How to Use the DoubleTick MCP in Pydantic AI

Q: How do I connect the DoubleTick MCP Server to Pydantic AI?

Install the package with pip install "pydantic-ai-slimmcp" and instantiate MCPToolset with your Vinkius HTTP endpoint. Pass the toolset into your Agent constructor to give your model validated access to the MCP tools.

Q: How does Pydantic AI handle invalid DoubleTick template variables?

The framework validates the inputs for sendwhatsapptemplate against your Pydantic models. If the agent tries to send a template with missing or malformed variables, the system raises a validation error before hitting the API.

Q: Does the Pydantic AI integration support SSE transports for the MCP Server?

Yes, the MCPToolset supports both Streamable HTTP and SSE transports. This allows you to connect to your externally running server using your preferred connection method.

Build type-safe WhatsApp workflows with Pydantic AI to validate contact lists and message templates at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DoubleTick MCP to Pydantic AI

Create your Vinkius account to connect DoubleTick 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 DoubleTick with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce type safety on DoubleTick MCP Server payload

The `get_contact_details` tool retrieves profile data and conversation status, while `search_contacts_by_keyword` finds matching customer records based on your search queries. Your agent processes these results through Pydantic AI's strict runtime validation to ensure every phone number and status field conforms to your exact data models. If the server returns unexpected null values or altered schemas, the framework halts execution immediately. This prevents malformed contact records from corrupting your downstream databases or causing silent failures in your code.

Validate outbound templates before delivery

The `send_whatsapp_template` tool dispatches pre-approved messages, and `list_approved_templates` retrieves the allowed layouts from your account. Your agent validates the template variables against your defined schemas before executing the outbound call on the MCP Server. This structure ensures that your system never sends incomplete templates to customers. By catching validation errors at runtime, you eliminate the risk of sending broken placeholders like raw bracket variables.

Audit messaging volumes with verified schemas

The `quick_whatsapp_volume_audit` tool retrieves high-level delivery success metrics, while `get_doubletick_account_metadata` checks your account limits. Your agent maps these metrics to structured Python classes to monitor your communication pipeline. Because the framework is model-agnostic, you can switch between different LLMs while maintaining the same strict validation rules. Your audit logs and account status checks remain reliable regardless of the underlying model.

Setup guide

Set up DoubleTick 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": {
        "doubletick-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent DoubleTick 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 DoubleTick. 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 DoubleTick 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 DoubleTick MCP in Pydantic AI

Install the package with `pip install "pydantic-ai-slim[mcp]"` and instantiate `MCPToolset` with your Vinkius HTTP endpoint. Pass the toolset into your `Agent` constructor to give your model validated access to the MCP tools.

The framework validates the inputs for `send_whatsapp_template` against your Pydantic models. If the agent tries to send a template with missing or malformed variables, the system raises a validation error before hitting the API.

Yes, the framework is model-agnostic and works with local models or commercial APIs. The agent will still validate all outputs from `list_conversation_messages` against your schemas.

Yes, the `MCPToolset` supports both Streamable HTTP and SSE transports. This allows you to connect to your externally running server using your preferred connection method.

Your contact records and phone numbers are validated locally in your runtime environment. Vinkius secures the API connection using end-to-end encryption and executes the underlying tools within isolated, zero-trust sandboxes.

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