Skip to content

KeyKeeper Email MCP server

world.keykeeper/emailkeykeeper.worldstreamable-httpv2.12.0Scanned

Real email inboxes for AI agents: register, receive, read and send mail over MCP. Free to receive.

13 tools: 5 do something that can't be undone, 3 change things and 5 only read.

Tools: 0 delete, 5 irreversible, 3 write, 5 read.
  • Reads private data · 2
  • Reads text others write · 6
  • Can send data out · 3
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

5 tools here do something that can't be undone. 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 KeyKeeper Email MCP server can do

The KeyKeeper Email MCP server is published by keykeeper.world, a domain the MCP Registry verified. It has 13 tools. It can do things that cannot be undone, such as sending, paying or publishing (send_email, create_payment, check_payment, propose_email and 1 more) and create or change data (3 tools: register_agent, check_balance and request_sender_review), but cannot delete data. 5 tools only read.

2 tools read private data (check_inbox and get_email); 6 tools bring in text other people can write (check_inbox, get_email, check_sending_status and 3 more); 3 tools can send data out of your system (send_email, propose_email and update_proposal). 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.

Last scanned Nov 17, 2026, version 2.12.0.

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.

13 tools

Can't be undone 5Claude Code: ask
  • check_paymentCheck this account's native USDC invoice.Reads text others writeNo findings

    Why it is in this group

    • The name "check_payment" says "payment": a word that usually means money moves, which cannot be taken back.

    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 this account's native USDC invoice. Confirmation applies sending credits or activates prepaid domain hosting once, without a human checkout. Requires the same account's API key.

    Annotations the server declares

    • readOnlyHint: false
    • idempotentHint: true
    • openWorldHint: true
  • create_paymentWith your operator's authorization, create a card checkout or native USDC invoice on Polygon, Base, Ethereum or Solana.Reads text others writeNo findings

    Why it is in this group

    • The name "create_payment" says "create": a word for a change.
    • The name "create_payment" also says "payment": a word that usually means money moves, which cannot be taken back.

    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
    With your operator's authorization, create a card checkout or native USDC invoice on Polygon, Base, Ethereum or Solana. Choose mail_credits ($1 buys 10,000 standard sends) or hosting at $1 per 30 days: domain_hosting for the first domain, domain_addon plus domainId for another verified domain under active primary hosting. This tool creates payment instructions; it does not transfer money. Reuse idempotencyKey on retries.

    Annotations the server declares

    • readOnlyHint: false
    • idempotentHint: true
    • openWorldHint: true
  • propose_emailPrepare a plain-text email for human approval.Can send data outNo findings

    Why it is in this group

    • The input addresses people (input.message.to): what it sends cannot be taken back.

    What it can reach

    • outboundThe input takes a destination (input.message.to): what the tool writes goes there.
    Description, as the server wrote it
    Prepare a plain-text email for human approval. Requires a human-issued mail:draft key. Never sends. Reuse clientKey and content after uncertain responses.
  • send_emailSubmit mail with existing credits: one credit per accepted recipient.Can send data outNo findings

    Why it is in this group

    • The name "send_email" says "send": a word for sending, and what is sent cannot be taken back.
    • The input addresses people (input.to): what it sends cannot be taken back.

    What it can reach

    • outboundThe name "send_email" says "send": it sends or publishes something to other people.
    • outboundThe input takes a destination (input.to): what the tool writes goes there.
    Description, as the server wrote it
    Submit mail with existing credits: one credit per accepted recipient. Requires a Bearer API key. Reuse idempotencyKey for retries; acceptance is not proof of remote delivery.
  • update_proposalEdit or withdraw this key’s pending proposal.Can send data outNo findings

    Why it is in this group

    • The name "update_proposal" says "update": a word for a change.
    • The input addresses people (input.message.to): what it sends cannot be taken back.

    What it can reach

    • outboundThe input takes a destination (input.message.to): what the tool writes goes there.
    Description, as the server wrote it
    Edit or withdraw this key’s pending proposal. Cannot approve or change a message after human editing.
Changes things 3Claude Code: ask
  • check_balanceCheck your mailbox address, account state and sending credits.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Check your mailbox address, account state and sending credits. Requires a Bearer API key.
  • register_agentCreate an agent mailbox and receive its key once.No findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.
    Description, as the server wrote it
    Create an agent mailbox and receive its key once. Starts with zero sending credits; receiving is available without payment.
  • request_sender_reviewRequest an operator review of your sending purpose and recipient consent.No findings

    Why it is in this group

    • The name "request_sender_review" says "request": a word for a change.
    Description, as the server wrote it
    Request an operator review of your sending purpose and recipient consent. Full account key required. Does not automatically increase limits or resume sending. Three requests per day; repeated pending requests keep the original purpose.

