How to Use the ANP (Revendedores de Combustíveis) MCP in LangChain

Q: How do I handle ANP (Revendedores de Combustíveis) pagination inside a LangChain agent?

You let the ReAct agent handle it. The agent calls listcombustivelresellers with specific state or municipality filters, inspects the payload, and decides if it needs to query the next batch based on your chain's prompt instructions.

Q: Can I trace ANP (Revendedores de Combustíveis) tool inputs in LangSmith?

Yes, absolutely. Every time your LangChain agent invokes listglpresellers, LangSmith logs the exact CNPJ or location arguments passed to this MCP Server alongside the latency of the ANP response.

Q: How do I filter fuel resellers by municipality?

Pass the exact municipality name as an argument to listcombustivelresellers. Your agent will extract the city name from your user's prompt and map it directly to the tool's parameters.

Get real-time Brazilian fuel and LPG reseller registries directly into your LangChain chains to verify CNPJ data on the fly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ANP (Revendedores de Combustíveis) MCP to LangChain

Create your Vinkius account to connect ANP (Revendedores de Combustíveis) 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 ANP (Revendedores de Combustíveis) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain ANP gas station checks with LangChain

Stop manually checking Brazilian gas station registries. With this MCP Server, your LangChain agents can call `list_combustivel_resellers` to pull active fuel dealer statuses inside any ReAct loop. It feeds the raw CNPJ and location data directly to the next step in your sequence without extra glue code. If a dealer's state or municipality changes, LangSmith catches the exact payload your agent received. You get full tracing on how the agent parsed the ANP response before it makes the next decision in your pipeline.

Validate LPG distributors in multi-step agents

Your LangChain agent can now query cooking gas providers using `list_glp_resellers` to verify if a business is legally registered. The tool returns official Brazilian government data, which your agent can immediately pass to a database write step. This setup lets you build autonomous verification pipelines. If the agent finds a mismatched CNPJ in the ANP registry, it flags the record and halts the chain before writing bad data to your production systems.

Aggregate multiple compliance endpoints

Combining this MCP tool with other compliance endpoints inside a single LangChain client is dead simple. Your agent queries `list_combustivel_resellers` to verify the physical location of a gas station, then checks a separate tax database to ensure the business is clean. You don't have to write custom wrappers for each API. The agent acts as the decision-maker, pulling from ANP data and passing the state variables downstream to your custom LangGraph nodes.

Setup guide

Set up ANP (Revendedores de Combustíveis) 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 ANP (Revendedores de Combustíveis) 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({
    "anp-revendedores-de-combustiveis-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 ANP (Revendedores de Combustíveis) 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 ANP (Agência Nacional do Petróleo). 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 ANP (Revendedores de Combustíveis) 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 ANP (Revendedores de Combustíveis) MCP in LangChain

You let the ReAct agent handle it. The agent calls `list_combustivel_resellers` with specific state or municipality filters, inspects the payload, and decides if it needs to query the next batch based on your chain's prompt instructions.

Yes, absolutely. Every time your LangChain agent invokes `list_glp_resellers`, LangSmith logs the exact CNPJ or location arguments passed to this MCP Server alongside the latency of the ANP response.

No. The server exposes the tools with clear JSON schemas, meaning the framework automatically translates them so your LangChain model knows how to format queries for fuel or LPG resellers.

Pass the exact municipality name as an argument to `list_combustivel_resellers`. Your agent will extract the city name from your user's prompt and map it directly to the tool's parameters.

Yes. The Vinkius sandbox isolates all requests, meaning the CNPJs and municipality names you pass to `list_glp_resellers` are never stored or leaked outside your execution context.

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