Skip to content

NOTIFY MCP server

io.github.n0t1fy/notify-sms-georgian0t1fystreamable-httpv0.2.0Scanned

SMS verification codes for Georgia (+995), sent and checked. Try test codes with a free test key.

5 tools: 3 do something that can't be undone, 1 change things and 1 only read.

Tools: 0 delete, 3 irreversible, 1 write, 1 read.
  • Reads private data · 1
  • Reads text others write · 3
  • Can send data out · 3
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

3 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 NOTIFY MCP server can do

The NOTIFY MCP server is published by the GitHub account n0t1fy. It has 5 tools. It can do things that cannot be undone, such as sending, paying or publishing (send_message, start_verification and check_verification) and create or change data (1 tool: create_test_key), but cannot delete data. 1 tool only reads.

1 tool reads private data (get_message); 3 tools bring in text other people can write (send_message, start_verification and get_message); 3 tools can send data out of your system (send_message, start_verification and check_verification). 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 21, 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.

5 tools

Can't be undone 3Claude Code: ask
  • check_verificationCheck the code the human typed, for the number the code was sent to.Can send data outNo findings

    Why it is in this group

    • The input addresses people (input.to): what it sends cannot be taken back.
    • The input takes a statement or command to run (input.code), which can change anything it can reach.

    What it can reach

    • outboundThe input takes a destination (input.to): what the tool writes goes there.
    Description, as the server wrote it
    Check the code the human typed, for the number the code was sent to. The result is the verification only when it is approved; every other outcome is a tool error with an `error.code`. Let the user in only when a check answers `200` with status `approved`; treat every other answer, a timeout and a network error as not approved. Errors: `incorrect_code` (attempts remain), `too_many_attempts` (start a new verification), `recipient_mismatch` (`to` is not the number the code was sent to), `verification_expired`, `verification_closed` (already approved or replaced), `verification_not_found`. A wrong code costs an attempt, and five close the verification: do not retry a check by yourself; ask the human for the code again.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • send_messageSend one transactional SMS to a Georgian mobile number.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "send_message" 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

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe name "send_message" 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
    Send one transactional SMS to a Georgian mobile number. The text comes from a built-in template; there is no free text (every template: https://n0t1fy.dev/templates). Team templates (`service_down`, `service_up`, `incident_opened`, `support_ticket_urgent`, `job_failed`, `agent_alert`) go only to numbers the project's owner confirmed on the dashboard's team page; with a test key, use the test numbers +995512345670 to +995512345679. A `recipient_not_on_team` error means the number is not confirmed on the team: ask the human to add it on the dashboard, and never retry by yourself. With a live key, a `service` or `job` must be a name on the owner's list there. With a test key (sk_test_) nothing is really sent: a simulator answers. These recipients simulate outcomes: +995512345671 rejected (status `failed`); +995512345672 provider unreachable (error `provider_unavailable`: nothing was sent, retry with the same idempotency_key); +995512345673 ambiguous (status `unknown`); +995512345674 accepted, then `undeliverable`. Any other valid number is accepted, then `delivered`, within about 30 seconds. With a live key it sends a real SMS and spends one credit per segment. Read `message.status` in the result. `submitted`: the provider accepted it, which is not yet delivery to the phone. `failed`: refused; `message.error` says why. `unknown`: it may or may not have been sent, so do not send it again automatically. `replayed: true`: this idempotency_key and request were already processed, and no second SMS was sent. Call get_message to learn the final outcome.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • start_verificationVerify a Georgian mobile number: NOTIFY makes a random six-digit code and sends it by SMS with a built-in template.Reads text others writeCan send data outNo findings

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a destination (input.to): what the tool writes goes there.
    Description, as the server wrote it
    Verify a Georgian mobile number: NOTIFY makes a random six-digit code and sends it by SMS with a built-in template. The code is never shown to you: ask the human for the code they received, then call check_verification. A code works for 10 minutes and 5 checks, once; a new start for the same number replaces it. With a test key (sk_test_), only the test numbers +995512345670 to +995512345679 are accepted and their code is always 000000; nothing is sent. At most 5 starts a minute go to one number, so spread test starts over the ten test numbers. +995512345671 simulates a refused SMS (status `failed`), +995512345672 an unreachable provider (error `provider_unavailable`: nothing was sent, retry with the same idempotency_key), +995512345673 an SMS that may or may not have arrived (still `pending`). With a live key it sends a real SMS and spends one credit. `replayed: true` means this idempotency_key and request were already processed and no second SMS was sent; the verification it shows may say `approved` by then, which is not a check result. On `too_many_verifications` (5 an hour or 10 in a rolling 24 hours to one number), tell the human when they can try again (`retry_at`), and never retry by yourself.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Changes things 1Claude Code: ask
  • create_test_keyGet an sk_test_ API key instantly, with no account and no human.No findings

