How to Use the Moka HR MCP in LangChain

Q: How do I hook up Moka HR to my LangChain agents?

You install the langchain-mcp-adapters package and initialize the MCP client with the server URL. From there, you call client.gettools() and pass them directly to your agent executor.

Q: Can I trace Moka HR tool usage inside LangChain?

Yes, every tool call like gethiringsummary is traced automatically if you have LangSmith enabled. You can see the exact input parameters, latency, and returned candidate data in your LangSmith dashboard.

Run multi-step recruitment pipelines in LangChain by connecting your agents directly to Moka HR candidate and job data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Moka HR MCP to LangChain

Create your Vinkius account to connect Moka HR 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 Moka HR with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pipeline Candidate Screening with LangChain

The `list_candidates` tool lets you fetch new applicants and run them through custom LangChain evaluation steps automatically. Your agents can pull raw resumes, pass them to evaluation chains, and write the output back using `create_candidate` to keep your system updated. This setup lets you build a full workflow where the output of one step feeds the next. You get complete tracing in LangSmith, showing you exactly how your agent decided to categorize a candidate before moving them to the next stage.

Build Automated Interview Prep Chains

You can use `get_interview` to pull upcoming schedule details and instantly generate custom prep sheets for your hiring managers. The agent reads the interview slot, grabs the candidate's profile with `get_candidate`, and compiles a brief of their skills. By chaining these tools together, your team gets a Slack notification with a full prep document before the meeting starts. Manual copying between your calendar and your ATS is officially dead.

Run Custom Hiring Audits via MCP Server Tools

The `list_jobs` tool gives your LangChain agent a clean list of active roles to cross-reference against your current applicant volume. You can query `list_applications` to see if any high-priority roles are stalling or if candidates are getting stuck in the pipeline. By combining these endpoints with a LangChain database connector, you can write agents that flag bottlenecks. They run on a cron job, check the status of active roles, and alert your recruiting lead when a job needs attention.

Setup guide

Set up Moka HR 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 Moka HR 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({
    "moka-hr-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 Moka HR 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 Moka HR. 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 Moka HR 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 Moka HR MCP in LangChain

You install the `langchain-mcp-adapters` package and initialize the MCP client with the server URL. From there, you call `client.get_tools()` and pass them directly to your agent executor.

Yes, every tool call like `get_hiring_summary` is traced automatically if you have LangSmith enabled. You can see the exact input parameters, latency, and returned candidate data in your LangSmith dashboard.

LangChain relies on your custom runnables or agent loops to handle retries when hitting rate limits. If `list_candidates` returns a rate limit error, you should configure your chain with a retry policy to back off and try again.

Yes, you can share the MCP client instance across multiple agents or chains. Since the MCP server is stateless, each agent can call tools like `get_job` independently without interfering with other runs.

All candidate profiles, resumes, and interview feedback fetched by `get_candidate` stay within your private environment. Vinkius runs the server in an isolated sandbox, meaning your recruitment data is never stored or used to train public models.

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