Skip to content

BRAINIAC Web & Page Intelligence MCP server

software.brainiac/web-intelligencebrainiac.softwarestreamable-httpv1.0.1Scanned

Paid Web & Page Intelligence API via x402. Unpaid tool calls return 402.

6 tools: 1 change things and 5 only read.

Tools: 0 delete, 0 irreversible, 1 write, 5 read.
  • Reads private data · 1
  • Reads text others write · 6
  • Can send data out · 5
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here changes things. Govern it.

  • 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 BRAINIAC Web & Page Intelligence MCP server can do

The BRAINIAC Web & Page Intelligence MCP server is published by brainiac.software, a domain the MCP Registry verified. It has 6 tools. It can create or change data (1 tool: web-intelligence_structured-page-extract), but cannot delete data. 5 tools only read.

1 tool reads private data (web-intelligence_website-contact-extract); 6 tools bring in text other people can write (web-intelligence_url-to-markdown, web-intelligence_structured-page-extract, web-intelligence_page-change-detect and 3 more); 5 tools can send data out of your system (web-intelligence_url-to-markdown, web-intelligence_structured-page-extract, web-intelligence_page-change-detect and 2 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, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 20, 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.

6 tools

Changes things 1Claude Code: ask
  • web-intelligence_structured-page-extractExtract caller-defined fields from one public webpage.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 caller-defined fields from one public webpage. A field is returned only when a selector, JSON-LD property, or matching meta tag contains it. Otherwise the value is null. Price $0.05 USDC. POST /api/v1/web-intelligence/structured-page-extract. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Extract structured page data
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 5Show 5 read-only tools
  • web-intelligence_page-change-detectFetch a public page and compare its Markdown with a caller-supplied previous snapshot.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 "web-intelligence_page-change-detect" says "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 page and compare its Markdown with a caller-supplied previous snapshot. The snapshot is not stored. The result lists added and removed lines and does not rank their importance. Price $0.05 USDC. POST /api/v1/web-intelligence/page-change-detect. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Detect page changes
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • web-intelligence_sitemap-content-indexFetch one public sitemap or sitemap index and return the listed URLs with lastmod, changefreq, and priority when those fields are present.Reads text others writeNo 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 "web-intelligence_sitemap-content-index" says "web": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Fetch one public sitemap or sitemap index and return the listed URLs with lastmod, changefreq, and priority when those fields are present. Page URLs are not fetched. Price $0.03 USDC. POST /api/v1/web-intelligence/sitemap-content-index. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Index sitemap content
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • web-intelligence_url-to-markdownFetch one public webpage and convert its readable HTML into Markdown.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 "web-intelligence_url-to-markdown" says "web": it reads web pages, which anyone can write.
    • untrusted-inputThe description's first sentence says "fetch" and "webpage": 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 one public webpage and convert its readable HTML into Markdown. Scripts are not run, and missing text is not filled in. Price $0.04 USDC. POST /api/v1/web-intelligence/url-to-markdown. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Convert URL to Markdown
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • web-intelligence_website-contact-extractRead publicly displayed emails, tel: links, address elements, and structured contact data from one public page.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 name "web-intelligence_website-contact-extract" says "contact": it reads contacts.
    • private-dataThe description's first sentence says "read" and "email": it reads mail.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "web-intelligence_website-contact-extract" says "web": it reads web pages, which anyone can write.
    • untrusted-inputThe description's first sentence says "read" and "email": it reads inbound email, which other people 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
    Read publicly displayed emails, tel: links, address elements, and structured contact data from one public page. Linked pages are not crawled, and missing contacts are not guessed. Price $0.04 USDC. POST /api/v1/web-intelligence/website-contact-extract. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Extract website contacts
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • web-intelligence_website-metadata-extractRead title, description, canonical URL, Open Graph tags, language, and robots directives from one public page.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 "web-intelligence_website-metadata-extract" says "web": it reads web pages, which anyone can write.
    • untrusted-inputThe description's first sentence says "read" 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
    Read title, description, canonical URL, Open Graph tags, language, and robots directives from one public page. Absent tags are null. robots.txt is not fetched. Price $0.02 USDC. POST /api/v1/web-intelligence/website-metadata-extract. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Extract website metadata
    • 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.

30 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.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__web-intelligence__web-intelligence_website-contact-extract"
    ]
  }
}

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, 19:35 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
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
1
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 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://www.brainiac.software/mcp/web-intelligence: tools/list returned 6 tools to an anonymous client, including web-intelligence_structured-page-extract (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.

  1. Tools6 changed.~6 changedView diff

Install

Pinned to version 1.0.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http web-intelligence https://www.brainiac.software/mcp/web-intelligence
claude mcp add --transport http web-intelligence https://www.brainiac.software/mcp/web-intelligence

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-intelligence__web-intelligence_sitemap-content-index"
    ],
    "ask": [
      "mcp__web-intelligence__web-intelligence_url-to-markdown",
      "mcp__web-intelligence__web-intelligence_structured-page-extract",
      "mcp__web-intelligence__web-intelligence_page-change-detect",
      "mcp__web-intelligence__web-intelligence_website-metadata-extract",
      "mcp__web-intelligence__web-intelligence_website-contact-extract"
    ],
    "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-intelligence. Review it before you use it.

Capability tags behind 6 rules
  • mcp__web-intelligence__web-intelligence_url-to-markdown untrusted-input, outbound
  • mcp__web-intelligence__web-intelligence_structured-page-extract untrusted-input, outbound
  • mcp__web-intelligence__web-intelligence_page-change-detect untrusted-input, outbound
  • mcp__web-intelligence__web-intelligence_website-metadata-extract untrusted-input, outbound
  • mcp__web-intelligence__web-intelligence_website-contact-extract private-data, untrusted-input, outbound
  • mcp__web-intelligence__web-intelligence_sitemap-content-index 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/software.brainiac/web-intelligence/verify?hash=659164f6ff9020cbb388d8af6c7b33862ee57e9a05bcca7e01c3d583d26499a0" | jq -e '.changed == false'

Pinned hash 659164f6ff90, from Nov 20, 2026, 01:19 UTC.

Watch

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

https://radar.anlyon.com/servers/software.brainiac/web-intelligence/changes.xml

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

Badge

Anlyon Radar badge for software.brainiac/web-intelligence
[![Anlyon Radar](https://radar.anlyon.com/badge/software.brainiac/web-intelligence.svg)](https://radar.anlyon.com/servers/software.brainiac/web-intelligence)

Source: MCP Registry. Synced Nov 20, 2026, 01:18 UTC.

BRAINIAC Web & Page Intelligence MCP server: questions and answers

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

Is the BRAINIAC Web & Page Intelligence MCP server safe?

No scan can promise that. What its definitions show: 6 tools, 1 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 BRAINIAC Web & Page Intelligence MCP server delete data?

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

Can the BRAINIAC Web & Page Intelligence 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 BRAINIAC Web & Page Intelligence MCP server have?

6 tools: 1 write, 5 read. web-intelligence_structured-page-extract, web-intelligence_url-to-markdown, web-intelligence_page-change-detect, web-intelligence_website-metadata-extract, web-intelligence_website-contact-extract and web-intelligence_sitemap-content-index.

Does the BRAINIAC Web & Page Intelligence MCP server need sign-in or OAuth?

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

Does the BRAINIAC Web & Page Intelligence MCP server send data to outside services?

5 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): web-intelligence_url-to-markdown, web-intelligence_structured-page-extract, web-intelligence_page-change-detect, web-intelligence_website-metadata-extract and web-intelligence_website-contact-extract.

Has the BRAINIAC Web & Page Intelligence MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.