postbox-tools MCP server
com.postboxservices/postbox-toolspostboxservices.comstreamable-httpv0.2.0Scanned
Free email checks: 24 blacklists, spoofing grade, redirects, spam test, WHOIS, BIMI, AI readiness.
10 tools: 7 change things and 3 only read.
- Reads private data · 2
- Reads text others write · 9
- Can send data out · 1
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
7 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.
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 postbox-tools MCP server can do
The postbox-tools MCP server is published by postboxservices.com, a domain the MCP Registry verified. It has 10 tools. It can create or change data (7 tools: check_blacklist, check_spoofability, trace_redirect, create_mailtest and 3 more), but cannot delete data. 3 tools only read.
2 tools read private data (get_mailtest_result and analyze_eml); 9 tools bring in text other people can write (check_blacklist, check_spoofability, trace_redirect and 6 more); 1 tool can send data out of your system (trace_redirect). 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, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 19, 2026, version 0.2.0.
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.
10 tools
Changes things 7Claude Code: ask
analyze_emlRun a deliverability/content analysis on a raw RFC 822 email (.eml source: full headers + body).Reads private dataReads text others write1 finding
Why it is in this group
- The name "analyze_eml" says "analyze": a word for reading.
- The description's first verb is "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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 "run" and "email": it reads inbound email, which other people can write.
Findings
- Warn
The server marks "analyze_eml" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "analyze_eml" says "analyze": a word for reading.
Description, as the server wrote it Run a deliverability/content analysis on a raw RFC 822 email (.eml source: full headers + body). IMPORTANT LIMITS: with no live SMTP session, SPF, blacklist and reverse-DNS cannot be verified from a file - for the authoritative score use create_mailtest instead.
Annotations the server declares
- title: Analyze a raw email file (.eml)
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
check_ai_discoverabilityGrade how discoverable a website is to AI answer engines (ChatGPT search, Perplexity, Claude, Google AI Overviews, Copilot and others) from its public files: robots.txt access for …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 Grade how discoverable a website is to AI answer engines (ChatGPT search, Perplexity, Claude, Google AI Overviews, Copilot and others) from its public files: robots.txt access for each major AI crawler (answer-engine vs training), sitemap.xml, plus llms.txt and ai.txt as informational signals. Returns an A-F grade, per-crawler access and findings.
Annotations the server declares
- title: AI discoverability check (A-F grade)
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
check_bimiCheck a domain's BIMI setup: looks up the default._bimi TXT record, fetches the logo it points to (l=) and validates the SVG against the BIMI SVG Tiny Portable/Secure profile, and …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 Check a domain's BIMI setup: looks up the default._bimi TXT record, fetches the logo it points to (l=) and validates the SVG against the BIMI SVG Tiny Portable/Secure profile, and reports whether a certificate (a=, VMC or CMC) is referenced. Does not verify the certificate itself or the DMARC policy (BIMI also needs DMARC at enforcement - use check_spoofability for that).
Annotations the server declares
- title: BIMI record + logo check
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
check_blacklistCheck a domain against domain blacklists (Spamhaus DBL, SURBL, URIBL and others), or an IP address against 24 IP blacklists including Spamhaus ZEN, Barracuda and SpamCop.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 Check a domain against domain blacklists (Spamhaus DBL, SURBL, URIBL and others), or an IP address against 24 IP blacklists including Spamhaus ZEN, Barracuda and SpamCop. Checks the exact target given: domains are not resolved to IPs. Returns per-list listing status.
Annotations the server declares
- title: Email blacklist check
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
check_spoofabilityGrade how exposed a domain is to email spoofing and business email compromise, from its public DNS (SPF, DMARC policy strength, alignment, live lookalike domains).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 Grade how exposed a domain is to email spoofing and business email compromise, from its public DNS (SPF, DMARC policy strength, alignment, live lookalike domains). Returns an A-F grade with findings.
Annotations the server declares
- title: Spoofing / BEC exposure check (A-F grade)
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
create_mailtestCreate a disposable test address for a full email deliverability audit (score /10: SPF, DKIM, DMARC + alignment, blacklists, reverse DNS, SpamAssassin content, Gmail/Yahoo bulk-sen…No findings
Why it is in this group
- The name "create_mailtest" says "create": a word for a change.
Description, as the server wrote it Create a disposable test address for a full email deliverability audit (score /10: SPF, DKIM, DMARC + alignment, blacklists, reverse DNS, SpamAssassin content, Gmail/Yahoo bulk-sender compliance). The USER must then send an email from the system they want to test to the returned address, after which get_mailtest_result returns the score.
Annotations the server declares
- title: Start an email deliverability test
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
trace_redirectFollow a URL server-side through every HTTP redirect hop to its real final destination - per-hop status, IP, TLS and timing, plus phishing/deliverability flags (cross-domain jumps,…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 Follow a URL server-side through every HTTP redirect hop to its real final destination - per-hop status, IP, TLS and timing, plus phishing/deliverability flags (cross-domain jumps, https downgrades, meta/JS redirects). Fetching is SSRF-hardened (private ranges blocked, HTTPS-only, per-hop validation); how it works: https://redirect.postboxservices.com/
Annotations the server declares
- title: URL redirect chain tracer
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
Only reads 3Show 3 read-only tools
get_domain_ageGet a domain's registration date and age (young domains have weak sending reputation).Reads text others writeNo findings
Why it is in this group
- The name "get_domain_age" says "get": a word for reading.
