How to Use the Radar MCP in OpenAI Agents SDK

Q: How do I connect the Radar MCP Server to my OpenAI Agents SDK?

Install openai-agents, then instantiate MCPServerStreamableHttp using the Vinkius endpoint URL. Pass this instance inside the mcpservers list when constructing your agent to expose all ten location endpoints instantly.

Q: Can my OpenAI Agents SDK agent calculate routes using Radar?

Yes, your agent calls calculateroutedistance to get precise travel times and distances between two points. It handles the raw coordinate inputs and processes the return payload to update your dispatch schedules.

Q: Does the Radar MCP Server support address autocompletion in OpenAI Agents SDK?

Yes, the autocomplete tool provides real-time address suggestions as your agent processes partial search strings. This prevents your OpenAI Agents SDK client from hallucinating coordinates or sending drivers to non-existent locations.

Q: How does this server handle reverse geocoding?

The reversegeocode tool converts latitude and longitude coordinates into structured, human-readable street addresses. Your agent invokes this tool to translate raw GPS telemetry data into recognizable drop-off locations.

Q: How does the Radar MCP Server protect my users' IP addresses and coordinates?

All IP addresses sent to ipgeocode and coordinates sent to reversegeocode run inside an isolated, zero-trust V8 sandbox. Vinkius handles the authorization token, meaning your database never exposes raw API keys to the agent client.

Give your OpenAI Agents SDK production bots direct access to coordinate lookups, routing matrices, and geofence checks.

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 OpenAI Agents SDK

Create your Vinkius account to connect Radar to OpenAI Agents SDK — 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Secure Address Cleanup with OpenAI Agents SDK

`validate_address` cleans up messy user inputs before your OpenAI Agents SDK agent triggers downstream actions. It spits back structured, verified location data, preventing invalid addresses from poisoning your production database or breaking your delivery pipelines. You get built-in guardrails through this MCP Server setup. The agent auto-discovers the tool, validates the schema, and lets you trace the entire address verification lifecycle right inside your OpenAI developer dashboard.

Multi-Point Routing Matrices for Your Agents

`calculate_routing_matrix` calculates travel times and distances across multiple origins and destinations simultaneously. Your agent handles complex logistics dispatching by calling this single endpoint instead of making dozens of slow, sequential API calls. This MCP Server integration exposes raw distance and duration matrices to your autonomous planner. OpenAI Agents SDK handles the tool execution tracing, so you can monitor latency and cost for every route calculated by your agent.

Geofence Queries for Production Agents

`search_geofences` queries your active spatial boundaries to determine if coordinates fall within specific physical territories. Your agent uses this spatial awareness to trigger location-specific notifications or restrict operations to permitted delivery zones. By integrating this MCP Server, your OpenAI Agents SDK setup gains instant spatial context. The agent queries nearby boundaries and maps coordinates to internal territory IDs without requiring custom GIS libraries in your codebase.

Setup guide

Set up Radar MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Radar tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Radar tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Radar tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Radar Agent",
            instructions="You have access to Radar tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents`, then instantiate `MCPServerStreamableHttp` using the Vinkius endpoint URL. Pass this instance inside the `mcp_servers` list when constructing your agent to expose all ten location endpoints instantly.

Yes, your agent calls `calculate_route_distance` to get precise travel times and distances between two points. It handles the raw coordinate inputs and processes the return payload to update your dispatch schedules.

Yes, the `autocomplete` tool provides real-time address suggestions as your agent processes partial search strings. This prevents your OpenAI Agents SDK client from hallucinating coordinates or sending drivers to non-existent locations.

The `reverse_geocode` tool converts latitude and longitude coordinates into structured, human-readable street addresses. Your agent invokes this tool to translate raw GPS telemetry data into recognizable drop-off locations.

All IP addresses sent to `ip_geocode` and coordinates sent to `reverse_geocode` run inside an isolated, zero-trust V8 sandbox. Vinkius handles the authorization token, meaning your database never exposes raw API keys to the agent client.

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