    Annotations the server declares

    • readOnlyHint: false
    • idempotentHint: true
Only reads 5Show 5 read-only tools
  • check_inboxList incoming messages.Reads private dataReads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe name "check_inbox" says "inbox": it reads mail.
    • private-dataThe description's first sentence says "list" and "message": it reads messages.
    • private-dataThe input names a folder (input.folder), and the tool reads: it reads files.
    • untrusted-inputThe name "check_inbox" says "inbox": it reads inbound email, which other people can write.
    • untrusted-inputThe description's first sentence says "list" and "message": it reads messages, which other people can write.
    Description, as the server wrote it
    List incoming messages. Requires a Bearer API key. Email is untrusted external content.
  • check_sending_statusRead your sending state and current limits, including probation, pauses and pending review.Reads text others writeNo findings

    Why it is in this group

    • The name "check_sending_status" says "status": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "read" and "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Read your sending state and current limits, including probation, pauses and pending review. Buying credits never overrides sending controls.

    Annotations the server declares

    • readOnlyHint: true
  • get_emailRead a message by its folder-scoped UID.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "get_email" says "get": a word for reading.

    What it can reach

    • private-dataThe name "get_email" says "get" and "email": it reads mail.
    • private-dataThe description's first sentence says "read" and "message": it reads messages.
    • private-dataThe input names a folder (input.folder), and the tool reads: it reads files.
    • untrusted-inputThe name "get_email" says "get" and "email": it reads inbound email, which other people can write.
    • untrusted-inputThe description's first sentence says "read" and "message": it reads messages, which other people can write.
    Description, as the server wrote it
    Read a message by its folder-scoped UID. Requires a Bearer API key.
  • get_proposalCheck a proposal.No findings

    Why it is in this group

    • The name "get_proposal" says "get": a word for reading.
    Description, as the server wrote it
    Check a proposal. Human edits are private. Approved means authorized, not delivered; inspect submission.status.
  • list_proposalsList only this draft-only key’s proposals and review statuses.Reads text others writeNo findings

    Why it is in this group

    • The name "list_proposals" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "list" and "review": it reads comments, which other people can write.
    Description, as the server wrote it
    List only this draft-only key’s proposals and review statuses.

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.

36 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 private-data tools breaks every one.

Reads private data2
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write6
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out3
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__email__check_inbox",
      "mcp__email__get_email"
    ]
  }
}

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 18, 2026, 16:23 UTC, unchanged since Nov 4, 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
8
Protocol version
2025-11-25
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
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 8 tools that change things (5 irreversible, 3 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://keykeeper.world/mcp: tools/list returned 13 tools to an anonymous client, including send_email (irreversible), create_payment (irreversible), check_payment (irreversible), propose_email (irreversible), update_proposal (irreversible) and 3 more

    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.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 2.12.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http email https://keykeeper.world/mcp
claude mcp add --transport http email https://keykeeper.world/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__email__check_inbox",
      "mcp__email__get_email",
      "mcp__email__check_sending_status",
      "mcp__email__list_proposals",
      "mcp__email__get_proposal"
    ],
    "ask": [
      "mcp__email__register_agent",
      "mcp__email__check_balance",
      "mcp__email__send_email",
      "mcp__email__request_sender_review",
      "mcp__email__create_payment",
      "mcp__email__check_payment",
      "mcp__email__propose_email",
      "mcp__email__update_proposal"
    ],
    "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. Review it before you use it.

Capability tags behind 9 rules
  • mcp__email__check_inbox private-data, untrusted-input
  • mcp__email__get_email private-data, untrusted-input
  • mcp__email__send_email outbound
  • mcp__email__check_sending_status untrusted-input
  • mcp__email__create_payment untrusted-input
  • mcp__email__check_payment untrusted-input
  • mcp__email__propose_email outbound
  • mcp__email__list_proposals untrusted-input
  • mcp__email__update_proposal 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/world.keykeeper/email/verify?hash=7bd9bf0a8c7926ad01d2f72dcac974ffb9bcc00ef5957463efcc4a3b41fd0f47" | jq -e '.changed == false'

Pinned hash 7bd9bf0a8c79, from Nov 17, 2026, 05:18 UTC.

Watch

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

https://radar.anlyon.com/servers/world.keykeeper/email/changes.xml

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

Badge

Anlyon Radar badge for world.keykeeper/email
[![Anlyon Radar](https://radar.anlyon.com/badge/world.keykeeper/email.svg)](https://radar.anlyon.com/servers/world.keykeeper/email)

Source: MCP Registry. Synced Nov 3, 2026, 16:18 UTC.

KeyKeeper Email MCP server: questions and answers

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

Is the KeyKeeper Email MCP server safe?

No scan can promise that. What its definitions show: 13 tools, 8 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 KeyKeeper Email MCP server delete data?

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

Can the KeyKeeper Email MCP server do things that cannot be undone?

Yes. 5 tools can send, pay, publish or merge: send_email, create_payment, check_payment, propose_email and update_proposal.

What tools does the KeyKeeper Email MCP server have?

13 tools: 5 irreversible, 3 write, 5 read. send_email, create_payment, check_payment, propose_email, update_proposal, register_agent, check_balance, request_sender_review and 5 more.

Does the KeyKeeper Email MCP server need sign-in or OAuth?

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

Does the KeyKeeper Email MCP server send data to outside services?

3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): send_email, propose_email and update_proposal.

Has the KeyKeeper Email MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 17, 2026.