How to Use the Radar MCP in AutoGen

Q: How do AutoGen agents negotiate routes using Radar tools?

One agent calls calculateroutingmatrix to gather travel times, while another agent evaluates constraints like driver shifts. They pass the coordinate outputs back and forth in a conversation loop until they agree on the optimal path.

Q: Can I use Radar to geolocate users inside an AutoGen group chat?

Yes, a triage agent can run ipgeocode on an incoming request to identify the user's region. The agent then shares this location data with other specialized agents in the group to ground the rest of the conversation.

Q: How do I register the Radar MCP Server tools with my AutoGen agents?

Use mcpservertools from autogen-extmcp to fetch the tools from the server's HTTP endpoint. Pass the resulting tool list directly to your AssistantAgent constructor, and the adapter will handle the schema mapping.

Q: How do AutoGen agents handle location search errors from Radar?

If searchplaces returns no results, the executing agent flags the empty response in the chat. The supervising agent can then instruct a geocoding agent to try reversegeocode on the coordinates to find alternative landmarks.

Let AutoGen agents debate routing options and validate physical addresses using live Radar spatial tools.

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 AutoGen

Create your Vinkius account to connect Radar to AutoGen — 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Resolve routing conflicts through AutoGen agent debates

When your logistics agents argue over the best delivery paths, give them the tools to settle it. This MCP Server allows one AutoGen agent to pull routing data using `calculate_routing_matrix` while a budget agent analyzes the cost of the trip. The agents debate the trade-offs between travel duration and total distance in a collaborative conversation. They use `calculate_route_distance` to verify specific segments, arriving at a consensus-driven delivery plan without human intervention.

Validate and parse addresses via AutoGen conversations

Messy address inputs can stall an automated workflow. In an AutoGen group chat, a validation agent can ingest raw text and run `validate_address` to clean up the postal formatting, while a verification agent cross-checks the result. The verification agent uses `forward_geocode` to ensure the address maps to real coordinates, and `reverse_geocode` to confirm the street details match. The conversation only proceeds once both agents agree the location is legitimate.

Coordinate geofence analysis with specialized AutoGen agents

Manage complex spatial monitoring tasks using dedicated agents. A tracking agent uses `search_geofences` to monitor coordinate boundaries via the MCP Server, while a context agent calls `get_location_context` to analyze local environment parameters. Together, they determine if a target has crossed a boundary and evaluate what local conditions might affect the journey. You get a coordinated response where each agent handles one specific piece of the spatial puzzle.

Setup guide

Set up Radar 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 Radar 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="Radar_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Radar 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="Radar_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Radar 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 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 AutoGen

One agent calls `calculate_routing_matrix` to gather travel times, while another agent evaluates constraints like driver shifts. They pass the coordinate outputs back and forth in a conversation loop until they agree on the optimal path.

Yes, a triage agent can run `ip_geocode` on an incoming request to identify the user's region. The agent then shares this location data with other specialized agents in the group to ground the rest of the conversation.

Use `mcp_server_tools` from `autogen-ext[mcp]` to fetch the tools from the server's HTTP endpoint. Pass the resulting tool list directly to your `AssistantAgent` constructor, and the adapter will handle the schema mapping.

If `search_places` returns no results, the executing agent flags the empty response in the chat. The supervising agent can then instruct a geocoding agent to try `reverse_geocode` on the coordinates to find alternative landmarks.

Every address string and IP address processed by tools like `validate_address` or `ip_geocode` runs in a highly secure, isolated V8 sandbox. No persistent logs of your users' location data are kept, keeping your spatial intelligence secure.

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