How to Use the Radar MCP in Pydantic AI

Q: How do I register the Radar MCP Server with Pydantic AI?

Install pydantic-ai-slimmcp and initialize MCPToolset with the Vinkius server HTTP endpoint. Pass the toolset into your Agent constructor to instantly register all ten location tools.

Q: How does Pydantic AI handle invalid address errors from Radar?

If validateaddress returns unexpected fields, Pydantic AI catches the schema mismatch at runtime. Your agent raises a validation error, preventing corrupt address data from executing downstream tasks.

Q: Can my Pydantic AI agent perform IP lookups using Radar?

Yes, the ipgeocode tool resolves IP addresses to geographic coordinates. Your Pydantic AI agent parses the strongly-typed country and city fields to enforce region-based access controls.

Q: Does this server support coordinate conversions?

Yes, the forwardgeocode and reversegeocode tools handle conversions between physical addresses and coordinates. The returned coordinates are strictly typed as floats, preventing parsing errors.

Run type-safe address validation and routing inside your Pydantic AI agents with strict runtime schema enforcement.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Radar MCP to Pydantic AI

Create your Vinkius account to connect Radar to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Radar with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Strict Address Validation in Pydantic AI

`validate_address` cleans up messy, unstructured addresses and forces the output to match your runtime Pydantic schemas. If the API returns unexpected location fields, your Pydantic AI agent fails loudly instead of letting silent data corruption slide into your system. This MCP Server integration eliminates the risk of hallucinated street addresses or malformed postal codes. Your agent validates the location schema at runtime, guaranteeing that only clean, structured addresses enter your database.

Type-Safe Distance Calculations via MCP Server

`calculate_route_distance` computes travel duration and physical distance between coordinates with strict type safety. Your Pydantic AI agent consumes the validated integer and float responses, preventing type errors during routing math. Integrating this MCP Server gives your agent a reliable way to calculate delivery times. The return payload matches the expected Pydantic model precisely, allowing your agent to safely update delivery schedules.

Place Search with Runtime Type Validation

`search_places` queries points of interest near a specific coordinate and returns structured place data. Your Pydantic AI agent parses the validated search results to find nearby businesses, landmarks, or fueling stations. Check the return: every point of interest comes back with typed latitude and longitude fields. This ensures your agent can pass the location coordinates straight to downstream routing tools without manual parsing.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]` and initialize `MCPToolset` with the Vinkius server HTTP endpoint. Pass the toolset into your `Agent` constructor to instantly register all ten location tools.

If `validate_address` returns unexpected fields, Pydantic AI catches the schema mismatch at runtime. Your agent raises a validation error, preventing corrupt address data from executing downstream tasks.

Yes, the `ip_geocode` tool resolves IP addresses to geographic coordinates. Your Pydantic AI agent parses the strongly-typed country and city fields to enforce region-based access controls.

Yes, the `forward_geocode` and `reverse_geocode` tools handle conversions between physical addresses and coordinates. The returned coordinates are strictly typed as floats, preventing parsing errors.

All latitude and longitude coordinate pairs are processed within Vinkius's ephemeral V8 sandbox. Your location queries are never logged, and API credentials remain securely hidden from the agent runtime.

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