How to Use the Lever MCP in AutoGen

Q: How do I register the Lever MCP Server tools with AutoGen?

Install autogen-extmcp and use the mcpservertools helper with your server URL. Pass the resulting tools list directly to your AssistantAgent constructor.

Q: Can AutoGen agents coordinate to update a Lever opportunity stage?

Yes. An agent can call updateopportunitystage once the group chat reaches a consensus on the candidate's qualification.

Coordinate candidate screening and job postings across debating AutoGen agents connected to Lever.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lever MCP to AutoGen

Create your Vinkius account to connect Lever 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 Lever with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-driven AutoGen candidate progression

This MCP Server provides `update_opportunity_stage` and `get_opportunity_details` to let your AutoGen agents debate candidate qualifications before moving them. A screening agent evaluates the profile while a hiring manager agent reviews the interview feedback. They must reach a consensus before the system updates the stage in the ATS. This multi-agent debate prevents premature transitions. If the screening agent flags a missing requirement, the update is blocked, saving interviewer time and keeping your pipeline clean.

Collaborative job posting creation

The `create_job_posting` tool on this MCP Server allows AutoGen agents to draft, review, and publish new roles collaboratively. One agent writes the initial job description based on team requirements, while a compliance agent checks for bias or formatting errors. Once both approve, the finalized posting is written to your account. This setup guarantees that no raw, unreviewed descriptions make it to the public board. The entire workflow runs within an automated conversation, outputting a polished posting via the API.

Archiving opportunities with multi-agent validation

Running `archive_hiring_opportunity` via AutoGen ensures that candidates are only rejected after a structured review process. A rejection agent flags candidates who do not match the criteria, while a partner agent verifies if they might fit other open roles. Only when both agents agree does the system execute the archive command. This prevents accidental rejections and preserves candidate relationships. The conversational framework logs the entire debate, giving you a clear audit trail of why the candidate was archived.

Setup guide

Set up Lever 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 Lever 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="Lever_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install `autogen-ext[mcp]` and use the `mcp_server_tools` helper with your server URL. Pass the resulting tools list directly to your `AssistantAgent` constructor.

Yes. An agent can call `update_opportunity_stage` once the group chat reaches a consensus on the candidate's qualification.

The agents debate within the group chat. One agent might call `get_candidate_profile` to pull more data, presenting the findings to resolve the conflict before any state-changing tool is invoked.

Yes. You can connect using either standard stdio or streamable HTTP transports by configuring the server parameters in your initialization code.

All candidate opportunities and job postings are processed locally within a secure, ephemeral V8 sandbox. Vinkius does not store your API tokens or candidate records, ensuring complete data isolation during agent debates.

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