How to Use the Hurma MCP in AutoGen

Let your AutoGen agents debate hiring decisions and coordinate leave requests using live Hurma HR data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hurma MCP to AutoGen

Create your Vinkius account to connect Hurma 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 Hurma with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent hiring debates with this MCP Server

The `get_candidate_details` tool feeds candidate profiles into an AutoGen conversation where different agents evaluate qualifications. A recruiter agent can argue for a candidate's background while a technical AutoGen agent analyzes their coding experience. Once they reach a consensus, the AutoGen system uses `create_candidate` to log the finalized profile or update their status. This debate-driven process ensures Hurma candidate evaluations inside AutoGen are thorough and unbiased before moving them forward.

Consensus-driven time-off approvals

Your AutoGen agents use `create_leave_request` to queue up time-off requests after negotiating team coverage. A scheduling agent checks the team schedule using `list_out_of_office` while another verifies the individual's remaining days. If both agents agree that the absence won't impact project deadlines, they authorize the request. This automated AutoGen negotiation keeps your Hurma-managed projects staffed without requiring constant manual oversight from managers.

Automated custom property mapping and validation

The `list_custom_properties` tool via the Hurma MCP Server allows your AutoGen agents to dynamically discover unique fields in your HR database before importing records. When importing a batch of employees, one AutoGen agent maps the legacy fields while a second agent validates them against current schema rules. By verifying the structure through `list_employees`, the AutoGen agents resolve mapping conflicts through conversation. This prevents malformed data from corrupting your Hurma employee database during large AutoGen migrations.

Setup guide

Set up Hurma 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 Hurma 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="Hurma_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You use the AutoGen MCP adapter to fetch the tools from your Vinkius server endpoint. Once loaded, pass the tools list to your AssistantAgent constructor so the agents can use them during conversations.

Yes, you can set up a coordinator agent and a recruiter agent that use `list_vacancy_stages` to find the right hiring step. They will discuss the candidate's status and update the pipeline collectively.

The agents will debate the conflict in their conversation thread, using tools like `get_employee_details` to verify the ground truth. They only execute updates once they resolve the discrepancy and reach a consensus.

The integration supports both stdio and Streamable HTTP transports. This allows your agents to communicate with the Hurma tools securely regardless of your infrastructure setup.

All employee data, candidate details, and overtime records retrieved via `get_employee_details` are kept strictly within your local agent session. Vinkius runs the Hurma MCP server in an isolated sandbox, preventing any sensitive HR information from leaking outside your network.

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