Skip to content

machine-inbox MCP server

com.machineinbox/machine-inboxmachineinbox.comstreamable-httpv0.1.0Scanned

Task-scoped email inboxes for AI agents: read mail, extract verification codes, and reply.

11 tools: 2 can delete or cancel things, 1 do something that can't be undone, 2 change things and 6 only read.

Tools: 2 delete, 1 irreversible, 2 write, 6 read.
  • Reads private data · 6
  • Reads text others write · 6
  • Can send data out · 2
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here can delete or cancel things and 1 does 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 machine-inbox MCP server can do

The machine-inbox MCP server is published by machineinbox.com, a domain the MCP Registry verified. It has 11 tools. It can delete or cancel things (2 tools: delete_webhook and delete_inbox), do things that cannot be undone, such as sending, paying or publishing (reply_to_message) and create or change data (2 tools: create_inbox and set_webhook). 6 tools only read.

6 tools read private data (get_service_info, get_inbox, list_messages and 3 more); 6 tools bring in text other people can write (get_service_info, get_inbox, list_messages and 3 more); 2 tools can send data out of your system (reply_to_message and set_webhook). 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 13, 2026, version 0.1.0.

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.

11 tools

Deletes or cancels 2Claude Code: deny
  • delete_inboxDelete an inbox: revokes the token and erases stored mail.No findings

    Why it is in this group

    • The name "delete_inbox" says "delete": a word for removing or ending something.
    Description, as the server wrote it
    Delete an inbox: revokes the token and erases stored mail.
  • delete_webhookRemove the inbox webhook.No findings

    Why it is in this group

    • The name "delete_webhook" says "delete": a word for removing or ending something.
    Description, as the server wrote it
    Remove the inbox webhook.
Can't be undone 1Claude Code: ask
  • reply_to_messageSend an included plain-text reply to the authenticated sender of an inbound message.Can send data outNo findings

    Why it is in this group

    • The name "reply_to_message" says "reply": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • outboundThe name "reply_to_message" says "reply": it sends or publishes something to other people.
    Description, as the server wrote it
    Send an included plain-text reply to the authenticated sender of an inbound message.
Changes things 2Claude Code: ask
  • create_inboxRequest a new paid inbox.No findings

    Why it is in this group

    • The name "create_inbox" says "create": a word for a change.
    Description, as the server wrote it
    Request a new paid inbox. Buying requires an out-of-band payment (Stripe MPP or x402 USDC on Base); this tool returns the live HTTP 402 payment challenge plus exact instructions to complete the purchase. Standard inbox: $2.00.
  • set_webhookRegister or replace the inbox webhook: an HMAC-signed POST fires on every inbound message with metadata, extracted verification codes, and injection risk (never the body).Can send data outNo findings

    Why it is in this group

    • The name "set_webhook" says "set": a word for a change.

    What it can reach

    • 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
    Register or replace the inbox webhook: an HMAC-signed POST fires on every inbound message with metadata, extracted verification codes, and injection risk (never the body). Returns the signing secret.
Only reads 6Show 6 read-only tools
  • get_inboxRead an inbox: address, status, expiry, limits, and usage.Reads private dataReads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe name "get_inbox" says "get" and "inbox": it reads mail.
    • private-dataThe description's first sentence says "read" and "inbox": it reads mail.
    • private-dataThe input names an inbox (input.inbox_id), and the tool reads: it reads mail.
    • untrusted-inputThe name "get_inbox" says "get" and "inbox": it reads inbound email, which other people can write.
    • untrusted-inputThe description's first sentence says "read" and "inbox": it reads inbound email, which other people can write.
    Description, as the server wrote it
    Read an inbox: address, status, expiry, limits, and usage.
  • get_messageFetch one message with parsed text, HTML, and attachment download URLs.Reads private dataReads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe name "get_message" says "get" and "message": it reads messages.
    • private-dataThe description's first sentence says "fetch" and "message": it reads messages.
    • private-dataThe input names an inbox (input.inbox_id), and the tool reads: it reads mail.
    • untrusted-inputThe name "get_message" says "get" and "message": it reads messages, which other people can write.
    • untrusted-inputThe description's first sentence says "fetch" and "message": it reads messages, which other people can write.
    Description, as the server wrote it
    Fetch one message with parsed text, HTML, and attachment download URLs.
  • get_service_infoRead the Machine Inbox service instructions: pricing, payment rails, endpoints, and limits.Reads private dataReads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "read" and "inbox": it reads mail.
    • untrusted-inputThe description's first sentence says "read" and "inbox": it reads inbound email, which other people can write.
    Description, as the server wrote it
    Read the Machine Inbox service instructions: pricing, payment rails, endpoints, and limits.
  • get_verification_codeExtract the newest one-time verification code or confirmation link from inbound mail.Reads private dataReads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "mail": it reads mail.
    • private-dataThe input names an inbox (input.inbox_id), and the tool reads: it reads mail.
    • untrusted-inputThe description's first sentence says "mail": it reads inbound email, which other people can write.
    Description, as the server wrote it
    Extract the newest one-time verification code or confirmation link from inbound mail. Ideal for signup and login flows.
  • get_webhookRead the inbox webhook state: URL, delivery counters, and whether it is disabled.Reads private dataReads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "read" and "inbox": it reads mail.
    • private-dataThe input names an inbox (input.inbox_id), and the tool reads: it reads mail.
    • untrusted-inputThe description's first sentence says "read" and "inbox": it reads inbound email, which other people can write.
    Description, as the server wrote it
    Read the inbox webhook state: URL, delivery counters, and whether it is disabled. The secret is only returned by set_webhook.
  • list_messagesList messages in an inbox, newest first.Reads private dataReads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe name "list_messages" says "list" and "message": it reads messages.
    • private-dataThe description's first sentence says "list" and "message": it reads messages.
    • private-dataThe input names an inbox (input.inbox_id), and the tool reads: it reads mail.
    • untrusted-inputThe name "list_messages" says "list" and "message": it reads messages, 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 messages in an inbox, newest first. Pass after=<newest createdAt seen> to poll for only new mail.

