How to Use the intelliHR MCP in AutoGen

Q: How do AutoGen agents share intelliHR tool results with each other?

When one agent calls getperson, the returned profile is posted directly into the group chat. Other agents in the conversation can read this message and use the details to make their own decisions. This makes collaborative decision-making completely transparent.

Q: Can an AutoGen agent check intelliHR skills databases?

Yes, you can assign listskills to a specialized talent agent. During a planning session, this agent can query the skills directory to suggest internal candidates for open projects. The coordinator agent then reviews these suggestions.

Let AutoGen agents debate and coordinate organizational changes using live intelliHR data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect intelliHR MCP to AutoGen

Create your Vinkius account to connect intelliHR 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 intelliHR with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate Hiring Decisions in AutoGen Teams

The `list_jobs` tool provides a live feed of active positions that your hiring agent can analyze during a team discussion. A second agent can challenge whether these roles match current department needs based on other data sources. This collaborative setup ensures that no job posting goes out without being cross-checked. The agents debate the requirements until they reach a consensus, then present the final recommendation to you.

Verify Department Locations via Multi-Agent Debate

Your agent uses `list_locations` to verify office addresses before a third-party audit agent reviews them. If the audit agent spots a discrepancy, it flags the issue and asks the location agent to double-check the record. By letting these specialized agents argue over the details, you catch data entry mistakes before they cause compliance issues. You only get involved when the agents cannot resolve the conflict themselves.

Audit Platform Users with an MCP Server

The `list_users` tool lists all accounts with platform access, allowing your security agent to review permissions. A compliance agent can then cross-reference this list against active employees to find orphaned accounts. Running this audit via an MCP Server keeps your access logs clean and secure. The adapter handles the underlying API schemas, leaving your agents free to focus on finding security anomalies.

Setup guide

Set up intelliHR 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 intelliHR 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="intelliHR_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

When one agent calls `get_person`, the returned profile is posted directly into the group chat. Other agents in the conversation can read this message and use the details to make their own decisions. This makes collaborative decision-making completely transparent.

Yes, you can assign `list_skills` to a specialized talent agent. During a planning session, this agent can query the skills directory to suggest internal candidates for open projects. The coordinator agent then reviews these suggestions.

You use the adapter to fetch the tool definitions from the server. Pass this list to your assistant agent during setup, and the adapter will translate the schemas automatically. Your agents can then call tools like `list_business_entities` natively.

Yes, it connects using streamable HTTP transports. This allows your agents to stream tool outputs in real-time during long conversations. You can watch the raw data come in as the agents debate.

All API requests for user lists and business entity configurations are isolated within ephemeral runtime environments. We enforce strict transport-layer security and discard your access tokens as soon as the session ends. Your directory data never touches persistent storage.

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