How to Use the Adzuna MCP in AutoGen

Q: How do I configure Adzuna MCP tools for my AutoGen agents?

Install autogen-extmcp and use mcpservertools with your transport parameters. Pass the resulting tool list directly into your AssistantAgent constructor.

Q: Does AutoGen convert the Adzuna MCP schema automatically?

McpToolAdapter handles all the translation behind the scenes. Your agents see native function definitions for the histogram and company listing tools without manual mapping.

Let your AutoGen agents debate hiring strategies and salary negotiations using live market data from the Adzuna MCP API.

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 AutoGen

Create your Vinkius account to connect Adzuna to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent MCP Server research

Give your AutoGen agents the ability to argue over real-world hiring data. You assign `search_jobs` to a dedicated research agent that pulls raw vacancy listings from specific countries. A separate analysis agent reviews those listings and challenges the findings. They debate the quality of the roles found, refine the search keywords, and hit the endpoint again until they reach a consensus on the best available positions.

Negotiating compensation trends

Complex salary decisions require competing perspectives. Expose the MCP Server's `get_salary_history` and `get_salary_histogram` tools to a financial agent while an HR agent advocates for the candidate. The financial agent pulls historical trends to argue for a lower offer, while the HR agent uses the current histogram distribution to prove the market rate has shifted. They deliberate using hard numbers until they agree on a data-backed salary band.

Mapping competitor activity

When entering a new market, you need to know who else is hiring. An agent calls `list_top_companies` to identify the dominant employers for a specific job category. A strategy agent takes that list and flags potential talent wars. The conversation continues autonomously as the agents weigh the risks of competing against these top companies, resulting in a synthesized report on market saturation.

Setup guide

Set up Adzuna MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Adzuna tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Adzuna_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Adzuna data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Adzuna_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Adzuna data")
    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 AutoGen

Install `autogen-ext[mcp]` and use `mcp_server_tools` with your transport parameters. Pass the resulting tool list directly into your `AssistantAgent` constructor.

Yes. You can equip different agents with specific endpoints. One might handle salary histories while another focuses strictly on active job searches.

`McpToolAdapter` handles all the translation behind the scenes. Your agents see native function definitions for the histogram and company listing tools without manual mapping.

If an agent tries to search without a valid 2-letter code, the server returns an error. The agents read that error, discuss the missing parameter, and retry the call with the correct format.

The server operates in a strict V8 Isolate Sandbox. The specific roles, company names, and salary numbers your agents debate never touch persistent storage and vanish the moment the session ends.

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