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.

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

Reads private data6
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 out2
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__machine-inbox__reply_to_message",
      "mcp__machine-inbox__set_webhook"
    ]
  }
}

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, 18:42 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
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
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 5 tools that change things (2 destructive, 1 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://machineinbox.com/mcp: tools/list returned 11 tools to an anonymous client, including delete_webhook (destructive), delete_inbox (destructive), reply_to_message (irreversible), create_inbox (write), set_webhook (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.

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

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http machine-inbox https://machineinbox.com/mcp
claude mcp add --transport http machine-inbox https://machineinbox.com/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__machine-inbox__get_service_info",
      "mcp__machine-inbox__get_inbox",
      "mcp__machine-inbox__list_messages",
      "mcp__machine-inbox__get_message",
      "mcp__machine-inbox__get_verification_code",
      "mcp__machine-inbox__get_webhook"
    ],
    "ask": [
      "mcp__machine-inbox__create_inbox",
      "mcp__machine-inbox__reply_to_message",
      "mcp__machine-inbox__set_webhook"
    ],
    "deny": [
      "mcp__machine-inbox__delete_webhook",
      "mcp__machine-inbox__delete_inbox"
    ]
  }
}

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 machine-inbox. Review it before you use it.

Capability tags behind 8 rules
  • mcp__machine-inbox__get_service_info private-data, untrusted-input
  • mcp__machine-inbox__get_inbox private-data, untrusted-input
  • mcp__machine-inbox__list_messages private-data, untrusted-input
  • mcp__machine-inbox__get_message private-data, untrusted-input
  • mcp__machine-inbox__get_verification_code private-data, untrusted-input
  • mcp__machine-inbox__reply_to_message outbound
  • mcp__machine-inbox__set_webhook outbound
  • mcp__machine-inbox__get_webhook 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/com.machineinbox/machine-inbox/verify?hash=d2aa662112cfa07c395cbf9f429ecc1c0b32197ce9d1e6c146dd0df39b152aa2" | jq -e '.changed == false'

Pinned hash d2aa662112cf, from Nov 13, 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.machineinbox/machine-inbox/changes.xml

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

Badge

Anlyon Radar badge for com.machineinbox/machine-inbox
[![Anlyon Radar](https://radar.anlyon.com/badge/com.machineinbox/machine-inbox.svg)](https://radar.anlyon.com/servers/com.machineinbox/machine-inbox)

Source: MCP Registry. Synced Oct 21, 2026, 17:58 UTC.

machine-inbox MCP server: questions and answers

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

Is the machine-inbox MCP server safe?

No scan can promise that. What its definitions show: 11 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 machine-inbox MCP server delete data?

Yes. 2 tools can delete, cancel or revoke something: delete_webhook and delete_inbox.

Can the machine-inbox MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: reply_to_message.

What tools does the machine-inbox MCP server have?

11 tools: 2 destructive, 1 irreversible, 2 write, 6 read. delete_webhook, delete_inbox, reply_to_message, create_inbox, set_webhook, get_service_info, get_inbox, list_messages and 3 more.

Does the machine-inbox MCP server need sign-in or OAuth?

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

Does the machine-inbox MCP server send data to outside services?

2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): reply_to_message and set_webhook.

Has the machine-inbox MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 13, 2026.