How to Use the Brevo MCP in Pydantic AI

Build type-safe marketing agents with Pydantic AI and the Brevo 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 Brevo MCP to Pydantic AI

Create your Vinkius account to connect Brevo 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 Brevo with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe Brevo CRM actions in Pydantic AI

Every response from `list_crm_contacts` is validated against your Pydantic models. If the schema shifts, the agent stops immediately to prevent bad data ingestion. Use `create_crm_contact` to safely add users to your system. The validation ensures that every mandatory field is present before the tool executes.

Reliable Brevo messaging with Pydantic AI

The agent uses `send_transactional_email` to trigger campaigns. Because it's a Pydantic AI project, the payload is checked for format errors before it hits the Brevo API. Dispatch SMS messages with `send_transactional_sms` knowing the output conforms to your defined structures. It eliminates the risk of silent failures during your outreach.

Manage Brevo account state in Pydantic AI

Fetch your account status via `get_smtp_account_details` and map it to a typed object. This gives your agent a clear view of your sending quotas. If you need to check contact details, `get_contact_attributes` returns a structured response. Your Pydantic AI logic can then parse these attributes without guessing the field types.

Setup guide

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

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

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

You get runtime validation for every tool call. If the Brevo API returns a malformed contact record, Pydantic AI catches it before it poisons your agent's context.

Yes, it is model-agnostic. You can pair it with any LLM in your Pydantic AI setup as long as the server is running.

It employs strict schema enforcement at the boundary. Only validated, authorized contact attributes are ever passed back into your agent's memory.

Yes, the server returns lists in manageable chunks. You can iterate through them while keeping your Pydantic models in sync with the data.

The agent receives a clear error response. Since you use Pydantic AI, you can catch this exception and retry the call or log the failure.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.