How to Use the HrFlow.ai MCP in LangChain

Q: How do I use HrFlow.ai tools in a LangChain agent?

Get the tools with client.gettools() and pass them to your agent constructor, like createagent. LangChain handles routing the user's request to the correct HrFlow.ai tool.

Q: Can I combine HrFlow.ai with other tools in one LangChain agent?

Absolutely. Your agent can use searchprofiles to find a candidate, then use a different tool to send them an email. The MCP tools just become part of your agent's toolkit.

Build autonomous recruiting agents with LangChain that find, score, and analyze candidates on their own.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HrFlow.ai MCP to LangChain

Create your Vinkius account to connect HrFlow.ai 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 HrFlow.ai with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Self-Correcting Sourcing Chains

Stop manually searching. Build a LangChain agent that takes a job description, uses `search_jobs` to find similar roles for context, then runs `search_profiles` to find matching candidates. The agent decides the next step. No hardcoded logic. If the initial search is weak, the agent can pivot. It might use `unfold_profile` on a near-miss candidate to find new keywords, then rerun `search_profiles` with a better query. You just watch it work in LangSmith.

Dynamic Profile Analysis for LangChain

Your agent can create a dynamic scoring pipeline. First, it pulls a job with `list_jobs` and a list of candidates with `list_profiles`. Then, it feeds them to `score_profiles` to get a baseline ranking. It doesn't stop there. For the top three candidates, the agent can automatically call `ask_profile` with specific questions like, "Does this person have experience with distributed systems?" The final output isn't just a score; it's a score with a reasoned explanation.

Ingest Resumes from Anywhere

Raw resume files are a mess. Use a LangChain agent to watch a folder or email inbox, grab new resumes, and immediately send them to the `parse_profile` tool. You get back clean, structured JSON every time. This becomes the first step in a longer chain. Once parsed, the agent can push the structured data to your ATS, score it with `score_profiles`, and notify a recruiter. It's a full workflow powered by this MCP Server, not just a single API call.

Setup guide

Set up HrFlow.ai 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 HrFlow.ai 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({
    "hrflowai-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 HrFlow.ai 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 HrFlow.ai. 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 HrFlow.ai 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 HrFlow.ai MCP in LangChain

Get the tools with `client.get_tools()` and pass them to your agent constructor, like `create_agent`. LangChain handles routing the user's request to the correct HrFlow.ai tool.

Yes, that's the point. Based on your prompt, the ReAct agent framework in LangChain chooses the best tool—`search_profiles` for discovery, `score_profiles` for ranking against a specific job.

Connect it to LangSmith. You'll see every tool call made through the MCP connection, its inputs, outputs, and latency. It's the only way to really see what your agent is thinking.

Absolutely. Your agent can use `search_profiles` to find a candidate, then use a different tool to send them an email. The MCP tools just become part of your agent's toolkit.

The MCP server itself is stateless; it processes data and returns it. When using LangChain, candidate profile data exists in-memory for the life of the agent's run. For privacy, don't log the raw profile data, and rely on LangSmith's tracing which separates logic from sensitive PII.

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