How to Use the Join MCP in LangChain

Q: How do I connect the Join MCP Server to my LangChain agent?

Install langchain-mcp-adapters and langgraph via pip. Initialize the MultiServerMCPClient with the Vinkius transport URL, retrieve the tools using client.gettools(), and pass them directly to your agent constructor.

Q: Does this LangChain MCP integration support running multiple Join tools in a single session?

You can run multiple tools sequentially by using client.session() to maintain context across your chain. This allows the agent to fetch a list of jobs with listjobs and then immediately inspect a single job using getjob without losing track of the initial query.

Feed Join candidate profiles and job data directly into your LangChain chains to automate hiring pipelines without manual tracking.

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 LangChain

Create your Vinkius account to connect Join 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 Join with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Join MCP Server tools for multi-step hiring actions

Your LangChain agents need to do more than just read raw text. By connecting this MCP Server, your agent can first execute `list_applications` to find new applicants, then pass those specific application IDs straight into `get_application` to pull screening answers. It turns separate API calls into a single, logical sequence that runs itself. You don't have to write glue code to pass data between these steps. The framework handles the output of one tool as the direct input for the next, letting your agent evaluate candidate qualifications against the requirements returned by `get_job` in real-time.

Trace candidate screening pipelines with LangSmith

Debugging hiring agents gets messy when you don't know why a candidate was flagged or skipped. When your agent calls `get_candidate` inside a chain, LangSmith traces the exact inputs, latency, and token usage of that specific tool execution. You see exactly what candidate data the model evaluated. This visibility prevents silent failures when pulling application statuses. If `list_candidates` returns an unexpected payload, you can pinpoint the exact step in the chain where the data diverged, ensuring your recruiting pipeline remains reliable.

Combine recruiting data with external databases

Don't let your candidate data live in a silo. LangChain lets you combine this server's tools with over 500 external integrations, meaning your agent can pull a hiring manager's email using `list_users` and immediately cross-reference it with your internal calendar database. You can build complex reasoning loops that query `list_departments` to find open roles, pull the matching job descriptions with `get_job`, and then draft personalized outreach messages. It connects your hiring tools directly to the rest of your tech stack.

Setup guide

Set up Join 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 Join 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({
    "join-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 Join 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 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 LangChain

Install `langchain-mcp-adapters` and `langgraph` via pip. Initialize the `MultiServerMCPClient` with the Vinkius transport URL, retrieve the tools using `client.get_tools()`, and pass them directly to your agent constructor.

Yes, the ReAct agent loop lets the model analyze the conversation context and choose to call `get_candidate` only when it needs specific details about an applicant. This prevents unnecessary API calls and keeps token usage low.

You can run multiple tools sequentially by using `client.session()` to maintain context across your chain. This allows the agent to fetch a list of jobs with `list_jobs` and then immediately inspect a single job using `get_job` without losing track of the initial query.

The framework catches tool execution errors and passes the error message back to the LLM as an observation. Your agent can then read the error, realize the application ID was wrong, and try again with a different ID from `list_candidates`.

Your candidate profiles, contact info, and application answers are protected because Vinkius runs this tool in an ephemeral, zero-trust sandbox. No recruiting data is stored on our servers, and all API communication uses your single secure endpoint token.

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