How to Use the Flowcode MCP in LangChain

Q: How do I pass a dynamic QR code from createflowcode to another tool in the LangChain MCP integration?

You chain the outputs directly. Pass the output of createflowcode to the getflowcodeimage tool within a LangGraph state graph or a simple run chain.

Q: Can a LangChain agent automatically organize codes using this Flowcode MCP Server?

Yes, your agent can query listfolders to find the correct directory, then use createflowcode to place the new asset there. LangSmith will trace each tool call to verify the agent selected the correct folder path.

Q: How does LangChain handle real-time scan logs from this MCP Server?

The agent calls getrecentscans to fetch the latest activity log. It then parses these entries to trigger downstream alerts or database updates in your chain.

Q: How does this LangChain integration protect my Flowcode CRM contacts and scan data?

Your CRM contacts retrieved via getflowpagecontacts stay inside your local LangChain execution environment. Vinkius runs the server in an isolated, ephemeral sandbox that never stores or logs your customer data.

Build multi-step LangChain pipelines that generate dynamic QR codes and trace scan performance from print to conversion.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flowcode MCP to LangChain

Create your Vinkius account to connect Flowcode 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 Flowcode with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate QR Generation in Chains

The `create_flowcode` tool lets your agent generate dynamic QR codes on the fly and feed them directly into the next link of your LangChain pipeline. Your agent handles the entire asset generation step, passing the resulting code to `get_flowcode_image` to fetch the actual graphic before saving it to a designated folder. LangSmith traces this entire transition, showing you the exact token cost and latency of the generation step. You see exactly when the model decides to create a code and how it structures the payload.

Trace Multi-Step Offline Funnel Analytics

The `list_conversion_rates` tool pulls scan-to-action performance metrics directly into your LangChain decision loops. Your agent uses these raw numbers to decide whether to pivot a campaign mid-run or maintain the current print distribution strategy. By feeding this data into a ReAct agent, the model evaluates physical scan performance alongside your digital conversion metrics. You track how offline campaigns convert without leaving your terminal or losing visibility in your LangSmith dashboard.

Map Scan Locations via LangChain MCP Server Tools

The `get_geographic_analytics` tool extracts geographic scan data so your agent can map where users interact with your physical assets. LangChain passes these regional coordinates to your database or mapping integrations within the same execution chain. This setup lets you build autonomous regional optimization loops. The agent reads the location data, compares it against active campaigns, and automatically schedules new codes for high-performing areas.

Setup guide

Set up Flowcode 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 Flowcode 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({
    "flowcode-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 Flowcode 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 Flowcode. 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 Flowcode 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 Flowcode MCP in LangChain

You chain the outputs directly. Pass the output of `create_flowcode` to the `get_flowcode_image` tool within a LangGraph state graph or a simple run chain.

Yes, your agent can query `list_folders` to find the correct directory, then use `create_flowcode` to place the new asset there. LangSmith will trace each tool call to verify the agent selected the correct folder path.

The agent calls `get_recent_scans` to fetch the latest activity log. It then parses these entries to trigger downstream alerts or database updates in your chain.

Manual exports take hours. LangChain automates the decision loop by letting an agent query `list_campaigns` and adjust physical marketing distribution based on live performance data.

Your CRM contacts retrieved via `get_flowpage_contacts` stay inside your local LangChain execution environment. Vinkius runs the server in an isolated, ephemeral sandbox that never stores or logs your customer data.

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