How to Use the Loops MCP in Pydantic AI

Q: How do I configure the Loops MCP toolset in Pydantic AI?

Install the library using pip install pydantic-ai-slimmcp and initialize an MCPToolset pointing to your server URL. Pass this toolset into your Agent constructor to give your model access to all ten tools.

Q: Can Pydantic AI validate Loops contact creation inputs?

Yes, when the agent invokes createcontact, the framework validates the email and metadata against strict schemas. If the agent generates an invalid email format, the run fails immediately instead of sending bad data to Loops.

Q: How does Pydantic AI handle Loops transactional delivery?

The agent uses sendtransactionalemail to send structured messages using your pre-defined templates. The variables are validated dynamically, ensuring your transactional emails always contain the correct metadata.

Q: How can I check if my API key is valid?

Use the testapikey tool to verify your connection status on startup. It returns a boolean status, allowing your application to halt early if your API key is missing or expired.

Run type-safe Loops contact management and transactional email delivery in Python with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Loops MCP to Pydantic AI

Create your Vinkius account to connect Loops 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 Loops with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Send transactional emails with Pydantic AI validation

The `send_transactional_email` tool ensures your agent sends structured template variables without silent errors. Pydantic AI validates the inputs at runtime, failing loudly if the agent tries to pass incorrect data variables. This strict type checking prevents broken emails from reaching your customers. If your agent tries to send a malformed payload, the framework catches it before the API call is even made.

Sync contacts using this type-safe MCP Server

This MCP Server exposes tools like `create_contact` and `update_contact` with strict validation schemas. Your agent can update names, email addresses, and user groups knowing that every property matches your Pydantic models. If the agent attempts to write an invalid email address, the validation layer blocks the execution. This keeps your Loops database clean and prevents API errors from halting your execution loop.

Verify suppression status before sending

The `get_contact_suppression` tool returns the suppression state of any email address before you trigger a campaign. Your agent queries this MCP tool to verify that the recipient is active and has not opted out. Integrating this check with `find_contact` protects your sender reputation. It ensures your Pydantic AI workflows never attempt to mail suppressed addresses, keeping your deliverability high.

Setup guide

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

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

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

Install the library using pip install pydantic-ai-slim[mcp] and initialize an MCPToolset pointing to your server URL. Pass this toolset into your Agent constructor to give your model access to all ten tools.

Yes, when the agent invokes `create_contact`, the framework validates the email and metadata against strict schemas. If the agent generates an invalid email format, the run fails immediately instead of sending bad data to Loops.

The agent uses `send_transactional_email` to send structured messages using your pre-defined templates. The variables are validated dynamically, ensuring your transactional emails always contain the correct metadata.

Use the `test_api_key` tool to verify your connection status on startup. It returns a boolean status, allowing your application to halt early if your API key is missing or expired.

No, the server operates on a zero-trust architecture and does not persist any email addresses or contact profiles. All payloads pass directly to the Loops API, and the Vinkius isolate sandbox is completely destroyed after execution.

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