How do I get a Cordial API Key?

Log in to your Cordial account, go to **Settings > API Keys**, and create a new key. Ensure you have the necessary permissions to manage contacts and messages.

Can the agent trigger batch campaigns?

This integration currently focuses on listing and monitoring campaigns. To trigger sends, you should use the Cordial dashboard or specific automation workflows.

What profile attributes can the agent update?

The agent can update any custom attributes defined in your Cordial schema, as well as channel subscription preferences, as long as the API Key has write access.

Cordial MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Cordial
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Cordial through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Cordial "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Cordial?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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

About Cordial MCP Server

Integrate Cordial, the cross-channel marketing platform, directly into your AI workflow. Manage your audience segments, trigger automated messages, and monitor campaign performance using natural language.

Pydantic AI validates every Cordial tool response against typed schemas, catching data inconsistencies at build time. Connect 10 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.

What you can do

Audience Management — List and search for subscribers, and update profile attributes seamlessly.
Campaign Monitoring — Track the performance of batch and transactional email/SMS campaigns.
Automation Control — Monitor and manage active message automation workflows.
Data Insights — Access supplementary data collections and account metadata via chat.

The Cordial MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Cordial to Pydantic AI via MCP

Follow these steps to integrate the Cordial MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Cordial with type-safe schemas

Why Use Pydantic AI with the Cordial MCP Server

Pydantic AI provides unique advantages when paired with Cordial through the Model Context Protocol.

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 Cordial integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Cordial connection logic from agent behavior for testable, maintainable code

Cordial + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Cordial MCP Server delivers measurable value.

Type-safe data pipelines: query Cordial with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Cordial tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Cordial and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Cordial responses and write comprehensive agent tests

Cordial MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Cordial to Pydantic AI via MCP:

get_account_details

Resolves system-level account identifiers, plan configuration, and core platform settings. Get metadata about your Cordial account

get_subscriber_profile

Resolves granular profile data including custom attributes, device tokens, and list memberships. Get full profile and attributes for a subscriber

list_audience_segments

Resolves list identity properties such as segment IDs, names, and subscriber counts. List contact segments and audience groups

list_automation_messages

Resolves active automated message definitions and workflow status for triggered communications. List active automated message workflows

list_contacts

Resolves contact identity properties including email addresses, channel opt-ins, and attribute metadata across the Cordial system boundary. List subscribers in Cordial

list_marketing_campaigns

Resolves campaign identity and status, including scheduling data and high-level performance indicators. List marketing campaigns and their performance

list_messages

Resolves batch and transactional message definitions, including templates, subject lines, and sender profiles. List batch and transactional messages

list_supplementary_data

Resolves metadata for custom data collections used for message personalization. List supplement collections (external data tables)

search_campaigns_by_name

Resolves a subset of campaigns matching the name criteria across the platform boundary. Search for marketing campaigns by name

upsert_subscriber

Creates or updates a profile with identity properties, channel preferences, and custom attributes. Create or update a subscriber profile

Example Prompts for Cordial in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Cordial immediately.

"List the most recent marketing campaigns and their open rates."

"Show me the profile for the subscriber 'user@example.com'."

"Check the size of our 'Active Customers' list."

Troubleshooting Cordial MCP Server with Pydantic AI

Common issues when connecting Cordial to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Cordial + Pydantic AI FAQ

Common questions about integrating Cordial MCP Server with Pydantic AI.

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 Cordial MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.