email-spam-tester MCP server
io.github.serg-tanichev/email-spam-testerserg-tanichevstreamable-httpv1.0.0Scanned
Test an email before it goes out: a disposable address, 41 checks with RFC citations, a fix plan.
4 tools: 1 change things and 3 only read.
- Reads private data · 3
- Reads text others write · 3
- Can send data out · 0
- 1 finding
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.
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 email-spam-tester MCP server can do
The email-spam-tester MCP server is published by the GitHub account serg-tanichev. It has 4 tools. It can create or change data (1 tool: get_test_address), but cannot delete data. 3 tools only read.
3 tools read private data (get_test_address, wait_for_report and get_message_source); 3 tools bring in text other people can write (get_test_address, wait_for_report and get_message_source).
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 20, 2026, version 1.0.0.
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.
4 tools
Changes things 1Claude Code: ask
get_test_addressReserve a single-use address to send a draft email to, for a full check.Reads private dataReads text others write1 finding
Why it is in this group
- The name "get_test_address" says "get": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
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 "email": it reads inbound email, which other people can write.
Findings
- Warn
The server marks "get_test_address" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "get_test_address" says "get": a word for reading.
Description, as the server wrote it Reserve a single-use address to send a draft email to, for a full check. Returns the address and the URL its report will appear at. The address accepts exactly one message and expires after an hour. The email has to be sent by the person, from the platform or mailbox they really send from: half the checks read what that platform adds. The report covers 42 checks (SPF, DKIM, DMARC, reverse DNS, TLS, blocklists, content, links, the Gmail and Yahoo bulk-sender rules) and a plan of what to fix. lang is decided now because the message arrives minutes later over SMTP, which carries no hint of who is waiting for it. What wait_for_report returns quotes check lines in English whatever it is set to; the person following report_url sees their own language.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: false
- title: Get a test address
Only reads 3Show 3 read-only tools
get_message_sourceThe message exactly as it was received: headers, both bodies, source.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_message_source" says "get": a word for reading.
What it can reach
- private-dataThe name "get_message_source" says "get" and "message": it reads messages.
- private-dataThe description's first sentence says "message": it reads messages.
- untrusted-inputThe name "get_message_source" says "get" and "message": it reads messages, which other people can write.
- untrusted-inputThe description's first sentence says "message": it reads messages, which other people can write.
Description, as the server wrote it The message exactly as it was received: headers, both bodies, source. Useful when a finding points at a header and the agent needs to see what it actually sent rather than what it believes it sent. The message is kept for an hour after it arrives and then deleted; within that hour anyone with the slug can read it. After that only the report remains.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Read the received message
get_reportRead a report by its slug without waiting, with provider placement so far.No findings
Why it is in this group
- The name "get_report" says "get": a word for reading.
Description, as the server wrote it Read a report by its slug without waiting, with provider placement so far. The report stays at its link for good and anyone with the link can read it: the checks, the score, the fix plan, and the subject and sender of the email.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Read a report
wait_for_reportWait until the message arrives and has been analysed, then summarise it.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "wait_for_report" says "wait": a word for reading.
What it can reach
- private-dataThe description's first sentence says "wait" and "message": it reads messages.
- untrusted-inputThe description's first sentence says "wait" and "message": it reads messages, which other people can write.
Description, as the server wrote it Wait until the message arrives and has been analysed, then summarise it. Call it after the email has been sent to the address from get_test_address. Blocks rather than returning "not ready yet": an agent told to poll writes a sleep loop and usually gives up before the analysis finishes. Provider placement keeps filling in for up to 30 minutes after the report; get_report reads the latest.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Wait for the report
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 outbound.
- Reads private data3
- 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 out0
- 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.
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, 19:10 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
- 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.
What this check looks forMatched text
https://email-spam-tester.com/mcp: tools/list returned 4 tools to an anonymous client, including get_test_address (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnget_test_address
The server marks "get_test_address" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "get_test_address" says "get": a word for reading.
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 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http email-spam-tester https://email-spam-tester.com/mcpclaude mcp add --transport http email-spam-tester https://email-spam-tester.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__email-spam-tester__wait_for_report",
"mcp__email-spam-tester__get_report",
"mcp__email-spam-tester__get_message_source"
],
"ask": [
"mcp__email-spam-tester__get_test_address"
],
"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-spam-tester. Review it before you use it.
Capability tags behind 3 rules
- mcp__email-spam-tester__get_test_address private-data, untrusted-input
- mcp__email-spam-tester__wait_for_report private-data, untrusted-input
- mcp__email-spam-tester__get_message_source private-data, 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/io.github.serg-tanichev/email-spam-tester/verify?hash=8e62879772a6fad797e2a280c3f12d1dbdf6a9575a1ac968f3d69e05154b6450" | jq -e '.changed == false'Pinned hash 8e62879772a6, from Nov 20, 2026, 12:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.serg-tanichev/email-spam-tester/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.serg-tanichev/email-spam-tester)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:49 UTC.
email-spam-tester MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the email-spam-tester MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 1 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 email-spam-tester MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the email-spam-tester 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 email-spam-tester MCP server have?
- 4 tools: 1 write, 3 read. get_test_address, wait_for_report, get_report and get_message_source.
Does the email-spam-tester MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the email-spam-tester MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the email-spam-tester MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.