How to Use the Nearmap (High-Res Aerial Imagery & AI) MCP in AutoGen

Deploy specialist AutoGen agent teams that debate and decide on geospatial problems using Nearmap's live data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nearmap (High-Res Aerial Imagery & AI) MCP to AutoGen

Create your Vinkius account to connect Nearmap (High-Res Aerial Imagery & AI) 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 Nearmap (High-Res Aerial Imagery & AI) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble an Automated Triage Team

Build a team of AutoGen agents to analyze a property from multiple angles. An "Analyst" agent uses `get_true_ortho_tile` to pull the latest top-down imagery. A "GIS-Specialist" agent then runs `get_ai_detected_features` to identify all structures on the property. Then, a "RiskAssessor" agent can take that output, pull elevation data with `get_dsm_elevation_tile`, and flag potential issues like building height or proximity to vegetation. The agents pass data and findings back and forth in a conversation, building a more complete picture than any single agent could.

Debate Claims with Competing Agents

AutoGen's real power is in agent conversation. Create a "ClaimValidator" agent and a "FraudDetector" agent and have them debate a property claim. The validator uses `list_survey_dates` to pull imagery from before a reported incident, while the fraud detector pulls the most recent tile. They can argue about what they see in the data. One might use `get_oblique_tile` to look for roof damage from a different angle, while the other uses `get_survey_metadata` to question the image resolution. The final decision is a consensus born from debate, not a simple script output.

Let Agents Negotiate Resource Use

With this MCP Server, you can even have agents manage their own API budget. Create a "Budget" agent that monitors tool usage and an "Operations" agent that's trying to complete a task, like mapping an entire district. The Ops agent might propose running `check_coverage_polygon` on a huge area, but the Budget agent will push back, arguing for a more targeted approach using `check_coverage_point` on specific addresses first. They negotiate a solution that balances cost and speed, right in the agent chat.

Setup guide

Set up Nearmap (High-Res Aerial Imagery & AI) 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 Nearmap (High-Res Aerial Imagery & AI) 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="Nearmap (High-Res Aerial Imagery & AI)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Nearmap (High-Res Aerial Imagery & AI) 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="Nearmap (High-Res Aerial Imagery & AI)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Nearmap (High-Res Aerial Imagery & AI) 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 Nearmap. 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 Nearmap (High-Res Aerial Imagery & AI) 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 Nearmap (High-Res Aerial Imagery & AI) MCP in AutoGen

You assign different tools to different agents. One agent can be a specialist in fetching imagery with `get_vertical_tile`, while another specializes in analysis with `get_ai_detected_features`. They collaborate by passing the output of their tool calls to each other in a conversation.

Yes, that's a core AutoGen pattern. You can create a dedicated "ElevationSpecialist" agent whose only function is to run the `get_dsm_elevation_tile` tool. Other agents can then call on this specialist when they need elevation data.

It's best for complex problems without a single right answer, like insurance claim validation, large-scale property assessment, or construction progress monitoring. These are situations where having agents debate evidence from different tools leads to a better outcome.

The conversation acts as a form of error-checking and validation. If one agent misinterprets the data from `get_ai_detected_features`, another agent can challenge it, perhaps by pulling an oblique view with `get_oblique_tile` to get a different perspective.

The agents exchange messages containing geographic coordinates and query parameters. Each tool call through the MCP Server is a discrete, stateless request processed in a zero-trust environment on Vinkius. Your Nearmap API keys are never present in the agent conversation logs or the execution 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