How to Use the Lever MCP in LangChain

Q: How do I connect the Lever MCP Server to LangChain?

Install langchain-mcp-adapters and langgraph via pip. Initialize MultiServerMCPClient with the Lever endpoint URL, then pass the tools from client.gettools() into your agent constructor.

Q: Can a LangChain agent use Lever tools to move candidates to different stages?

Yes, the agent calls updateopportunitystage inside a ReAct loop. It checks the stage names via listhiringstages first to make sure it uses a valid target stage.

Q: How does LangSmith trace Lever tool calls in LangChain?

LangSmith logs every input and output for tools like getpostingdetails. You see the exact JSON payload sent to the API and the response returned, making it easy to debug failed transitions.

Chain Lever hiring tools directly into your LangChain LLM pipelines to automate candidate progression without manual overhead.

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 LangChain

Create your Vinkius account to connect Lever to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

LangChain candidate progression loops

This MCP Server uses `update_opportunity_stage` and `get_opportunity_details` to let your LangChain agent transition candidates through your hiring funnel. You can build a sequential chain where the output of a candidate screening assessment feeds directly into the next step of the pipeline. The agent checks the current status, evaluates the score, and moves the candidate forward. By feeding these tools into a LangGraph state machine, you eliminate manual triage. LangSmith traces every single state change, showing you exactly why a candidate moved from screen to interview.

Dynamic job posting creation

The `create_job_posting` tool allows your LangChain chain to generate and publish new roles based on department requests. Your agent reads a raw request from a document, structures it, and writes it directly to Lever. You bypass copy-pasting descriptions across platforms. Because LangChain handles structured output, the agent maps the generated text to the precise schema required by `create_job_posting`. This guarantees that every posting has the correct department, location, and grading before it goes live.

Deep candidate profiling for chains

Running `get_candidate_profile` alongside `list_hiring_opportunities` gives your LangChain agent immediate access to candidate history. The agent pulls the complete record, including past applications and interviewer notes, during active runs. This lets the chain build a complete background profile before draft replies or interview prep sheets are created. You can combine these tools with external vector databases in the same LangChain execution. This allows your agent to compare the active candidate profile against historic hiring trends stored in your local system.

Setup guide

Set up Lever MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Lever tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "lever-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Lever transactions"
    })
    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 LangChain

Install `langchain-mcp-adapters` and `langgraph` via pip. Initialize `MultiServerMCPClient` with the Lever endpoint URL, then pass the tools from `client.get_tools()` into your agent constructor.

Yes, the agent calls `update_opportunity_stage` inside a ReAct loop. It checks the stage names via `list_hiring_stages` first to make sure it uses a valid target stage.

LangSmith logs every input and output for tools like `get_posting_details`. You see the exact JSON payload sent to the API and the response returned, making it easy to debug failed transitions.

Yes. You can aggregate the Lever server with database or calendar tools using the multi-server client, allowing your agent to coordinate across different platforms in one run.

The server processes candidate profiles and opportunities in an ephemeral V8 sandbox. Your credentials and candidate data are never stored or logged on Vinkius servers, maintaining strict compliance with your hiring privacy policies.

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