How do I move a candidate to a specific stage?

Use the `update_opportunity_stage` tool with the unique opportunity ID and the target stage ID. You can find stage IDs using the `list_hiring_stages` tool.

Can I archive an application via the agent?

Yes, use the `archive_hiring_opportunity` tool. You will need to provide the opportunity ID and a valid archive reason ID.

Is it possible to see a candidate's contact information?

Absolutely. Use the `get_candidate_profile` tool with the candidate's unique ID to retrieve their full profile, including email, phone, and links.

Lever MCP Server for AutoGen 10 tools — connect in under 2 minutes

Name: Lever
Availability: InStock
Author: Vinkius

microsoft.github.io/autogen/docs/tools/mcp-tools

Built by Vinkius GDPR 10 Tools Framework

Microsoft AutoGen enables multi-agent conversations where agents negotiate, delegate, and execute tasks collaboratively. Add Lever as an MCP tool provider through Vinkius and every agent in the group can access live data and take action.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.tools.mcp import McpWorkbench

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with McpWorkbench(
        server_params={"url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"},
        transport="streamable_http",
    ) as workbench:
        tools = await workbench.list_tools()
        agent = AssistantAgent(
            name="lever_agent",
            tools=tools,
            system_message=(
                "You help users with Lever. "
                "10 tools available."
            ),
        )
        print(f"Agent ready with {len(tools)} tools")

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Lever MCP Server

Connect your Lever account to any AI agent to streamline your recruitment and talent acquisition workflows. This MCP server enables your agent to interact with job postings, manage candidate opportunities, and move applications through your hiring pipeline directly.

AutoGen enables multi-agent conversations where agents negotiate, delegate, and collaboratively use Lever tools. Connect 10 tools through Vinkius and assign role-based access. a data analyst queries while a reviewer validates, with optional human-in-the-loop approval for sensitive operations.

What you can do

Posting Oversight — List and retrieve detailed configurations for all your active job advertisements
Opportunity Management — Manage candidate applications (Opportunities), track their status, and move them through hiring stages
Candidate Insight — Access complete candidate profiles, contact details, and interaction histories
Pipeline Control — List hiring stages and automate the archiving of applications with specific reasons
Workflow Automation — Create new job postings or candidate records directly from natural language interfaces

The Lever MCP Server exposes 10 tools through the Vinkius. Connect it to AutoGen in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Lever to AutoGen via MCP

Follow these steps to integrate the Lever MCP Server with AutoGen.

Install AutoGen

Run pip install "autogen-ext[mcp]"

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Integrate into workflow

Use the agent in your AutoGen multi-agent orchestration

Explore tools

The workbench discovers 10 tools from Lever automatically

Why Use AutoGen with the Lever MCP Server

AutoGen provides unique advantages when paired with Lever through the Model Context Protocol.

Multi-agent conversations: multiple AutoGen agents discuss, delegate, and collaboratively use Lever tools to solve complex tasks

Role-based architecture lets you assign Lever tool access to specific agents. a data analyst queries while a reviewer validates

Human-in-the-loop support: agents can pause for human approval before executing sensitive Lever tool calls

Code execution sandbox: AutoGen agents can write and run code that processes Lever tool responses in an isolated environment

Lever + AutoGen Use Cases

Practical scenarios where AutoGen combined with the Lever MCP Server delivers measurable value.

Collaborative analysis: one agent queries Lever while another validates results and a third generates the final report

Automated review pipelines: a researcher agent fetches data from Lever, a critic agent evaluates quality, and a writer produces the output

Interactive planning: agents negotiate task allocation using Lever data to make informed decisions about resource distribution

Code generation with live data: an AutoGen coder agent writes scripts that process Lever responses in a sandboxed execution environment

Lever MCP Tools for AutoGen (10)

These 10 tools become available when you connect Lever to AutoGen via MCP:

archive_hiring_opportunity

Archive a candidate opportunity

create_hiring_opportunity

Requires a JSON body with opportunity details. Create a new candidate opportunity

create_job_posting

Requires a JSON body with posting details. Create a new job posting

get_candidate_profile

Get details for a specific candidate (person)

get_opportunity_details

Get details for a specific candidate opportunity

get_posting_details

Get details for a specific job posting

list_hiring_opportunities

List all candidate opportunities (applications)

list_hiring_stages

g., Screen, Interview) configured in your Lever account. List all defined hiring pipeline stages

list_job_postings

List all job postings

update_opportunity_stage

g., move to "Interview" or "Offer"). Move a candidate to a different hiring stage

Example Prompts for Lever in AutoGen

Ready-to-use prompts you can give your AutoGen agent to start working with Lever immediately.

"List all my current job postings in Lever."

"Move opportunity ID 'opp-123' to the 'Interview' stage (ID: 'stage-abc')."

"Get the full profile for candidate ID 'cand-987'."

Troubleshooting Lever MCP Server with AutoGen

Common issues when connecting Lever to AutoGen through the Vinkius, and how to resolve them.

McpWorkbench not found

Install: pip install "autogen-ext[mcp]"

Lever + AutoGen FAQ

Common questions about integrating Lever MCP Server with AutoGen.

How does AutoGen connect to MCP servers?

Create an MCP tool adapter and assign it to one or more agents in the group chat. AutoGen agents can then call Lever tools during their conversation turns.

Can different agents have different MCP tool access?

Yes. AutoGen's role-based architecture lets you assign specific MCP tools to specific agents, so a querying agent has different capabilities than a reviewing agent.