    Why it is in this group

    • The name "create_test_key" says "create": a word for a change.
    Description, as the server wrote it
    Get an sk_test_ API key instantly, with no account and no human. A test key never sends a real SMS and never spends credits, so a whole integration can be built and verified with it. Pass it as `api_key` to send_message and get_message, and keep it in the application's configuration (for example NOTIFY_API_KEY), never in source code. The result also has a `claim_url` for a human: opening it lets them sign in and take over the project. Anyone who opens it, signs in and confirms becomes the owner: give it only to the person who will own the project, and do not paste it into shared logs or tickets. Real SMS need an sk_live_ key that the human creates on the dashboard (https://n0t1fy.dev/dashboard). Limited to a few keys per minute and per day for each address: reuse a key you already have.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
Only reads 1Show 1 read-only tool
  • get_messageRead the current state of a message sent with a key of the same project.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 "read" and "message": it reads messages.
    • untrusted-inputThe name "get_message" says "get" and "message": it reads messages, 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 the current state of a message sent with a key of the same project. Poll only while `status` is `queued` or `submitted`: `delivered`, `undeliverable` and `failed` are final, and `unknown` never changes. Wait about 2 seconds before the first read and double the wait each time, up to 30 seconds. Always set a time limit (two minutes is generous for a test message); when it passes, treat the message as unconfirmed and do not send it again.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

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.

9 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.

Reads private data1
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 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__notify-sms-georgia__get_message"
    ]
  }
}

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, 19:08 UTC, unchanged since Oct 29, 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
4
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 4 tools that change things (3 irreversible, 1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://api.n0t1fy.dev/mcp: tools/list returned 5 tools to an anonymous client, including send_message (irreversible), start_verification (irreversible), check_verification (irreversible), create_test_key (write)

    What this check looks for

Posture changes

  1. Oct 29, 2026
    • Reachable: no to yes
    • HTTP status of an anonymous initialize: none to 200
    • tools/list served without credentials: no to yes
    • Tools that change things, listed without credentials: 0 to 4
    • Protocol version: none to 2025-06-18

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. Tools1 changed.~1 changedView diff
  2. PostureRemote posture changed. Reachable: no -> yes; HTTP status of an anonymous initialize: none -> 200; tools/list served without credentials: no -> yes (and 2 more).View diff
    • Reachable: no to yes
    • HTTP status of an anonymous initialize: none to 200
    • tools/list served without credentials: no to yes
    • Tools that change things, listed without credentials: 0 to 4
    • Protocol version: none to 2025-06-18

Install

Pinned to version 0.2.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http notify-sms-georgia https://api.n0t1fy.dev/mcp
claude mcp add --transport http notify-sms-georgia https://api.n0t1fy.dev/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__notify-sms-georgia__get_message"
    ],
    "ask": [
      "mcp__notify-sms-georgia__create_test_key",
      "mcp__notify-sms-georgia__send_message",
      "mcp__notify-sms-georgia__start_verification",
      "mcp__notify-sms-georgia__check_verification"
    ],
    "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 notify-sms-georgia. Review it before you use it.

Capability tags behind 4 rules
  • mcp__notify-sms-georgia__send_message untrusted-input, outbound
  • mcp__notify-sms-georgia__start_verification untrusted-input, outbound
  • mcp__notify-sms-georgia__check_verification outbound
  • mcp__notify-sms-georgia__get_message 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.n0t1fy/notify-sms-georgia/verify?hash=fb880dc5e1ad711a87521b33169606190f0c8c54406c62fa9f8718e26e516716" | jq -e '.changed == false'

Pinned hash fb880dc5e1ad, from Nov 21, 2026, 01:17 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.n0t1fy/notify-sms-georgia/changes.xml

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

Badge

Anlyon Radar badge for io.github.n0t1fy/notify-sms-georgia
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.n0t1fy/notify-sms-georgia.svg)](https://radar.anlyon.com/servers/io.github.n0t1fy/notify-sms-georgia)

Source: MCP Registry. Synced Oct 21, 2026, 18:42 UTC.

NOTIFY MCP server: questions and answers

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

Is the NOTIFY MCP server safe?

No scan can promise that. What its definitions show: 5 tools, 4 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 NOTIFY MCP server delete data?

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

Can the NOTIFY MCP server do things that cannot be undone?

Yes. 3 tools can send, pay, publish or merge: send_message, start_verification and check_verification.

What tools does the NOTIFY MCP server have?

5 tools: 3 irreversible, 1 write, 1 read. send_message, start_verification, check_verification, create_test_key and get_message.

Does the NOTIFY MCP server need sign-in or OAuth?

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

Does the NOTIFY 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_message, start_verification and check_verification.

Has the NOTIFY MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 6, 2026. Every change is on this page and in its Atom feed.