How to Use the Mapulus MCP in Pydantic AI

Inject type-safe Australian boundary and demographic data into your Pydantic AI agents with absolute validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mapulus MCP to Pydantic AI

Create your Vinkius account to connect Mapulus 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 Mapulus with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict type validation for Pydantic AI spatial lookups

The `get_postcode_data` tool returns highly structured geographic data that Pydantic AI validates against strict schemas at runtime. This prevents your agent from parsing malformed postcode responses or executing logic on corrupted data. If the underlying Mapulus MCP Server API structure shifts, your agent fails loudly and immediately with a validation error. This design ensures that your application never silently processes hallucinated spatial fields or incorrect coordinates.

Type-safe isochrone and routing analysis

The `get_isochrone` tool generates travel-time boundaries that are instantly parsed into validated Python models by your agent. This ensures that the travel contours and coordinates conform exactly to your application's expected types. You can run this toolset across any LLM provider supported by Pydantic AI, including OpenAI, Anthropic, and local models. The framework handles the SSE or HTTP transport layer cleanly, keeping your type-safe spatial logic decoupled from the model provider.

Structured suburb and demographic lookups

The `search_suburbs` tool allows your agent to find Australian suburbs and map them directly to strongly typed Pydantic models. You can combine this with `get_demographics` to build a reliable pipeline for regional analysis. By instantiating `MCPToolset` with your Vinkius endpoint, your Pydantic AI agent gains immediate, secure access to the entire suite of spatial tools. This MCP setup eliminates manual schema writing and keeps your type definitions perfectly in sync with the live API.

Setup guide

Set up Mapulus 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": {
        "mapulus-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Mapulus 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 Mapulus. 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 Mapulus 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 Mapulus MCP in Pydantic AI

Install the MCP extension and instantiate MCPToolset with your Vinkius HTTP or SSE endpoint URL. Pass this toolset directly into your Agent constructor to give your model immediate access to tools like search_suburbs.

The framework will trigger a runtime validation error immediately instead of letting your agent proceed with bad data. This is crucial when calling tools like get_demographics where data integrity is essential for business logic.

Yes, Pydantic AI is completely model-agnostic, meaning you can run your spatial queries using Anthropic, Gemini, or local models. The tool schemas for get_isochrone are translated automatically to fit whatever model you choose.

Yes, you can connect to the server using either Streamable HTTP or Server-Sent Events (SSE) transports. This allows your python agent to maintain a stable connection to the remote spatial tools hosted on Vinkius.

Every transaction involving Australian statistical boundaries is executed within an isolated, zero-trust V8 sandbox on Vinkius. This MCP architecture guarantees that your location queries are ephemeral and never logged or exposed to third parties.

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