How to Use the KPA Flex MCP in LangChain

Q: How do I connect KPA Flex to LangChain?

Install the langchain-mcp-adapters and langgraph packages. Use the MultiServerMCPClient with your KPA Flex HTTP transport URL. Call client.gettools() and pass the resulting list directly into your ReAct agent.

Q: Can my LangChain agent run KPA Flex inspection reports automatically?

Yes. The agent uses the listehsinspections tool to pull recent data. You configure the chain to run on a schedule, passing the output into your notification systems.

Build multi-step EHS compliance pipelines with LangChain by chaining KPA Flex safety data into your workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect KPA Flex MCP to LangChain

Create your Vinkius account to connect KPA Flex 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 KPA Flex with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Workflows via LangChain MCP Server

The `kpa-flex-mcp` tools integrate directly into your LangChain ReAct agents to pull safety data. You start by running `list_ehs_inspections` to grab recent safety checks across all your active sites. If an agent spots a failed check, it immediately chains that output into `get_inspection_details` to read the exact safety violations logged by the site manager. LangSmith tracks every token and API call during this process. You see exactly how long your agent took to map the failed inspection against the `get_employee_ehs_profile` tool to find out who was responsible. You build a pipeline that automatically cross-references site statistics without writing custom integration code.

Chain Safety Training Records

Connect `list_safety_trainings` to your LangChain graph to verify employee certifications. Your agent pulls the raw list of completed courses and feeds that data into a custom prompt. The chain then queries `list_flex_employees` to cross-check active staff against expired safety modules. This setup turns static compliance reporting into an active, multi-step reasoning task. When a worker misses a required safety module, the agent uses `search_ehs_reports` to see if that same employee caused any recent incidents. The output of one tool dictates the input of the next.

Track Equipment Assets

Fetch active equipment logs using the `list_company_assets` tool inside your autonomous workflows. LangChain handles the tool execution while your agent decides which heavy machinery needs an audit. It passes the asset IDs to `list_custom_forms` to find the exact safety checklist required for that specific machine. You get full visibility into how your agent queries the KPA Flex database. If the agent hits a dead end looking for a form schema via `get_form_schema`, it automatically pivots to query site-wide safety statistics using `get_flex_site_stats`. The reasoning loop stays intact.

Setup guide

Set up KPA Flex 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 KPA Flex 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({
    "kpa-flex-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 KPA Flex 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 KPA Flex. 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 KPA Flex 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 KPA Flex MCP in LangChain

Install the `langchain-mcp-adapters` and `langgraph` packages. Use the `MultiServerMCPClient` with your KPA Flex HTTP transport URL. Call `client.get_tools()` and pass the resulting list directly into your ReAct agent.

Yes. The agent uses the `list_ehs_inspections` tool to pull recent data. You configure the chain to run on a schedule, passing the output into your notification systems.

LangSmith captures the exact inputs and outputs of every MCP tool call. You see the parameters sent to `get_employee_ehs_profile` and the raw JSON response returned by the server.

You build a graph where the agent decides the execution order. It might start with `get_flex_site_stats`, identify a problematic location, and then loop through `list_company_assets` to pinpoint faulty equipment.

The server processes sensitive worker certification records and EHS profiles. The MCP protocol ensures zero-trust execution where your LangChain client only reads the data via a temporary, ephemeral session. No employee records are permanently stored outside your designated vector stores.

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