How to Use the Cuiabá Transparency MCP in LangChain

Build municipal data pipelines connecting Cuiabá public finances directly to your LangChain agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cuiabá Transparency MCP to LangChain

Create your Vinkius account to connect Cuiabá Transparency 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 Cuiabá Transparency with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Cuiabá Transparency MCP Server

LangChain excels at linking sequential tool calls. Your agent can hit `list_revenues` to pull incoming tax figures, then instantly feed that context into `list_expenses` to calculate municipal surplus. You build the reasoning logic, and the ReAct agent executes the sequence. Every step of this financial analysis gets logged in LangSmith. You track exactly how many tokens the agent burned while comparing personnel costs via `list_personnel` against the total budget.

ReAct Agents for Public Tenders

Public procurement requires checking multiple data points before reaching a conclusion. Your LangGraph setup can instruct an agent to run `list_contracts` to find recent infrastructure bids, then conditionally check `list_budget` to confirm funding allocation. Passing these outputs between MCP tools happens natively. The agent decides the execution order based on intermediate results, meaning you don't write hardcoded API requests for every possible municipal query.

Persistent Context Across Sessions

Analyzing city finances takes multiple prompts. Using LangChain's persistent sessions, your client remembers the output of yesterday's `list_budget` call. You just ask for the variance against today's newly published figures. Combine this MCP server with other database endpoints in the same chain. Pull municipal data, format it, and write it straight to your local Postgres instance without writing integration scripts.

Setup guide

Set up Cuiabá Transparency 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 Cuiabá Transparency 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({
    "cuiaba-transparency-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 Cuiabá Transparency 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 Cuiabá Transparency Portal. 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 Cuiabá Transparency 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 Cuiabá Transparency MCP in LangChain

Install the langchain-mcp-adapters package first. Then initialize a MultiServerMCPClient pointing to the server URL and pass the output of client.get_tools() to your ReAct agent.

Yes, ReAct agents handle multi-step reasoning by design. They will call `list_revenues` and then `list_expenses` in a single run if your prompt requires a combined financial summary.

Every tool invocation logs directly to your trace. You see the exact payload sent to the MCP endpoint and the raw JSON returned by the municipal database.

The adapter supports both standard input/output for local execution and HTTP transports for remote connections. You configure this in the client initialization block.

Vinkius isolates all execution within a V8 sandbox. When your agent queries municipal servant salaries via this server, the ephemeral container processes the request and immediately destroys the environment. Your endpoint token is the only authentication required.

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