How to Use the Focus Admin MCP in LangChain

Q: How do I connect Focus Admin to my LangChain agents?

Install the langchain-mcp-adapters package and initialize the MultiServerMCPClient pointing to the Vinkius endpoint. From there, call client.gettools() to pass the Focus Admin tools directly into your agent's tool list.

Q: Can I download PDF invoices using this integration?

Yes, the downloadnfedanfe tool returns the invoice PDF as a base64 string. Your LangChain agent can receive this string and write the file to your local disk or cloud storage.

Run multi-step fiscal compliance chains in LangChain by hooking your agent directly to the Focus Admin MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Focus Admin MCP to LangChain

Create your Vinkius account to connect Focus Admin 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 Focus Admin with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Correct and void tax documents in your chains

The `send_cc_e` tool lets your LangChain agent submit Correction Letters for NF-e directly through the Focus NFe API. This tool changes incorrect invoice data on the fly so you don't have to leave your code editor. If you make a mistake, you can use `cancel_cc_e` to undo the correction or `inutilize_numbering` to flag unused invoice numbers as void. Your agents can run these tools back-to-back in a single execution pipeline to handle compliance errors instantly.

Build multi-step fiscal audit pipelines in LangChain

The `list_nfe_by_period` tool fetches invoice data within specific timeframes to feed your LangChain data pipelines. Your agent can pull this tax data, parse it, and automatically decide which invoices require further inspection. By chaining this with `download_nfe_xml`, the agent downloads the raw XML files for any flagged documents without manual intervention. LangSmith traces every step of this document retrieval pipeline so you can monitor latency and token costs.

Automatically sync municipal service invoices

The `list_nfse_emitted` tool retrieves all service invoices issued by your company for any given date range. This tool works alongside `list_nfse_received` to pull incoming service invoices from your vendors. Connecting these tools to a LangChain agent lets you build automated reconciliation workflows. The agent checks both endpoints, compares the records against your internal database, and flags discrepancies for your accounting team.

Setup guide

Set up Focus Admin 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 Focus Admin 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({
    "focus-admin-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 Focus Admin 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 Focus NFe. 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 Focus Admin 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 Focus Admin MCP in LangChain

Install the `langchain-mcp-adapters` package and initialize the `MultiServerMCPClient` pointing to the Vinkius endpoint. From there, call `client.get_tools()` to pass the Focus Admin tools directly into your agent's tool list.

Yes, you can build a LangGraph workflow that orchestrates sequential tool calls. For example, your agent can run `list_nfe_by_period` and pass the resulting IDs to `download_nfe_xml` one by one.

Use LangSmith to trace the exact input inputs and output payloads of tools like `distribute_dfe`. If the Focus NFe API returns an error or rate limit, the trace shows the raw response payload immediately.

Yes, the `download_nfe_danfe` tool returns the invoice PDF as a base64 string. Your LangChain agent can receive this string and write the file to your local disk or cloud storage.

Your XML payloads, invoice numbers, and CNPJ details pass through a secure, ephemeral V8 isolate sandbox on Vinkius. No fiscal data is stored on our servers, and all requests go directly to the official Focus NFe 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