How to Use the Clickatell MCP in Pydantic AI

Q: What's the setup process for Pydantic AI and Clickatell?

After installing the library, you create an MCPToolset instance, passing it the Vinkius URL for your Clickatell server. You then include this toolset in the toolsets list when you create your Agent. It's a two-step process to give your agent messaging powers.

Send type-safe SMS and WhatsApp messages with Pydantic AI. Get validated Pydantic models back from every Clickatell API call.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Clickatell MCP to Pydantic AI

Create your Vinkius account to connect Clickatell to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Clickatell with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Send Messages That Can't Fail Silently

Stop guessing what the API will return. When your agent uses `send_sms` or `send_whatsapp`, the JSON response is automatically parsed and validated against a Pydantic model. If Clickatell returns an unexpected field or a `null` where a string should be, your code raises a `ValidationError` immediately. This means you can trust the data your agent works with. No more defensive coding, no more silent data corruption. If a call to the Clickatell MCP succeeds, you get a clean, predictable Python object.

Build Auditing Tools You Can Actually Trust

Build internal tools that are correct by construction. An agent tasked with checking your account status can call `get_account_balance` or `get_account_info`, and Pydantic AI guarantees the response fits the exact data model you defined. The balance will be a float, the account ID a string. This is perfect for financial reconciliation or compliance bots. You can run an agent that pulls data with `list_message_history` and writes it to a database, confident that every single record has been validated. The data integrity is built-in.

Use Any LLM with a Single, Type-Safe Interface

Pydantic AI is model-agnostic, so you aren't locked into a specific LLM provider. You can use GPT-4, Gemini, a local Llama model, or anything else to power your agent's brain. The tool-use logic remains the same. Your agent can decide to `list_whatsapp_templates`, have the user pick one, and then call `send_whatsapp`. This entire chain is type-safe and works identically whether you're calling a major cloud LLM or one running on your own machine. The MCPToolset just works.

Setup guide

Set up Clickatell MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "clickatell-alternative-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Clickatell tools.",
)

result = await agent.run("List recent Clickatell transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Clickatell. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Clickatell now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Clickatell MCP in Pydantic AI

Pydantic AI validates every response from the Clickatell MCP Server against a corresponding Pydantic model. If the API's response doesn't perfectly match the expected structure and data types, it throws an error instead of letting your agent use bad data.

Yes. Pydantic AI is designed to be model-agnostic. You can use it with local models like Llama or Mistral, as long as you have a compatible inference server. Your local agent can access all the Clickatell tools just like a cloud-based one.

After installing the library, you create an `MCPToolset` instance, passing it the Vinkius URL for your Clickatell server. You then include this toolset in the `toolsets` list when you create your `Agent`. It's a two-step process to give your agent messaging powers.

Yes, there is a very small overhead for parsing and validating the JSON response into a Pydantic model. This is typically measured in milliseconds and is a worthwhile trade-off for guaranteeing data correctness in your application.

Your data, such as WhatsApp template content and message status details, is handled by Vinkius in secure, ephemeral sandboxes. Pydantic AI adds another layer of security by acting as a strict data contract; it will reject any malformed or unexpected data from the API before it even reaches your agent's logic.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript