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

Q: How do I index ANP (Revendedores de Combustíveis) data into a LlamaIndex vector store?

You call listcombustivelresellers to retrieve the active reseller list. Then, you convert the JSON output into Document objects and inject them into your VectorStoreIndex.

Q: Can I use LlamaIndex agentic RAG with the ANP (Revendedores de Combustíveis) server?

Yes. Your agent can decide to query listglpresellers whenever a user asks about LPG distribution in a specific state, indexing the result on the fly to answer the query.

Q: How does LlamaIndex handle the privacy of CNPJs queried from ANP?

The CNPJ numbers and regional filters passed to listcombustivelresellers are processed in an ephemeral V8 sandbox. No query history or Brazilian fuel reseller data is cached or stored on external servers.

Index live ANP (Revendedores de Combustíveis) fuel data into LlamaIndex vector stores for hallucination-free search.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build fuel registry RAG with LlamaIndex

Stop letting your model guess if a Brazilian gas station is active. This MCP Server lets your LlamaIndex pipeline query `list_combustivel_resellers` and index the official ANP records directly into your local document store. When users ask about fuel distribution networks in a specific municipality, the system pulls the exact matches from the indexed tool output. You get grounded answers based on real CNPJ records instead of outdated training data.

Semantic search over LPG distributor data

Connect `list_glp_resellers` to your LlamaIndex agent to query cooking gas suppliers dynamically. The agent fetches the active registrants, and the framework's indexers convert the raw text into searchable nodes. This makes it easy to find patterns across states and municipalities. Your agent can run semantic queries over the retrieved LPG metadata to identify clusters of suppliers without manual sorting.

Ground your vector indices in official ANP records

Use the tool specs to turn this MCP Server into a live data source for your indexing pipelines. Instead of relying on static PDFs of Brazilian energy regulations, your agent queries `list_combustivel_resellers` to pull live registration statuses. The framework merges this live API data with your existing vector stores, giving your RAG application a real-time view of Brazilian fuel resellers that updates every time you run a query.

Setup guide

Set up ANP (Revendedores de Combustíveis) MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all ANP (Revendedores de Combustíveis) MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to ANP (Revendedores de Combustíveis) tools.",
)
response = await agent.run("List recent ANP (Revendedores de Combustíveis) data")

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 LlamaIndex

You call `list_combustivel_resellers` to retrieve the active reseller list. Then, you convert the JSON output into Document objects and inject them into your VectorStoreIndex.

Yes. Your agent can decide to query `list_glp_resellers` whenever a user asks about LPG distribution in a specific state, indexing the result on the fly to answer the query.

It provides official, structured data from the Brazilian government. By feeding the output of `list_combustivel_resellers` directly into the LLM's context window, LlamaIndex avoids making up CNPJ numbers or address details.

You can filter the index inputs by CNPJ, state, or municipality using the parameters in `list_glp_resellers`. This keeps your vector store clean and focused on specific regions.

The CNPJ numbers and regional filters passed to `list_combustivel_resellers` are processed in an ephemeral V8 sandbox. No query history or Brazilian fuel reseller data is cached or stored on external servers.

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