How to Use the ApplicantStack MCP in AutoGen

Q: How do I configure ApplicantStack MCP Server tools for AutoGen agents?

Install autogen-extmcp. You use mcpservertools with a StreamableHttpServerParams pointing to your Vinkius URL, then pass the resulting tool list to your AssistantAgent constructor.

Q: What happens if the API connection fails during an agent debate?

Assign the getaccountcheck tool to a supervisor agent. If a data pull fails, the supervisor runs the check to diagnose whether the auth token expired or the API is unreachable.

Connect ApplicantStack to AutoGen and let multi-agent systems debate candidate qualifications and hiring stages.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ApplicantStack MCP to AutoGen

Create your Vinkius account to connect ApplicantStack 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 ApplicantStack with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Equip AutoGen agents with the MCP Server

The ApplicantStack MCP Server equips your agents with seven distinct tools to read jobs, evaluate candidates, and update hiring stages. You assign the `list_candidates` and `get_candidate` tools to a screening agent that pulls fresh applications into the chat. A second agent acts as the hiring manager, reviewing the first agent's findings against the role requirements pulled via `get_job`. They debate the candidate's fit based on the raw API data before reaching a consensus on whether to proceed.

Debate candidate progression

Your multi-agent system uses `update_candidate` to move applicants through the hiring workflow only after deliberation. A technical agent evaluates the skills, while an HR agent checks salary expectations, arguing over the candidate's viability. Once the agents agree, one of them executes the stage change. You verify the system has access to perform this action by having an administrative agent run `get_account_check` at the start of the conversation.

Monitor headcount and onboarding

Agents track your overall recruitment velocity by calling `list_jobs` and `list_hires`. A reporting agent pulls the active job count and compares it against recent onboarding numbers to identify bottlenecks in the pipeline. These agents discuss the metrics in the shared conversation thread. If they spot a role that has been open too long without recent hires, they flag it for human review, using the exact data pulled from the API.

Setup guide

Set up ApplicantStack 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 ApplicantStack 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="ApplicantStack_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install `autogen-ext[mcp]`. You use `mcp_server_tools` with a `StreamableHttpServerParams` pointing to your Vinkius URL, then pass the resulting tool list to your `AssistantAgent` constructor.

You assign specific tools to specific agents. One agent might hold the `get_job` tool to act as the requirements expert, while another holds `get_candidate` to act as the resume reviewer.

After the agents debate and reach consensus, the designated actor calls the `update_candidate` tool. The agent passes the new stage value back to the API to advance the applicant.

Assign the `get_account_check` tool to a supervisor agent. If a data pull fails, the supervisor runs the check to diagnose whether the auth token expired or the API is unreachable.

The system isolates candidate emails, phone numbers, and job histories inside a V8 sandbox on Vinkius. The environment executes the request and self-destructs, ensuring no personal data remains on the host servers.

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