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

Q: Can I trace ANVISA (Portal de APIs) tool calls in LangChain using LangSmith?

Yes, every execution of tools like precosmedicamentos or consultarmedicamentos is tracked with full inputs and outputs. You can monitor latency and token costs for each regulatory query.

Query official Brazilian drug prices and food registrations directly within your LangChain reasoning loops.

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 LangChain

Create your Vinkius account to connect ANVISA (Portal de APIs) to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Verify Brazilian Drug Prices in LangChain Loops

This MCP Server exposes raw regulatory data directly to your ReAct agents, allowing them to pull real-time pricing data via `precos_medicamentos`. By linking these tools, your agent can take the output of `consultar_medicamentos` and feed it directly into a custom pricing sheet. You get a fully traceable chain in LangSmith showing exactly how the agent resolved the drug's registration status before checking its price.

Automate Food and Cosmetic Compliance Checks

Your pipeline can run checks on imported goods by calling `registros_alimentos` to check a food product's registration. If the shipment also contains personal care items, the same LangChain agent executes `consultar_cosmeticos` to verify the cosmetics registry. You don't have to write manual routing logic because the agent dynamically chooses the correct ANVISA tool based on the product list.

Run Pharmacopeia Research with Multi-Step Chains

Deep chemical research requires pulling official monographs using `monografias_farmacopeia`. From there, the agent can cross-reference those substances with sanitizing products using `consultar_saneantes` to flag any regulatory discrepancies. Having this MCP Server connected means your chains can audit entire chemical inventories without manual intervention.

Setup guide

Set up ANVISA (Portal de APIs) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes ANVISA (Portal de APIs) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "anvisa-portal-de-apis-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent ANVISA (Portal de APIs) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install the adapter using pip install langchain-mcp-adapters langgraph and configure the MultiServerMCPClient with the Vinkius HTTP endpoint. Once connected, call client.get_tools() and pass them to your agent.

Yes, every execution of tools like precos_medicamentos or consultar_medicamentos is tracked with full inputs and outputs. You can monitor latency and token costs for each regulatory query.

Your agent uses a ReAct loop to chain tools, meaning it can search for a medicine's registration first and then look up its price in a single run. The output of one tool automatically feeds into the next.

LangChain lets you pass these tools alongside your existing vector store retrievers. Your agent can query your internal product manuals and then pull official ANVISA data to verify compliance.

Vinkius runs the server in an isolated sandbox, meaning your search queries for specific active ingredients or medicine registration numbers are never stored. Only the raw, ephemeral API requests to the official Brazilian portal are processed.

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