How to Use the Cordial MCP in Pydantic AI

Q: How is my subscriber contact and email channel opt-in data secured?

All contact emails and channel opt-ins fetched via listcontacts are processed in memory within an ephemeral MCP sandbox. We never store, log, or inspect the payloads passing through the gateway.

Build type-safe marketing pipelines with Pydantic AI and the Cordial MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cordial MCP to Pydantic AI

Create your Vinkius account to connect Cordial 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 Cordial with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict Schema Validation with Pydantic AI

Stop silent data corruption in your marketing pipelines. When your agent fetches subscriber details using the MCP Server's `get_subscriber_profile`, the framework validates the incoming JSON against strict Pydantic models at runtime. If the API returns unexpected custom attributes or malformed device tokens, the system raises a validation error immediately. This prevents your agent from making decisions based on corrupted or incomplete customer profiles.

Type-Safe Contact Updates

Writing data back to your Cordial marketing platform requires absolute precision. The Pydantic AI framework ensures that any payload sent to `upsert_subscriber` matches your defined Python types exactly before the request is made. This guarantees that channel preferences, email addresses, and list memberships are formatted correctly. You won't waste API quota on rejected requests or corrupt your audience data with bad types.

Reliable Campaign Audits

Run audits across your active Cordial workflows without worrying about model hallucinations. The Pydantic AI agent queries `list_automation_messages` and `list_marketing_campaigns` to inspect your current outreach. Because the outputs are validated against Pydantic schemas, your agent can safely parse subject lines and performance metrics. You get clean, typed objects that you can pipe directly into your reporting database.

Setup guide

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

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

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

Use the unified toolset class with your server URL to register the tools. This automatically exposes functions like `list_contacts` to your agent, with all responses validated at runtime.

The framework will raise a validation error instantly instead of letting the agent proceed with bad data. This is crucial when processing complex structures from `list_supplementary_data`.

Yes, the toolset is model-agnostic. You can run your validation pipelines using local models or other providers while querying `get_account_details` through the MCP Server.

You can define a Pydantic model for your subscribers and validate the data before calling `upsert_subscriber`. This ensures only clean, properly formatted attributes are sent to the API.

All contact emails and channel opt-ins fetched via `list_contacts` are processed in memory within an ephemeral MCP sandbox. We never store, log, or inspect the payloads passing through the gateway.

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