How to Use the Correios API (REST) MCP in Pydantic AI

Validate Correios shipping rates and tracking status at runtime 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 Correios API (REST) MCP to Pydantic AI

Create your Vinkius account to connect Correios API (REST) 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 Correios API (REST) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce strict types on Correios shipping calculations

The `calculate_price_deadline` tool returns structured Brazilian shipping costs and delivery estimates directly to your agent. Pydantic AI validates this incoming payload against strict Python type models before your code executes. This runtime check prevents your application from crashing due to unexpected API changes. If Correios returns an empty field, your agent catches the validation error immediately instead of failing silently.

Track Brazilian parcels using a type-safe MCP Server

The `track_object` tool queries the official Brazilian postal service to pull the current delivery status of any package. Your agent parses this tracking history and maps it directly to your internal database models. You register the toolset using the unified MCPToolset class pointing to your Vinkius MCP Server endpoint. The framework handles the underlying SSE or HTTP transport details automatically.

Build model-agnostic shipping agents

The `calculate_price_deadline` tool operates independently of the underlying LLM you choose to run. You can swap between commercial models and local open-source models without rewriting your Correios tool logic. Pydantic AI ensures that whichever model you deploy receives clean, structured JSON from the Correios API. You focus on agent prompts while the framework guarantees data integrity.

Setup guide

Set up Correios API (REST) 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": {
        "correios-api-rest-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Correios API (REST) 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 Correios. 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 Correios API (REST) 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 Correios API (REST) MCP in Pydantic AI

Use the MCPToolset class with your external server URL. Pass this toolset instance inside the toolsets list when initializing your Pydantic AI agent.

Yes, the MCPToolset class supports both SSE and Streamable HTTP transports. You specify the connection protocol when setting up your server string.

The MCP Server framework raises a validation error immediately at runtime. This loud failure prevents corrupted shipping rates or broken tracking strings from entering your production database.

No, you should avoid the deprecated MCPServerHTTP class entirely. Use the modern, unified MCPToolset approach to connect your Correios tools.

Your Brazilian tracking codes and zip codes pass through an isolated execution sandbox. Vinkius never logs the payload contents, and the Pydantic AI framework processes the validated data strictly in memory before discarding it.

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