Skip to content

SMS Vert Pro MCP server

com.smsvertpro/mcpsmsvertpro.comstreamable-httpv1.1.0Scanned

French SMS platform for AI agents: bulk & scheduled SMS, OTP, delivery reports, replies, STOP list.

10 tools: 1 can delete or cancel things, 3 do something that can't be undone, 2 change things and 4 only read.

Tools: 1 delete, 3 irreversible, 2 write, 4 read.
  • Reads private data · 1
  • Reads text others write · 1
  • Can send data out · 3
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things and 3 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 SMS Vert Pro MCP server can do

The SMS Vert Pro MCP server is published by smsvertpro.com, a domain the MCP Registry verified. It has 10 tools. It can delete or cancel things (1 tool: cancel_sms), do things that cannot be undone, such as sending, paying or publishing (send_sms, generate_otp and verify_otp) and create or change data (2 tools: check_credits and verify_number). 4 tools only read.

1 tool reads private data (count_sms_parts); 1 tool brings in text other people can write (count_sms_parts); 3 tools can send data out of your system (send_sms, generate_otp and verify_otp). 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 14, 2026, version 1.1.0.

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.

10 tools

Deletes or cancels 1Claude Code: deny
  • cancel_smsAnnule une campagne SMS non encore envoyée et recrédite le compte.No findings

    Why it is in this group

    • The name "cancel_sms" says "cancel": a word for removing or ending something.
    Description, as the server wrote it
    Annule une campagne SMS non encore envoyée et recrédite le compte.
Can't be undone 3Claude Code: ask
  • generate_otpGénère et envoie un code OTP par SMS pour authentifier un utilisateur.Can send data outNo findings

    Why it is in this group

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

    What it can reach

    • outboundThe input takes a destination (input.to): what the tool writes goes there.
    Description, as the server wrote it
    Génère et envoie un code OTP par SMS pour authentifier un utilisateur.
  • send_smsEnvoie un SMS à un ou plusieurs destinataires via SMS Vert Pro.Can send data outNo findings

    Why it is in this group

    • The name "send_sms" 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_sms" 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
    Envoie un SMS à un ou plusieurs destinataires via SMS Vert Pro. Les numéros doivent être au format international sans le '+' (ex: 33612345678). Un SMS fait 160 caractères ; au-delà, le message part en plusieurs SMS de 153 caractères, chacun facturé (estimation avec count_sms_parts). IMPORTANT : si le compte est en route marketing, la mention 'STOP 36173' doit être ajoutée à la fin du message (obligation légale).
  • verify_otpVérifie un code OTP saisi par l'utilisateur.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
    Vérifie un code OTP saisi par l'utilisateur.
Changes things 2Claude Code: ask
  • check_creditsConsulte le solde de crédits SMS.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
    Consulte le solde de crédits SMS. 1 crédit = 1 SMS de 160 caractères.
  • verify_numberVérifie le format des numéros d'une liste de contacts (regex sur format international FR 336/337 + 11 chiffres).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
    Vérifie le format des numéros d'une liste de contacts (regex sur format international FR 336/337 + 11 chiffres). Retourne la liste des numéros mal formatés. Validation locale, ne consomme pas de crédits.
Only reads 4Show 4 read-only tools
  • count_sms_partsCalcule localement combien de SMS (parts) un message va consommer, sans rien envoyer ni consommer de crédit.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "count_sms_parts" says "count": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "message": it reads messages.
    • untrusted-inputThe description's first sentence says "message": it reads messages, which other people can write.
    Description, as the server wrote it
    Calcule localement combien de SMS (parts) un message va consommer, sans rien envoyer ni consommer de crédit. Permet à l'agent IA d'estimer le coût d'une campagne avant d'appeler send_sms : 1 SMS = 160 caractères, 153 par partie au-delà. Le calcul porte sur le texte tel qu'il partira : les caractères hors alphabet SMS sont convertis automatiquement (ê en e, ç en c, € en E, guillemets et tirets typographiques en caractères simples), ceux sans équivalent sont supprimés, et { } [ ] | \ comptent double. Les émojis sont refusés par défaut (status EMOJI_NOT_ALLOWED) ; l'option émojis (Unicode, 70 caractères par SMS) s'active sur demande auprès du support SMS Vert Pro.
  • get_blacklistRécupère la liste des numéros ayant envoyé STOP (liste noire).No findings

