How to Use the Mapulus MCP in AutoGen

Q: How do AutoGen agents access Mapulus tools via an MCP Server?

You load the tools using the mcpservertools helper. Pass this tool list directly to your AutoGen AssistantAgent constructor to give it full access to the Australian spatial endpoints.

Build AutoGen agent networks that debate and analyze Australian location intelligence.

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 AutoGen

Create your Vinkius account to connect Mapulus to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let AutoGen agents debate Mapulus demographics

In AutoGen, your agents don't just run tools in isolation. You can set up a demographic analyst agent that calls `get_demographics` and a finance agent that challenges those numbers based on local trends. They talk to each other to find the best suburb for a new retail store. This conversational approach prevents single-agent bias when analyzing Australian regional data. The agents use the structured output from this MCP Server to back up their arguments with actual census statistics.

Coordinate spatial lookups with AutoGen networks

You can build an agent that specializes in geography and queries `search_boundaries` to find statistical zones. It then hands these boundaries over to a logistics agent to calculate optimal delivery routes. Because AutoGen automatically translates the schemas of this MCP Server, your agents can coordinate complex tasks without you writing manual routing code. They use tools like `get_postcode_data` to resolve boundary disputes during their conversation.

Solve complex travel-time problems in AutoGen

When planning transit networks, one agent can generate drive-time zones using `get_isochrone` while a second agent evaluates the population density inside those zones. They negotiate the best location for a new hub. This cooperative problem-solving uses tools like `enrich_location` to feed real-time geographic context into the agent debate. The result is a highly reasoned decision grounded in actual spatial measurements.

Setup guide

Set up Mapulus 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 Mapulus 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="Mapulus_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You load the tools using the `mcp_server_tools` helper. Pass this tool list directly to your AutoGen `AssistantAgent` constructor to give it full access to the Australian spatial endpoints.

Yes, multiple agents in your group chat can share access to the same tools. A research agent can call `search_suburbs` while a planning agent uses those results to run demographic queries.

The MCP adapter converts server errors into natural text responses. If `get_boundary_details` fails due to an invalid ID, the executing agent receives the error directly and can debate a correction with its peers.

AutoGen allows a performance agent to challenge travel-time estimates from `get_isochrone`. The agents can run multiple scenarios with different parameters to find the most reliable route.

All Australian boundary coordinates and suburb lookups are processed through an ephemeral, zero-trust V8 isolate sandbox. Your conversational agent logs remain on your local machine, and no geographic data is saved or stored on our servers.

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