How to Use the Join MCP in AutoGen

Q: How do I register Join recruiting tools with my AutoGen agents?

Install autogen-extmcp and use the mcpservertools function with your Vinkius server URL. Pass the returned tools list directly into your AssistantAgent constructor to give them access to the recruiting API.

Q: Can AutoGen agents call Join job tools during a group chat?

Yes, any agent in the group chat can invoke listjobs to share active job postings with the other agents. The framework automatically converts the tool schema so all agents understand the available positions.

Let your AutoGen agents debate candidate qualifications and job matches using live data from your Join pipeline.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Join MCP to AutoGen

Create your Vinkius account to connect Join 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 Join with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run candidate reviews using this MCP Server in AutoGen

Hiring decisions shouldn't rely on a single model's opinion. With this MCP Server, you can set up a multi-agent system where a screening agent pulls application details using `get_application` and a technical agent evaluates them against the job requirements fetched by `get_job`. These agents talk to each other to find discrepancies. If the screening agent flags a candidate, the technical agent can query `get_candidate` to double-check their background, forcing a collaborative decision before moving them to the next stage.

Coordinate hiring managers and departments automatically

Managing communication between different departments is a bottleneck. AutoGen allows a coordinator agent to check active teams using `list_departments` and match them with available hiring managers retrieved via `list_users`. The agents negotiate who should review which candidate. Instead of spamming everyone, the coordinator agent assigns the candidate profile to the correct team lead based on the location data fetched from `list_locations`.

Audit recruiting pipelines with specialized critic agents

Avoid bias and errors in your screening process. You can deploy a critic agent whose sole job is to audit the decisions of your screening agents by reviewing the full pipeline status via `list_applications`. The critic agent requests specific profiles using `list_candidates` to verify that no promising applicants were skipped. This multi-agent verification loop ensures your hiring pipeline remains fair, consistent, and thoroughly vetted.

Setup guide

Set up Join 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 Join 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="Join_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install `autogen-ext[mcp]` and use the `mcp_server_tools` function with your Vinkius server URL. Pass the returned tools list directly into your `AssistantAgent` constructor to give them access to the recruiting API.

Yes, any agent in the group chat can invoke `list_jobs` to share active job postings with the other agents. The framework automatically converts the tool schema so all agents understand the available positions.

The agents use conversational consensus. One agent might pull candidate details using `get_candidate` and argue for hiring, while a budget agent analyzes the role via `get_job` and objects, continuing the debate until they agree.

Yes, this setup uses Streamable HTTP transport parameters to connect your local AutoGen agents to the managed Vinkius runtime. This ensures fast tool execution without needing complex local server setups.

Your candidate profiles, interview notes, and contact info processed by this MCP server are run in an ephemeral V8 sandbox managed by Vinkius. No data is stored permanently, keeping your sensitive recruiting records completely private.

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