How to Use the HrFlow.ai MCP in AutoGen

Q: Can I have one AutoGen agent find candidates with HrFlow.ai and another one analyze them?

Yes. You can create a "Sourcing" agent using searchprofiles. It then hands off the top candidates to a "Screening" agent that uses askprofile to conduct a preliminary Q&A.

Q: How do I give HrFlow.ai tools to my AutoGen agents?

Use the mcpservertools function from the autogen-ext library. It connects to the MCP server and returns a list of tools you can pass directly to your AssistantAgent's constructor.

Assemble a team of AutoGen agents to debate and decide on hiring strategy using live HrFlow.ai data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HrFlow.ai MCP to AutoGen

Create your Vinkius account to connect HrFlow.ai 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 HrFlow.ai with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let Your Agents Debate Hiring Choices

Hiring isn't a simple script. With AutoGen, you create a team of agents that collaborate. A "Sourcing Agent" uses `search_profiles` to find candidates, passing them to a "Vetting Agent." The Vetting Agent then uses `score_profiles` and `ask_profile` to analyze the list. It can challenge the Sourcing Agent's choices, asking for a new search with different criteria. The final output is a consensus, not just a list.

Simulate a Hiring Committee with this MCP Server

You can model your whole team. Create an "Engineering Manager" agent that prioritizes technical skills and a "Recruiter" agent that looks for culture fit. Give them a job from `list_jobs` and a pool of candidates from `list_profiles`. The agents will converse, using tools like `unfold_profile` to argue their points. The conversation transcript shows you exactly *why* they ranked a candidate a certain way. It surfaces disagreements you'd normally only find in a live debrief.

Automated Resume Triage and Review

Set up a "Clerk" agent whose only job is to watch for new resumes. When one appears, it calls `parse_profile` to structure the data. Simple enough. But then it gets interesting. The Clerk passes the structured profile to a group chat with other agents. A "Compliance" agent might check for red flags, while a "Sourcing" agent checks if the profile is a good match for any open roles found with `search_jobs`. The work is automatically delegated.

Setup guide

Set up HrFlow.ai 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 HrFlow.ai 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="HrFlow.ai_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

AutoGen is about conversation. Instead of one agent executing a plan, multiple agents use HrFlow.ai tools like `score_profiles` to gather evidence for a debate, leading to a group decision.

Yes. You can create a "Sourcing" agent using `search_profiles`. It then hands off the top candidates to a "Screening" agent that uses `ask_profile` to conduct a preliminary Q&A.

Use the `mcp_server_tools` function from the `autogen-ext` library. It connects to the MCP server and returns a list of tools you can pass directly to your AssistantAgent's constructor.

Absolutely. The entire conversation, including which agent called which tool (`score_profiles`, `ask_profile`, etc.) and what the results were, is logged. This gives you a full audit trail of the decision-making process.

The HrFlow.ai candidate data, like structured profiles and scores, is passed between agents in memory during the conversation. You must treat the conversation logs as sensitive, as they will contain PII. Ensure your environment and log storage are secure, as AutoGen itself doesn't automatically redact this data.

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