How to Use the Adzuna MCP in Pydantic AI

Q: How does Pydantic AI handle schema mismatches from Adzuna?

The framework validates the JSON payload from getsalaryhistory against the MCP Server runtime schema. If a field fails validation, Pydantic AI raises a validation error immediately rather than passing corrupt data to your model.

Q: Can I use Pydantic AI to validate the country code parameter for Adzuna?

Yes, you can define a strict Pydantic model for the searchjobs inputs. The agent will validate that the country code is exactly two characters long before executing the tool call.

Build type-safe job market agents with Pydantic AI to validate every salary and vacancy payload at runtime.

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 Pydantic AI

Create your Vinkius account to connect Adzuna to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Salary Trends with Pydantic AI

The `get_salary_history` tool delivers historical compensation trends that Pydantic AI validates against your exact Python type models instantly. If the API returns unexpected null values or missing fields, the framework catches the error at runtime before your application ingests the bad data. This strict validation guarantees that your downstream analysis code never processes corrupted salary metrics. By connecting this MCP Server to your type-safe agent, you ensure that trend calculations are always based on clean, structured numbers.

Enforce Strict Job Search Parameters

Your agent invokes `search_jobs` while Pydantic AI guarantees the required two-letter country code matches ISO standards before sending the request. This pre-flight validation prevents unnecessary API failures by blocking malformed queries at the client level. Once the query executes, the returned job listings are parsed into strongly-typed objects. Your system can safely extract descriptions, postal codes, and company names knowing that every string matches your structural definitions.

Parse Salary Histograms Safely

When your agent calls `get_salary_histogram`, Pydantic AI parses the distribution data into a strict numerical schema. This prevents silent failures where missing brackets or corrupt integers could crash your graphing components. Using this MCP Server toolset, you build highly resilient data pipelines that work with any LLM. The framework handles the JSON schema translation, ensuring your agent receives predictable, structured outputs every time.

Setup guide

Set up Adzuna MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "adzuna-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Adzuna tools.",
)

result = await agent.run("List recent Adzuna transactions")
print(result.output)

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 Pydantic AI

The framework validates the JSON payload from `get_salary_history` against the MCP Server runtime schema. If a field fails validation, Pydantic AI raises a validation error immediately rather than passing corrupt data to your model.

Yes, you can define a strict Pydantic model for the `search_jobs` inputs. The agent will validate that the country code is exactly two characters long before executing the tool call.

You initialize the unified toolset class with your Vinkius HTTP endpoint. The framework manages the underlying SSE or HTTP transport, exposing the four job market tools to your agent automatically.

No, Vinkius hosts and manages the server on cloud infrastructure. Your code connects to a single hosted endpoint, removing the need to manage local Node or Python runtimes.

All data validation happens in your local runtime, and transmissions to the hosted endpoint use end-to-end TLS encryption. Your search keywords and salary parameters are processed in isolated, single-tenant memory spaces that are wiped immediately after the API call completes.

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