How to Use the Câmara dos Deputados (v2) MCP in LlamaIndex

Q: How do I configure Câmara dos Deputados (v2) with LlamaIndex?

Run pip install llama-index-tools-mcp. Create a BasicMCPClient with the endpoint URL, wrap it in McpToolSpec, and pass the async tool list to your FunctionAgent.

Q: Can LlamaIndex filter which Câmara dos Deputados (v2) tools are active?

You pass the allowedtools array when initializing the spec. This restricts your RAG pipeline to only use specific endpoints like getdeputado while ignoring massive list operations.

Q: How do I find out how a specific politician voted?

Your agent uses the listvotacaovotos tool. It returns the exact nominal vote cast by individual members during a specific session.

Index Brazilian legislative speeches and voting records directly into LlamaIndex vector stores.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Câmara dos Deputados (v2) MCP to LlamaIndex

Create your Vinkius account to connect Câmara dos Deputados (v2) 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 Câmara dos Deputados (v2) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build RAG systems with this MCP Server

The `list_deputado_discursos` tool pulls raw transcripts of politician speeches directly into your LlamaIndex data ingestion pipeline. Instead of just reading the text once, your application embeds these transcripts and stores them in a vector database for semantic search. Querying past sessions becomes highly accurate because the answers ground themselves in actual API data. You ask your agent about a specific debate, and it searches the index built from `get_evento` and `list_evento_pauta` outputs rather than hallucinating facts.

Index parliamentary expenses and committee memberships

Mapping out financial data requires calling `list_deputado_despesas` and indexing the resulting JSON arrays. Your RAG setup can combine these expense reports with committee assignments pulled from `list_orgao_membros`. This creates a unified knowledge base where financial records and political influence sit side by side. When users query the system, the FunctionAgent uses `get_deputado` to fetch real-time updates and compares them against your historical vector store.

Track bill propositions and legislative history

You feed the entire history of a law into your index by looping through `list_proposicoes` and `list_proposicao_tramitacoes`. The framework converts these complex legislative steps into searchable documents. Finding related laws is just a matter of semantic similarity. The agent can also trigger `list_proposicao_relacionadas` on the fly if the vector search decides it needs more current context from the Brazilian Chamber.

Setup guide

Set up Câmara dos Deputados (v2) 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 Câmara dos Deputados (v2) 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 Câmara dos Deputados (v2) tools.",
)
response = await agent.run("List recent Câmara dos Deputados (v2) 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 Câmara dos Deputados. 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 Câmara dos Deputados (v2) 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 Câmara dos Deputados (v2) MCP in LlamaIndex

Run `pip install llama-index-tools-mcp`. Create a `BasicMCPClient` with the endpoint URL, wrap it in `McpToolSpec`, and pass the async tool list to your `FunctionAgent`.

You pass the `allowed_tools` array when initializing the spec. This restricts your RAG pipeline to only use specific endpoints like `get_deputado` while ignoring massive list operations.

The MCP integration automatically formats the complex Brazilian government XML/JSON into documents your vector store understands. You skip writing custom parsers for all 49 endpoints.

Your agent uses the `list_votacao_votos` tool. It returns the exact nominal vote cast by individual members during a specific session.

The system only pulls public expense reports, speeches, and voting histories from the Chamber. The integration runs ephemerally, meaning your local vector embeddings never get sent back to the upstream government API.

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