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 Get a domain's registration date and age (young domains have weak sending reputation).
Annotations the server declares
- title: Domain age lookup
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
get_mailtest_resultFetch the score and breakdown of a mail test created with create_mailtest, once the user has sent their email to the disposable address.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_mailtest_result" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "fetch" and "mail": it reads mail.
- untrusted-inputThe description's first sentence says "fetch" and "mail": it reads inbound email, which other people can write.
Description, as the server wrote it Fetch the score and breakdown of a mail test created with create_mailtest, once the user has sent their email to the disposable address.
Annotations the server declares
- title: Get an email deliverability test result
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
whois_lookupWHOIS summary for a domain: registrar, created/updated/expires dates, nameservers, DNSSEC, status flags.Reads text others writeNo findings
Why it is in this group
- The name "whois_lookup" says "lookup": a word for reading.
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 WHOIS summary for a domain: registrar, created/updated/expires dates, nameservers, DNSSEC, status flags.
Annotations the server declares
- title: WHOIS lookup
- readOnlyHint: true
- destructiveHint: false
- 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.
18 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write9
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__postbox-tools__trace_redirect"
]
}
}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.
Looked at Nov 20, 2026, 18:44 UTC, unchanged since Nov 6, 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
- 7
- 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 7 tools that change things (7 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.postboxservices.com/mcp: tools/list returned 10 tools to an anonymous client, including check_blacklist (write), check_spoofability (write), trace_redirect (write), create_mailtest (write), analyze_eml (write) and 2 more
Posture changes
- Nov 6, 2026
- Tools that change things, listed without credentials: 5 to 7
Findings
Matches of fixed checks, with the text they matched.
- Warnanalyze_eml
The server marks "analyze_eml" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "analyze_eml" says "analyze": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools10 changed.~10 changedView diff
- Changed:analyze_emlChanges thingsannotations
- Changed:check_ai_discoverabilityChanges thingsannotations
- Changed:check_bimiChanges thingsannotations
- Changed:check_blacklistChanges thingsannotations
- Changed:check_spoofabilityChanges thingsannotations
- Changed:create_mailtestChanges thingsannotations
- Changed:get_domain_ageOnly readsannotations
- Changed:get_mailtest_resultOnly readsannotations
- Changed:trace_redirectChanges thingsannotations
- Changed:whois_lookupOnly readsannotations
PostureRemote posture changed. Tools that change things, listed without credentials: 5 -> 7.View diff
- Tools that change things, listed without credentials: 5 to 7
Tools2 added.+2 addedView diff
- Added:check_ai_discoverabilityChanges things
- Added:check_bimiChanges things
Install
Pinned to version 0.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http postbox-tools https://mcp.postboxservices.com/mcpclaude mcp add --transport http postbox-tools https://mcp.postboxservices.com/mcpRun 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.
{
"permissions": {
"allow": [
"mcp__postbox-tools__get_mailtest_result",
"mcp__postbox-tools__get_domain_age",
"mcp__postbox-tools__whois_lookup"
],
"ask": [
"mcp__postbox-tools__check_blacklist",
"mcp__postbox-tools__check_spoofability",
"mcp__postbox-tools__trace_redirect",
"mcp__postbox-tools__create_mailtest",
"mcp__postbox-tools__analyze_eml",
"mcp__postbox-tools__check_bimi",
"mcp__postbox-tools__check_ai_discoverability"
],
"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 postbox-tools. Review it before you use it.
Capability tags behind 9 rules
- mcp__postbox-tools__check_blacklist untrusted-input
- mcp__postbox-tools__check_spoofability untrusted-input
- mcp__postbox-tools__trace_redirect untrusted-input, outbound
- mcp__postbox-tools__get_mailtest_result private-data, untrusted-input
- mcp__postbox-tools__analyze_eml private-data, untrusted-input
- mcp__postbox-tools__get_domain_age untrusted-input
- mcp__postbox-tools__whois_lookup untrusted-input
- mcp__postbox-tools__check_bimi untrusted-input
- mcp__postbox-tools__check_ai_discoverability 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/com.postboxservices/postbox-tools/verify?hash=87940b5dc556e412bf4e0a2fad8d42092b888906854dd5e46062f42e1fefb600" | jq -e '.changed == false'Pinned hash 87940b5dc556, from Nov 19, 2026, 17:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.postboxservices/postbox-tools/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.postboxservices/postbox-tools)Source: MCP Registry. Synced Nov 5, 2026, 20:17 UTC.
postbox-tools MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the postbox-tools MCP server safe?
- No scan can promise that. What its definitions show: 10 tools, 7 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 postbox-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 postbox-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 postbox-tools MCP server have?
- 10 tools: 7 write, 3 read. check_blacklist, check_spoofability, trace_redirect, create_mailtest, analyze_eml, check_bimi, check_ai_discoverability, get_mailtest_result and 2 more.
Does the postbox-tools MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the postbox-tools MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): trace_redirect.
Has the postbox-tools MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 19, 2026. Every change is on this page and in its Atom feed.