How to Use the ANVISA (Portal de APIs) MCP in Pydantic AI

Q: How does the framework handle complex chemical data from the pharmacopeia?

The monografiasfarmacopeia tool returns clean structured text. Pydantic AI validates the structure, making it easy for your model to extract specific chemical properties without parsing raw HTML.

Run type-safe ANVISA regulatory queries with Pydantic AI to guarantee zero data corruption in your health tech stack.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ANVISA (Portal de APIs) MCP to Pydantic AI

Create your Vinkius account to connect ANVISA (Portal de APIs) 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 ANVISA (Portal de APIs) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate sanitizers and cosmetics with Pydantic AI

`consultar_saneantes` searches the official Brazilian database for registered sanitizing products and household cleaning agents. Your agent uses this tool to check active registrations, validating the response schema at runtime against strict Pydantic models. If the API returns unexpected fields, your system catches the validation error immediately rather than passing corrupted data downstream. For hygiene products, the agent calls `consultar_cosmeticos` with the same type-safe guarantees.

Parse medicine pricing via this type-safe MCP Server

`precos_medicamentos` fetches official price ceilings, including factory and consumer limits, for registered drugs. The tool enforces structured data output, ensuring your pricing calculations never run on malformed floats. To verify the drug's active registration, your agent runs `consultar_medicamentos` in tandem. This MCP Server integration ensures your compliance database stays clean, accurate, and completely free of hallucinated registration numbers.

Audit food registrations using Pydantic AI

`registros_alimentos` lists food products officially registered with the Brazilian health authority. Your agent parses the structured JSON response, instantly mapping fields to your local data models. For items exempt from full registration, the agent runs `notificacoes_alimentos` to check simple pre-market notifications. By using this toolset, you eliminate the fragile regex parsing typically required when scraping government portals.

Setup guide

Set up ANVISA (Portal de APIs) 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": {
        "anvisa-portal-de-apis-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent ANVISA (Portal de APIs) 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 ANVISA. 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 ANVISA (Portal de APIs) 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 ANVISA (Portal de APIs) MCP in Pydantic AI

You instantiate MCPToolset with your Vinkius HTTP endpoint URL. Then, pass this MCP Server toolset directly into your Agent constructor to give your model access to all seven Brazilian regulatory tools.

The framework raises a validation error immediately. This prevents your agent from making decisions based on incomplete or corrupted regulatory data.

Yes, this MCP Server is model-agnostic. You can run Pydantic AI with local models or other commercial providers while maintaining complete type safety across all ANVISA queries.

The `monografias_farmacopeia` tool returns clean structured text. Pydantic AI validates the structure, making it easy for your model to extract specific chemical properties without parsing raw HTML.

Yes, all connections run over HTTPS through secure V8 sandboxes. Your regulatory queries—whether searching for drug prices, cosmetic ingredients, or food notifications—are processed in an ephemeral environment and never stored.

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