with the signed PaymentPayload in params._meta["x402/payment"]. Invalid input and calls where every item fails are never charged. Fetches follow robots.txt, use the User-Agent AdamHaleTools/1.0 and refuse private or internal addresses.

    Annotations the server declares

    • title: Sitemap URL extractor
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • tech_stack_lookupDetect what a website is built with: CMS, frameworks, analytics, CDN, hosting, email and DNS providers (MX, SPF, DMARC) and a security-header grade, from one fetch of its homepage.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "tech_stack_lookup" 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 "website": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Detect what a website is built with: CMS, frameworks, analytics, CDN, hosting, email and DNS providers (MX, SPF, DMARC) and a security-header grade, from one fetch of its homepage. Free for 1 domain per call (10 free calls a minute per IP); 2-3 domains in one call cost $0.005 USDC. Paid calls made without a payment return isError with the x402 v2 PaymentRequired object (amount in USDC atomic units, network, payTo, HTTP endpoint); retry with the signed PaymentPayload in params._meta["x402/payment"]. Invalid input and calls where every item fails are never charged. Fetches follow robots.txt, use the User-Agent AdamHaleTools/1.0 and refuse private or internal addresses.

    Annotations the server declares

    • title: Website tech stack lookup
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • url_status_checkCheck whether links are alive: HTTP status, every redirect hop, final URL and a classification (ok, redirect, broken, restricted, blocked_by_site, disallowed_by_robots_txt, timeout…Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "url_status_check" says "status": 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 "url_status_check" says "status" and "url": it reads web pages, which anyone can write.
    • untrusted-inputThe description's first sentence says "http": it reads web pages, which anyone can write.
    • untrusted-inputThe input takes a URL (input.urls), and the tool reads it: 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.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Check whether links are alive: HTTP status, every redirect hop, final URL and a classification (ok, redirect, broken, restricted, blocked_by_site, disallowed_by_robots_txt, timeout). HEAD first, GET to confirm errors. Free for 1 URL when the free web tool is enabled; up to 10 URLs per call cost $0.003 USDC. Paid calls made without a payment return isError with the x402 v2 PaymentRequired object (amount in USDC atomic units, network, payTo, HTTP endpoint); retry with the signed PaymentPayload in params._meta["x402/payment"]. Invalid input and calls where every item fails are never charged. Fetches follow robots.txt, use the User-Agent AdamHaleTools/1.0 and refuse private or internal addresses.

    Annotations the server declares

    • title: URL status and redirect checker
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • website_screenshotScreenshot one public web page in a headless browser: desktop (1440x900) or mobile (390x844) viewport, PNG or JPEG, returned as an image.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "website_screenshot" says "screenshot": 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 "website_screenshot" says "screenshot" and "website": it reads web pages, which anyone can write.
    • untrusted-inputThe description's first sentence says "screenshot" 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
    Screenshot one public web page in a headless browser: desktop (1440x900) or mobile (390x844) viewport, PNG or JPEG, returned as an image. Viewport only, no logins or scripts; follows robots.txt and does not get past bot walls; at most one screenshot every 10 seconds across all callers. Paid only: $0.01 USDC per page. Paid calls made without a payment return isError with the x402 v2 PaymentRequired object (amount in USDC atomic units, network, payTo, HTTP endpoint); retry with the signed PaymentPayload in params._meta["x402/payment"]. Invalid input and calls where every item fails are never charged. Fetches follow robots.txt, use the User-Agent AdamHaleTools/1.0 and refuse private or internal addresses.

    Annotations the server declares

    • title: Website screenshot
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: 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.

216 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 private-data tools breaks every one.

Reads private data2
Reads files, mail, messages, databases, secrets, calendars or repositories.
Can send data out9
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-research__page_to_markdown",
      "mcp__web-research__tech_stack_lookup"
    ]
  }
}

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, 18:53 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
5
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 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://tools.adamhaleworks.workers.dev/mcp: tools/list returned 12 tools to an anonymous client, including seo_meta_tags_check (write), domain_intel (write), robots_txt_check (write), document_to_markdown (write), transcribe_short_audio (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "document_to_markdown" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "convert": a word for a change.

    What this check looks for

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 web-research https://tools.adamhaleworks.workers.dev/mcp
claude mcp add --transport http web-research https://tools.adamhaleworks.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-research__tech_stack_lookup",
      "mcp__web-research__ted_tender_search"
    ],
    "ask": [
      "mcp__web-research__seo_meta_tags_check",
      "mcp__web-research__url_status_check",
      "mcp__web-research__sitemap_urls",
      "mcp__web-research__rss_to_json",
      "mcp__web-research__page_to_markdown",
      "mcp__web-research__domain_intel",
      "mcp__web-research__robots_txt_check",
      "mcp__web-research__document_to_markdown",
      "mcp__web-research__transcribe_short_audio",
      "mcp__web-research__website_screenshot"
    ],
    "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-research. Review it before you use it.

Capability tags behind 12 rules
  • mcp__web-research__tech_stack_lookup private-data, untrusted-input
  • mcp__web-research__seo_meta_tags_check untrusted-input, outbound
  • mcp__web-research__url_status_check untrusted-input, outbound
  • mcp__web-research__sitemap_urls untrusted-input, outbound
  • mcp__web-research__rss_to_json untrusted-input, outbound
  • mcp__web-research__ted_tender_search untrusted-input
  • mcp__web-research__page_to_markdown private-data, untrusted-input, outbound
  • mcp__web-research__domain_intel untrusted-input
  • mcp__web-research__robots_txt_check untrusted-input, outbound
  • mcp__web-research__document_to_markdown untrusted-input, outbound
  • mcp__web-research__transcribe_short_audio untrusted-input, outbound
  • mcp__web-research__website_screenshot 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.workers.adamhaleworks.tools/web-research/verify?hash=9bfd3c1e30dfe2a7636cfdccf9d241434dbdd5f3ad1f4441c0dcfdcf95ec622d" | jq -e '.changed == false'

Pinned hash 9bfd3c1e30df, from Nov 15, 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.adamhaleworks.tools/web-research/changes.xml

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

Badge

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

Source: MCP Registry. Synced Oct 21, 2026, 18:12 UTC.

Adam Hale Tools: Web Research and Open Data MCP server: questions and answers

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

Is the Adam Hale Tools: Web Research and Open Data MCP server safe?

No scan can promise that. What its definitions show: 12 tools, 5 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Adam Hale Tools: Web Research and Open Data MCP server delete data?

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

Can the Adam Hale Tools: Web Research and Open Data 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 Adam Hale Tools: Web Research and Open Data MCP server have?

12 tools: 5 write, 7 read. seo_meta_tags_check, domain_intel, robots_txt_check, document_to_markdown, transcribe_short_audio, tech_stack_lookup, url_status_check, sitemap_urls and 4 more.

Does the Adam Hale Tools: Web Research and Open Data MCP server need sign-in or OAuth?

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

Does the Adam Hale Tools: Web Research and Open Data MCP server send data to outside services?

9 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): seo_meta_tags_check, url_status_check, sitemap_urls, rss_to_json, page_to_markdown, robots_txt_check and 3 more.

Has the Adam Hale Tools: Web Research and Open Data MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 15, 2026.