Skip to content
anlyon.devby Anlyon

Web Research Agent

io.github.elaysuu/web-research-agent-mcpelaysuustreamable-httpv0.3.0Scanned

Company profiles, site audits and page-to-JSON extraction for AI agents.

6 tools: 2 change things and 4 only read.

Tools: 0 delete, 0 irreversible, 2 write, 4 read.
  • Reads private data · 0
  • Reads text others write · 3
  • Can send data out · 5
  • No findings

Anlyon alternative

2 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 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 →
Compare with similar serversMarkdownJSONReport this listing

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.

6 tools

Changes things 2Claude Code: ask
  • company_profileResearch a company from its website: name, description, socials, emails, key pages, pricing mentions, tech stack.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
    Research a company from its website: name, description, socials, emails, key pages, pricing mentions, tech stack.
  • site_auditAudit a web page: SEO, performance hints, security headers, broken internal links; returns score 0-100 and issues.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
    Audit a web page: SEO, performance hints, security headers, broken internal links; returns score 0-100 and issues.
Only reads 4Show 4 read-only tools
  • email_checkValidate an email address or domain via live DNS: syntax, MX/null-MX, SPF, DMARC policy, disposable/free/role flags, deliverability verdict and 0-100 score.No findings

    Why it is in this group

    • The description's first verb is "validate": a word for reading.
    Description, as the server wrote it
    Validate an email address or domain via live DNS: syntax, MX/null-MX, SPF, DMARC policy, disposable/free/role flags, deliverability verdict and 0-100 score. No SMTP probe.
  • page_diffMonitor a page for changes: returns normalized text + SHA-256 content_hash; pass previous_text (or previous_hash) from an earlier call to get changed flag and added/removed lines.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "page_diff" says "diff": 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
    Monitor a page for changes: returns normalized text + SHA-256 content_hash; pass previous_text (or previous_hash) from an earlier call to get changed flag and added/removed lines.
  • page_to_jsonFetch a web page and return structured JSON: meta, Open Graph, JSON-LD, headings, links, images, clean text.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 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 web page and return structured JSON: meta, Open Graph, JSON-LD, headings, links, images, clean text.
  • sitemap_urlsList a site's URLs from its sitemaps (robots.txt Sitemap: lines, nested indexes, text sitemaps) with lastmod/changefreq/priority; optional since date filter.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 name "sitemap_urls" 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
    List a site's URLs from its sitemaps (robots.txt Sitemap: lines, nested indexes, text sitemaps) with lastmod/changefreq/priority; optional since date filter.

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 out5
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.

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.

All changes to this server

Install

Pinned to version 0.3.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http web-research-agent https://web-research-agent-mcp.mcpize.run/mcp
claude mcp add --transport http web-research-agent https://web-research-agent-mcp.mcpize.run/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-agent__email_check"
    ],
    "ask": [
      "mcp__web-research-agent__company_profile",
      "mcp__web-research-agent__site_audit",
      "mcp__web-research-agent__page_to_json",
      "mcp__web-research-agent__sitemap_urls",
      "mcp__web-research-agent__page_diff"
    ],
    "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-agent. Review it before you use it.

Capability tags behind 5 rules
  • mcp__web-research-agent__company_profile outbound
  • mcp__web-research-agent__site_audit outbound
  • mcp__web-research-agent__page_to_json untrusted-input, outbound
  • mcp__web-research-agent__sitemap_urls untrusted-input, outbound
  • mcp__web-research-agent__page_diff 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://anlyon.dev/api/v1/servers/io.github.elaysuu/web-research-agent-mcp/verify?hash=bac7c29b03ce958186452fb55b42d2b980908cec527631a9922dc077b3489ea6" | jq -e '.changed == false'

Pinned hash bac7c29b03ce, from Nov 2, 2026, 19:18 UTC.

Watch

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

https://anlyon.dev/servers/io.github.elaysuu/web-research-agent-mcp/changes.xml

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

Badge

anlyon.dev badge for io.github.elaysuu/web-research-agent-mcp
[![anlyon.dev](https://anlyon.dev/badge/io.github.elaysuu/web-research-agent-mcp.svg)](https://anlyon.dev/servers/io.github.elaysuu/web-research-agent-mcp)

Source: MCP Registry · repository. Synced Nov 2, 2026, 19:18 UTC.