Skip to content

BRAINIAC Email & Communication Security MCP server

software.brainiac/email-securitybrainiac.softwarestreamable-httpv1.0.1Scanned

Paid Email & Communication Security API via x402. Unpaid tool calls return 402.

8 tools: 5 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 5 write, 3 read.
  • Reads private data · 3
  • Reads text others write · 8
  • Can send data out · 8
  • No findings

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 BRAINIAC Email & Communication Security MCP server can do

The BRAINIAC Email & Communication Security MCP server is published by brainiac.software, a domain the MCP Registry verified. It has 8 tools. It can create or change data (5 tools: email-security_spoofing-detect, email-security_phishing-signal-detect, email-security_bec-pattern-detect, email-security_domain-impersonation-check and 1 more), but cannot delete data. 3 tools only read.

3 tools read private data (email-security_header-forensics, email-security_url-chain-analyze and email-security_attachment-risk-analyze); 8 tools bring in text other people can write (email-security_header-forensics, email-security_spoofing-detect, email-security_phishing-signal-detect and 5 more); 8 tools can send data out of your system (email-security_header-forensics, email-security_spoofing-detect, email-security_phishing-signal-detect and 5 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.

8 tools

Changes things 5Claude Code: ask
  • email-security_bec-pattern-detectDetect Business Email Compromise patterns such as payment-change language, executive persona cues, external Reply-To, and lookalike sender domains from supplied mail.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
    Detect Business Email Compromise patterns such as payment-change language, executive persona cues, external Reply-To, and lookalike sender domains from supplied mail. Price $0.05 USDC. POST /api/v1/email-security/bec-pattern-detect. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Detect BEC patterns
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • email-security_conversation-tamper-detectIdentify inconsistencies between supplied email conversation copies (missing messages, body hash mismatches, header field divergence).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
    Identify inconsistencies between supplied email conversation copies (missing messages, body hash mismatches, header field divergence). Export artifacts are distinguished from confirmed tampering. Price $0.05 USDC. POST /api/v1/email-security/conversation-tamper-detect. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Detect conversation tampering
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • email-security_domain-impersonation-checkIdentify domains resembling supplied company or brand domains using edit distance, hyphen variants, homoglyph folding, and brand-token embedding.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
    Identify domains resembling supplied company or brand domains using edit distance, hyphen variants, homoglyph folding, and brand-token embedding. Resemblance is not proof of abuse. Price $0.03 USDC. POST /api/v1/email-security/domain-impersonation-check. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Check domain impersonation
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • email-security_phishing-signal-detectIdentify phishing indicators in caller-supplied email content and URLs (urgency phrases, lookalike hosts, IP URLs, password forms).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
    Identify phishing indicators in caller-supplied email content and URLs (urgency phrases, lookalike hosts, IP URLs, password forms). Indicators are not confirmed malicious activity. Price $0.04 USDC. POST /api/v1/email-security/phishing-signal-detect. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Detect phishing signals
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • email-security_spoofing-detectDetect sender spoofing indicators from supplied SPF/DKIM/DMARC authentication results and optional public DNS TXT evidence.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
    Detect sender spoofing indicators from supplied SPF/DKIM/DMARC authentication results and optional public DNS TXT evidence. Not a confirmed spoof verdict without multi-signal evidence. Price $0.05 USDC. POST /api/v1/email-security/spoofing-detect. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Detect email spoofing indicators
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 3Show 3 read-only tools
  • email-security_attachment-risk-analyzeInspect caller-supplied attachment filenames, metadata, and local magic-byte structures for suspicious patterns.Reads private dataReads text others writeCan send data outNo findings

    Why it is in this group

    • The name "email-security_attachment-risk-analyze" says "analyze": a word for reading.

    What it can reach

    • private-dataThe name "email-security_attachment-risk-analyze" says "analyze" and "email": it reads mail.
    • private-dataThe input names a file (input.file), and the tool reads: it reads files.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "email-security_attachment-risk-analyze" says "analyze" and "email": it reads inbound email, which other people 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
    Inspect caller-supplied attachment filenames, metadata, and local magic-byte structures for suspicious patterns. No external sandbox or scanner is used. Price $0.04 USDC. POST /api/v1/email-security/attachment-risk-analyze. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Analyze email attachment risk
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • email-security_header-forensicsAnalyze caller-supplied email headers for routing hops and suspicious inconsistencies (From/Return-Path/Reply-To, auth results, dates).Reads private dataReads text others writeCan send data outNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe name "email-security_header-forensics" says "email": it reads mail.
    • private-dataThe description's first sentence says "analyze" and "email": it reads mail.
    • private-dataThe input names a file (input.file), and the tool reads: it reads files.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "email-security_header-forensics" says "email": it reads inbound email, which other people can write.
    • untrusted-inputThe description's first sentence says "analyze" and "email": it reads inbound email, which other people 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
    Analyze caller-supplied email headers for routing hops and suspicious inconsistencies (From/Return-Path/Reply-To, auth results, dates). Indicators only—not confirmed malice. Price $0.04 USDC. POST /api/v1/email-security/header-forensics. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Analyze email headers
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • email-security_url-chain-analyzeAnalyze caller-supplied redirect hops or optionally follow public URLs with strict SSRF protections.Reads private dataReads text others writeCan send data outNo findings

    Why it is in this group

    • The name "email-security_url-chain-analyze" says "analyze": a word for reading.

