How to Use the KPA Flex MCP in AutoGen

Q: How do I load KPA Flex tools into AutoGen?

Install the autogen-extmcp package. Use mcpservertools with a StreamableHttpServerParams configuration pointing to your endpoint. Pass the resulting tool list directly into your AssistantAgent constructor.

Q: Can multiple AutoGen agents share the KPA Flex connection?

Yes. You can provide the listehsinspections and listcustomforms tools to a shared group chat. Any agent in the conversation can invoke the tools when they need to pull safety data to support their argument.

Q: How does AutoGen handle KPA Flex schema conversions?

The McpToolAdapter automatically translates the complex JSON schemas returned by the API into formats the conversational agents understand. You do not write any manual parsing logic.

Build debating AutoGen agents that negotiate safety compliance decisions using live KPA Flex data.

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 AutoGen

Create your Vinkius account to connect KPA Flex to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate Compliance via AutoGen MCP Server

The `kpa-flex-mcp` tools allow your conversational agents to argue over safety protocols using real data. You assign `get_flex_site_stats` to a compliance agent and `list_safety_trainings` to an HR agent. When a site's safety score drops, the two agents debate whether the issue is a lack of training or a systemic management failure. They do not just execute commands. The compliance agent pulls the failure logs, while the HR agent cross-references the staff roster via `list_flex_employees`. They challenge each other's findings until they reach a consensus on which corrective action to recommend to the site director.

Negotiate Equipment Audits

Give your AutoGen assistants access to `list_company_assets` to manage physical machinery inspections. A risk-assessment agent queries the asset list and flags overdue maintenance. A productivity agent argues that taking the machines offline will hurt output, forcing a negotiation based on the severity of the hazard. The risk agent calls `get_inspection_details` to present hard evidence of previous mechanical failures. The conversation continues until the agents agree on a phased inspection schedule. You watch them weigh the operational cost against the strict EHS requirements.

Resolve EHS Incident Reports

Feed complex workplace incidents into your multi-agent system using `search_ehs_reports`. One agent acts as the safety inspector, pulling the raw incident data. Another acts as the union representative, checking the involved worker's background using `get_employee_ehs_profile`. They analyze the event from competing perspectives. The inspector might suggest immediate disciplinary action based on the report. The union agent pushes back by using `get_form_schema` to prove the inspection checklist itself was flawed. They deliver a balanced, multi-faceted summary of the incident.

Setup guide

Set up KPA Flex MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes KPA Flex tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="KPA Flex_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent KPA Flex data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="KPA Flex_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent KPA Flex data")
    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 AutoGen

Install the `autogen-ext[mcp]` package. Use `mcp_server_tools` with a `StreamableHttpServerParams` configuration pointing to your endpoint. Pass the resulting tool list directly into your `AssistantAgent` constructor.

Yes. You can provide the `list_ehs_inspections` and `list_custom_forms` tools to a shared group chat. Any agent in the conversation can invoke the tools when they need to pull safety data to support their argument.

The `McpToolAdapter` automatically translates the complex JSON schemas returned by the API into formats the conversational agents understand. You do not write any manual parsing logic.

This is where the multi-agent debate shines. If one agent pulls bad data from `search_ehs_reports`, you configure a reviewer agent to double-check the findings using `get_inspection_details`. They correct each other before presenting the final verdict.

The system reads precise employee incident histories and equipment failure logs. The architecture relies on a zero-trust model where authentication is handled server-side. Your agents read the data in memory during the conversation, leaving no persistent footprint once the session ends.

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