How to Use the Humaans MCP in AutoGen

Use AutoGen agents to debate and resolve HR tasks by accessing your Humaans organization data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Humaans MCP to AutoGen

Create your Vinkius account to connect Humaans 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 Humaans with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate HR status with AutoGen

Configure your agents to cross-reference `list_employees` and `list_roles` when making personnel decisions. One agent checks the data while another verifies compliance against company policy. This creates a system where agents negotiate based on real Humaans data. You get a consensus-driven outcome without manually checking every single employee record yourself.

Negotiate time off with AutoGen

Your agents can discuss leave requests by calling `list_leaves` and `list_public_holidays`. They compare the request against existing company coverage to reach a decision. It removes the back-and-forth for simple approvals. By using `get_me` to identify the requester, the agents ensure the decision is tailored to the specific employee context.

Analyze org structure in AutoGen

Have your agents debate team alignment using `list_teams` and `list_departments`. They can identify structural bottlenecks by looking at the raw hierarchy provided by Humaans. This is useful for planning and organizational review. The agents don't just read the data; they challenge each other's interpretations until they agree on the best path forward.

Setup guide

Set up Humaans 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 Humaans 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="Humaans_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Yes, you pass the tool list directly to your AssistantAgent. AutoGen will then decide when to call the tools during the conversation to get the info it needs.

The agents exchange information to converge on an answer. They can access any of the 10 tools to ensure their debate is grounded in your actual HRIS data.

The MCP adapter automatically handles schema conversion for all tool calls. Your agents can reliably invoke `list_employees` or `list_offices` as part of their standard workflow.

You control which tools are passed to the agent constructor. You can restrict access to sensitive endpoints like `list_documents` while keeping others available.

All requests to your HRIS are mediated through the Vinkius platform. Your Humaans credentials remain secure, and the agents only interact with the data during the active conversation loop.

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