    What it can reach

    • private-dataThe name "email-security_url-chain-analyze" says "analyze" and "email": it reads mail.
    • private-dataThe input names a file (input.file), and the tool reads: it reads files.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "email-security_url-chain-analyze" says "analyze" and "email": it reads inbound email, which other people 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
    Analyze caller-supplied redirect hops or optionally follow public URLs with strict SSRF protections. Never sends email content to external scanners. Price $0.05 USDC. POST /api/v1/email-security/url-chain-analyze. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Analyze email URL redirect chains
    • 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.

192 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 3 private-data tools breaks every one.

Reads private data3
Reads files, mail, messages, databases, secrets, calendars or repositories.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__email-security__email-security_attachment-risk-analyze",
      "mcp__email-security__email-security_header-forensics",
      "mcp__email-security__email-security_url-chain-analyze"
    ]
  }
}

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, 19:32 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
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://www.brainiac.software/mcp/email-security: tools/list returned 8 tools to an anonymous client, including email-security_spoofing-detect (write), email-security_phishing-signal-detect (write), email-security_bec-pattern-detect (write), email-security_domain-impersonation-check (write), email-security_conversation-tamper-detect (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. Tools8 changed.~8 changedView diff

Install

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

claude mcp add --transport http email-security https://www.brainiac.software/mcp/email-security
claude mcp add --transport http email-security https://www.brainiac.software/mcp/email-security

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": [],
    "ask": [
      "mcp__email-security__email-security_header-forensics",
      "mcp__email-security__email-security_spoofing-detect",
      "mcp__email-security__email-security_phishing-signal-detect",
      "mcp__email-security__email-security_bec-pattern-detect",
      "mcp__email-security__email-security_domain-impersonation-check",
      "mcp__email-security__email-security_url-chain-analyze",
      "mcp__email-security__email-security_attachment-risk-analyze",
      "mcp__email-security__email-security_conversation-tamper-detect"
    ],
    "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 email-security. Review it before you use it.

Capability tags behind 8 rules
  • mcp__email-security__email-security_header-forensics private-data, untrusted-input, outbound
  • mcp__email-security__email-security_spoofing-detect untrusted-input, outbound
  • mcp__email-security__email-security_phishing-signal-detect untrusted-input, outbound
  • mcp__email-security__email-security_bec-pattern-detect untrusted-input, outbound
  • mcp__email-security__email-security_domain-impersonation-check untrusted-input, outbound
  • mcp__email-security__email-security_url-chain-analyze private-data, untrusted-input, outbound
  • mcp__email-security__email-security_attachment-risk-analyze private-data, untrusted-input, outbound
  • mcp__email-security__email-security_conversation-tamper-detect 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/software.brainiac/email-security/verify?hash=91ebb38eeb9dd814ad3469696f56fbfa11b48677a33d0324fadac49977c7c5d4" | jq -e '.changed == false'

Pinned hash 91ebb38eeb9d, 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/email-security/changes.xml

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

Badge

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

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

BRAINIAC Email & Communication Security MCP server: questions and answers

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

Is the BRAINIAC Email & Communication Security MCP server safe?

No scan can promise that. What its definitions show: 8 tools, 5 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 Email & Communication Security 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 Email & Communication Security 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 Email & Communication Security MCP server have?

8 tools: 5 write, 3 read. email-security_spoofing-detect, email-security_phishing-signal-detect, email-security_bec-pattern-detect, email-security_domain-impersonation-check, email-security_conversation-tamper-detect, email-security_header-forensics, email-security_url-chain-analyze and email-security_attachment-risk-analyze.

Does the BRAINIAC Email & Communication Security MCP server need sign-in or OAuth?

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

Does the BRAINIAC Email & Communication Security MCP server send data to outside services?

8 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): email-security_header-forensics, email-security_spoofing-detect, email-security_phishing-signal-detect, email-security_bec-pattern-detect, email-security_domain-impersonation-check, email-security_url-chain-analyze and 2 more.

Has the BRAINIAC Email & Communication Security 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.