Bring Sms Notifications
to Pydantic AI
Learn how to connect CM.com to Pydantic AI and start using 11 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the CM.com MCP Server?
Connect your CM.com account to any AI agent and control your omnichannel communications through natural conversation.
What you can do
- SMS Messaging — Send individual SMS messages or broadcast to multiple recipients in a single request
- Rich Messaging — Deliver messages through WhatsApp, Viber, RCS, or Apple Messages for Business
- WhatsApp Templates — Send pre-approved WhatsApp Business template messages with namespace support
- Voice Communications — Place automated calls for voice OTP delivery or text-to-speech notifications
- Email Delivery — Send HTML emails through CM.com's delivery infrastructure
- OTP Verification — Send SMS OTPs and verify codes for two-factor authentication
- Account Management — Check your credit balance and list virtual phone numbers
How it works
1. Subscribe to this server
2. Enter your CM.com Product Token from your Channels dashboard
3. Start sending messages from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Operations Teams — send transactional SMS, WhatsApp notifications, and voice alerts without writing integration code
- Security Teams — implement OTP verification flows for two-factor authentication directly from AI workflows
- Marketing Teams — send bulk SMS campaigns and check delivery through conversational AI
Built-in capabilities (11)
com account. Check account balance
com account. List phone numbers
Send bulk SMS
com email delivery infrastructure. Send an email
Send OTP via SMS
Send a rich message
Send an SMS
Send voice notification
Send voice OTP
Send WhatsApp template
Verify OTP code
Why Pydantic AI?
Pydantic AI validates every CM.com tool response against typed schemas, catching data inconsistencies at build time. Connect 11 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your CM.com integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your CM.com connection logic from agent behavior for testable, maintainable code
CM.com in Pydantic AI
CM.com and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect CM.com to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for CM.com in Pydantic AI
The CM.com MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 11 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
CM.com for Pydantic AI
Every tool call from Pydantic AI to the CM.com MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I send messages through WhatsApp, Viber, and other rich channels?
Yes! The send_rich_message action lets you send through WhatsApp, Viber, RCS, or Apple Messages by specifying the channel parameter. For WhatsApp Business specifically, use send_whatsapp to send pre-approved template messages with a template ID and namespace.
Can I implement two-factor authentication with OTP verification?
Yes. Use send_otp_sms to deliver a verification code via SMS — it returns a verification ID. Then call verify_otp with that verification ID and the code the user enters. For voice-based OTP delivery, use send_voice_otp to read the code to the user via an automated phone call.
Can I check my CM.com credit balance before sending campaigns?
Yes. The get_balance tool retrieves your current credit balance. Use list_numbers to see all virtual phone numbers in your account. Both tools help you plan campaigns before committing to bulk sends via send_bulk_sms.
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your CM.com MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai