How to Use the Asaas MCP in LangChain

Q: How do I connect the Asaas MCP Server to my LangChain agent?

Install langchain-mcp-adapters and use MultiServerMCPClient pointing to the Vinkius endpoint. You then fetch the tools with client.gettools() and pass them directly to your agent constructor.

Run complex Brazilian payment workflows by hooking the Asaas MCP Server directly into 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 Asaas MCP to LangChain

Create your Vinkius account to connect Asaas 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 Asaas with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Brazilian payment runs inside LangChain loops

The `create_payment` tool lets your LangChain agent generate Pix keys or bank slips and feed them immediately to subsequent chain steps. You build multi-step financial runs where the output of one Brazilian customer check determines if the agent fires off a new charge. LangSmith tracks every tool execution, showing you the exact inputs sent to `create_customer` and the raw JSON returned. This transparency prevents silent failures when registering foreign or local entities in your automated workflows.

Verify accounts and track balances in active runs

The `get_balance` tool retrieves your current Brazilian Real balance so your agent can verify available funds before initiating transfers. This tool connects directly to your active LangChain decision nodes to halt outbound transfers if the account drops below your specified threshold. If the balance check passes, the agent triggers `get_account_check` to verify the API connection is active. You get a deterministic financial pipeline that checks its own status before executing sensitive financial operations.

Audit active subscriptions and customer records

The `list_subscriptions` tool pulls active customer billing schedules directly into your LangChain vector stores or memory buffers. Your agent reads these schedules to flag delinquent accounts or identify customers who need manual billing intervention. Combining this with `list_customers` lets your agent build a complete profile of your Brazilian client base. The agent cross-references these lists in real time, matching transaction histories to ensure your records stay clean.

Setup guide

Set up Asaas 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 Asaas 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({
    "asaas-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 Asaas 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 Asaas. 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 Asaas 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 Asaas MCP in LangChain

Install `langchain-mcp-adapters` and use `MultiServerMCPClient` pointing to the Vinkius endpoint. You then fetch the tools with `client.get_tools()` and pass them directly to your agent constructor.

Yes, every call to the Asaas API goes through LangSmith tracing automatically if you have it configured. You'll see the exact payload sent to `create_payment` and the raw response from the Brazilian banking network.

You handle retries by wrapping the tools in a LangGraph node with a custom retry policy. This prevents transient network errors from failing your entire payment run.

You instantiate separate client sessions for each account token using the stateful session helper. This keeps your Brazilian customer databases isolated during parallel runs.

Vinkius runs this MCP Server in an isolated V8 sandbox, meaning your API tokens never leak. Your customer records and transaction balances pass directly to your LangChain runtime without persistent middleman storage.

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