How to Use the Bleez MCP in LangChain

Q: Can LangChain trace Bleez tool execution in LangSmith?

Yes, every call to listinvoices or createaccountingentry shows up as a distinct run in your LangSmith dashboard. You can track latency, input parameters, and exact payloads for every Brazilian tax operation.

Q: Can my agent handle Brazilian supplier lookups?

Absolutely. Your agent calls listsuppliers to pull active vendor profiles, allowing it to cross-reference incoming bills before executing any financial writes.

Feed live Brazilian accounting data straight into your LangChain runs to build self-correcting financial pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bleez MCP to LangChain

Create your Vinkius account to connect Bleez 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 Bleez with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chaining Brazilian Invoices Into LangChain Runs

Your LangChain agent can now trigger Bleez invoicing directly inside your active pipeline chains. By exposing `create_invoice`, this MCP Server lets your runner check customer details first, verify the amount, and spin up a new invoice in one clean step. If a step fails, LangSmith catches it. You see exactly why a chain call to `list_customers` or `create_invoice` choked, letting you debug Bleez payment runs without digging through raw logs.

Multi-Step Accounting Entry Pipelines

Stop manually copying numbers into your ledger. This MCP Server gives your LangChain agent the power to run `create_accounting_entry` based on live transaction feeds in your chains. The LangChain agent grabs raw invoice data, matches it against `list_accounting_entries`, and writes the correct double-entry lines to Bleez. You get clean Brazilian financial records without writing custom glue code.

Automated Document Processing Chains

Toss raw receipts or XML files into your LangChain runs. This MCP Server lets your agent use `upload_document` to push files directly into Bleez, letting the platform parse them for local compliance. Once uploaded, the LangChain agent chains a call to `list_suppliers` to match the document to an existing Bleez vendor. It keeps your entire Brazilian e-commerce back office running on autopilot.

Setup guide

Set up Bleez 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 Bleez 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({
    "bleez-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 Bleez 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 Bleez. 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 Bleez 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 Bleez MCP in LangChain

Install the MCP adapter package and initialize the client pointing to our hosted endpoint. Grab the tools with `client.get_tools()` and pass them directly into your agent's tool list to start running invoicing workflows.

Yes, every call to `list_invoices` or `create_accounting_entry` shows up as a distinct run in your LangSmith dashboard. You can track latency, input parameters, and exact payloads for every Brazilian tax operation.

It does. You can combine this server with a database or email client using `MultiServerMCPClient` to build complex agents that read local DBs and write to Bleez.

Absolutely. Your agent calls `list_suppliers` to pull active vendor profiles, allowing it to cross-reference incoming bills before executing any financial writes.

We run your tool calls in isolated, ephemeral V8 sandboxes. Your sensitive invoices, supplier records, and accounting entries are never stored on our platform, passing directly to the endpoint over encrypted tunnels.

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