How to Use the HCSS MCP in AutoGen

Q: How do I configure HCSS tools for AutoGen?

Use mcpservertools with StreamableHttpServerParams pointing to your endpoint. Pass the resulting tool list into your AssistantAgent constructor.

Q: Can AutoGen agents read HCSS timecards?

Yes. You grant an agent access to listtimecards. It can pull the weekly labor data and discuss discrepancies with other specialized agents in your chat.

Q: Does the framework handle the tool schema automatically?

McpToolAdapter translates the HCSS server schema directly into a format the Microsoft framework understands. You skip the manual mapping completely.

Q: How do AutoGen agents track HCSS equipment?

One agent calls getequipmentlocation to find the asset. Another agent might call getequipmentmeters to check its usage, then they debate whether to deploy it.

Deploy multi-agent AutoGen teams to debate and manage your HCSS construction operations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HCSS MCP to AutoGen

Create your Vinkius account to connect HCSS 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 HCSS with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent payroll verification

Assign `list_timecards` and `list_employees` to an auditor agent to review daily labor entries. This agent pulls the raw hours and flags anomalies for a secondary compliance agent to review. The two agents debate the findings. If a timecard looks heavy on overtime, the compliance agent checks the specific `list_cost_codes` to see if the work phase justifies the extra expense before approving it.

Negotiate fleet moves via MCP Server

Give your logistics agents access to `list_equipment` and `get_equipment_location` through the MCP Server. A superintendent agent requests a dozer, while a dispatcher agent checks where the closest idle machine sits. They don't just blindly assign hardware. The dispatcher agent pulls `get_equipment_meters` to check the odometer. If the machine is due for maintenance, the agents negotiate a different asset assignment.

Validate project handoffs automatically

Use `list_estimates` and `get_bid_items` to arm a precon agent with the original project budget. An operations agent then pulls `list_jobs` to see how the project is actually being built in the field. The agents compare the bid against reality. If the field is missing specific work phases outlined in `list_precon_projects`, the precon agent challenges the operations setup until they reach consensus on the discrepancy.

Setup guide

Set up HCSS 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 HCSS 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="HCSS_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent HCSS 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="HCSS_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent HCSS 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 HCSS. 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 HCSS 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 HCSS MCP in AutoGen

Use `mcp_server_tools` with `StreamableHttpServerParams` pointing to your endpoint. Pass the resulting tool list into your `AssistantAgent` constructor.

Yes. You grant an agent access to `list_timecards`. It can pull the weekly labor data and discuss discrepancies with other specialized agents in your chat.

`McpToolAdapter` translates the HCSS server schema directly into a format the Microsoft framework understands. You skip the manual mapping completely.

One agent calls `get_equipment_location` to find the asset. Another agent might call `get_equipment_meters` to check its usage, then they debate whether to deploy it.

You maintain total control over your endpoints. When your agents query `list_employees` or `list_equipment`, authentication happens via a single endpoint token. The Vinkius infrastructure drops all data immediately after the API returns the payload.

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