    Why it is in this group

    • The name "get_blacklist" says "get": a word for reading.
    Description, as the server wrote it
    Récupère la liste des numéros ayant envoyé STOP (liste noire).
  • get_delivery_reportRécupère le rapport de délivrabilité d'une campagne SMS.No findings

    Why it is in this group

    • The name "get_delivery_report" says "get": a word for reading.
    Description, as the server wrote it
    Récupère le rapport de délivrabilité d'une campagne SMS.
  • get_responsesRécupère les réponses reçues sur une campagne SMS.No findings

    Why it is in this group

    • The name "get_responses" says "get": a word for reading.
    Description, as the server wrote it
    Récupère les réponses reçues sur une campagne SMS.

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.

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

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
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__smsvertpro__count_sms_parts"
    ]
  }
}

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, 18:47 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
6
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://www.smsvertpro.com/.well-known/oauth-protected-resource/mcp
Authorization servers
https://www.smsvertpro.com/mcp
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 6 tools that change things (1 destructive, 3 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://www.smsvertpro.com/mcp/: tools/list returned 10 tools to an anonymous client, including cancel_sms (destructive), send_sms (irreversible), generate_otp (irreversible), verify_otp (irreversible), check_credits (write) and 1 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 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http smsvertpro https://www.smsvertpro.com/mcp/
claude mcp add --transport http smsvertpro https://www.smsvertpro.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__smsvertpro__get_delivery_report",
      "mcp__smsvertpro__get_responses",
      "mcp__smsvertpro__get_blacklist",
      "mcp__smsvertpro__count_sms_parts"
    ],
    "ask": [
      "mcp__smsvertpro__send_sms",
      "mcp__smsvertpro__check_credits",
      "mcp__smsvertpro__verify_number",
      "mcp__smsvertpro__generate_otp",
      "mcp__smsvertpro__verify_otp"
    ],
    "deny": [
      "mcp__smsvertpro__cancel_sms"
    ]
  }
}

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 smsvertpro. Review it before you use it.

Capability tags behind 4 rules
  • mcp__smsvertpro__send_sms outbound
  • mcp__smsvertpro__generate_otp outbound
  • mcp__smsvertpro__verify_otp outbound
  • mcp__smsvertpro__count_sms_parts 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.smsvertpro/mcp/verify?hash=6252fa90388ba935bc2322cf0c427de44596ef7946b1714ab634e3007cbc05e8" | jq -e '.changed == false'

Pinned hash 6252fa90388b, from Nov 14, 2026, 09:17 UTC.

Watch

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

https://radar.anlyon.com/servers/com.smsvertpro/mcp/changes.xml

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

Badge

Anlyon Radar badge for com.smsvertpro/mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/com.smsvertpro/mcp.svg)](https://radar.anlyon.com/servers/com.smsvertpro/mcp)

Source: MCP Registry. Synced Oct 21, 2026, 18:05 UTC.

SMS Vert Pro MCP server: questions and answers

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

Is the SMS Vert Pro MCP server safe?

No scan can promise that. What its definitions show: 10 tools, 6 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 SMS Vert Pro MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: cancel_sms.

Can the SMS Vert Pro MCP server do things that cannot be undone?

Yes. 3 tools can send, pay, publish or merge: send_sms, generate_otp and verify_otp.

What tools does the SMS Vert Pro MCP server have?

10 tools: 1 destructive, 3 irreversible, 2 write, 4 read. cancel_sms, send_sms, generate_otp, verify_otp, check_credits, verify_number, get_delivery_report, get_responses and 2 more.

Does the SMS Vert Pro MCP server need sign-in or OAuth?

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

Does the SMS Vert Pro 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_sms, generate_otp and verify_otp.

Has the SMS Vert Pro MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 14, 2026.