How to Use the Customer.io MCP in Pydantic AI

Q: How do I set up Customer.io with Pydantic AI?

Install the slim package with MCP support and initialize MCPToolset using your Vinkius HTTP endpoint. Pass this toolset array to your Agent instance. The framework automatically maps the messaging endpoints to strict Pydantic models.

Q: Can Pydantic AI trigger Customer.io broadcasts?

The framework supports executing dispatchbroadcast through the unified toolset. You define the exact input schema required, preventing the LLM from hallucinating invalid broadcast parameters.

Q: Does Pydantic AI support reading Customer.io campaign stats?

Your agent calls getcampaignperformance to pull the metrics. Every single click and open rate integer gets validated against your Pydantic schema before your application processes it.

Q: How are Customer.io user profiles secured in Pydantic AI?

Person profiles fetched via getcustomerdetails execute inside an isolated V8 MCP Server sandbox. Vinkius manages the authentication layer entirely, meaning your Pydantic application never stores the raw API keys locally.

Build type-safe Customer.io agents in Pydantic AI that validate campaign stats and segment data 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 Customer.io MCP to Pydantic AI

Create your Vinkius account to connect Customer.io 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 Customer.io with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe Customer.io MCP Server integration

Silent API errors break automated messaging systems. When your Pydantic AI agent calls `get_customer_details`, the response must match your exact schema. If the person profile comes back missing required fields, the framework fails loudly with a validation error. This strictness keeps your data clean across any LLM you choose. Local models and Anthropic endpoints process `list_customers` predictably. You use the unified `MCPToolset` approach to connect the server, ensuring absolute correctness over raw speed.

Read segments and campaigns predictably

Pulling list data requires exact formatting. Your agent uses `list_audience_segments` and `list_segment_members` to figure out who receives what via the MCP Server. Because every output is validated, your application never hallucinates a user ID that does not exist. Tracking active sends works exactly the same way. The agent fires `list_active_campaigns` and `list_scheduled_broadcasts` to monitor your pipeline. You pass the toolset to the Agent, and Pydantic handles the HTTP transport behind the scenes.

Trigger emails and track metrics safely

Sending individual messages demands precision. The agent executes `send_transactional_email` only when the input payload perfectly matches your defined Pydantic models. You review past sends via `list_transactional_messages` to audit the system. Reporting relies on accurate numbers. Calling `get_campaign_performance` returns open and click data that your code actually trusts. The agent checks `get_connection_status` first, ensuring the endpoint is alive before attempting any data extraction.

Setup guide

Set up Customer.io 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": {
        "customerio-alternative-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install the slim package with MCP support and initialize `MCPToolset` using your Vinkius HTTP endpoint. Pass this toolset array to your Agent instance. The framework automatically maps the messaging endpoints to strict Pydantic models.

Yes, runtime validation ensures that unexpected payloads from tools like `list_newsletters` trigger immediate errors. The agent fails loudly instead of passing corrupted data downstream.

The framework supports executing `dispatch_broadcast` through the unified toolset. You define the exact input schema required, preventing the LLM from hallucinating invalid broadcast parameters.

Your agent calls `get_campaign_performance` to pull the metrics. Every single click and open rate integer gets validated against your Pydantic schema before your application processes it.

Person profiles fetched via `get_customer_details` execute inside an isolated V8 MCP Server sandbox. Vinkius manages the authentication layer entirely, meaning your Pydantic application never stores the raw API keys locally.

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