How to Use the Adzuna MCP in LangChain

Q: How do I load Adzuna tools into LangChain?

Install langchain-mcp-adapters and use MultiServerMCPClient. Call client.gettools() to expose the Adzuna endpoints to your ReAct agent.

Q: Can my LangChain agent analyze historical Adzuna salary trends?

Yes. The agent calls getsalaryhistory and uses its reasoning loop to interpret the returned timeline. It handles the API response natively without extra parsing logic.

Q: How do I maintain state across multiple job searches?

LangChain is stateless by default. You need to use client.session() if you want the agent to remember previous company queries during a long session.

Build multi-step job market analysis chains by connecting the Adzuna MCP Server directly into your LangChain agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Adzuna MCP to LangChain

Create your Vinkius account to connect Adzuna 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 Adzuna with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

LangChain agents driving job search

Connect `search_jobs` to your ReAct agents and watch them parse global employment markets autonomously. You feed the agent a 2-letter country code and a target role. It hits the Adzuna MCP Server, pulls live vacancy data, and decides what to do next based on the returned job descriptions. Here's the thing. The real power comes from chaining these results. Your agent can take the output from that initial search, pass the role into `get_salary_history`, and build a detailed timeline of compensation trends before returning a final parsed report.

Tracing market data pipelines

Every request to the MCP Server's `list_top_companies` endpoint gets tracked natively in LangSmith. You see exactly which job categories your agent queried and how many tokens it spent processing the employer list. This observability matters when you build complex hiring workflows. If an agent loops too many times trying to find niche tech roles, you catch the latency spike immediately and adjust your prompt logic.

Connecting compensation context

Combine external database tools with `get_salary_histogram` to map internal payroll against live market distributions. Your chain reads a local employee record, extracts their title, and fetches the current market average. Because LangChain handles the intermediate state, you don't write glue code. The agent routes the histogram data straight into a formatting prompt, giving you an instant comparison of your team's pay versus the wider industry.

Setup guide

Set up Adzuna 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 Adzuna 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({
    "adzuna-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 Adzuna 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 Adzuna. 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 Adzuna 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 Adzuna MCP in LangChain

Install `langchain-mcp-adapters` and use `MultiServerMCPClient`. Call `client.get_tools()` to expose the Adzuna endpoints to your ReAct agent.

Yes. The agent calls `get_salary_history` and uses its reasoning loop to interpret the returned timeline. It handles the API response natively without extra parsing logic.

LangSmith captures every tool invocation. You get full visibility into execution time and payload size for every job search request your agent makes.

LangChain is stateless by default. You need to use `client.session()` if you want the agent to remember previous company queries during a long session.

Vinkius runs the server in a V8 Isolate Sandbox. Your specific job titles, country codes, and salary search parameters exist only for the duration of the request and are immediately destroyed.

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