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

Q: How do I handle areas without coverage when building a chain with Nearmap (High-Res Aerial Imagery & AI) and LangChain?

Your agent should always start with checkcoveragepoint or checkcoveragepolygon. Your chain's logic can then route to a different path or end gracefully if the tool returns 'false', preventing wasted calls to imagery tools.

Build autonomous geospatial agents with LangChain that chain together high-res imagery and AI feature extraction.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Coverage Checks to Imagery Pulls

Stop writing brittle, step-by-step scripts. Build a LangChain agent that decides its own path. It can start with `check_coverage_polygon` to confirm a property is in Nearmap's flight path. If it gets a 'true', the agent can then automatically call `list_survey_dates` to find the most recent flyover. This isn't a simple if/then. The output from one tool becomes the direct input for the next. The agent takes the latest date and feeds it into `get_true_ortho_tile` or `get_oblique_tile` to pull the exact image it needs. It's a smart, sequential workflow, not a dumb list of commands.

Automate Property Analysis with a LangChain Agent

Give your agent the full suite of Nearmap tools and a goal, then watch it work. It can start by fetching a tile with `get_vertical_tile` and then decide to run `get_ai_detected_features` on that same tile to find buildings, pools, or solar panels. It doesn't stop there. The agent can then use `get_dsm_elevation_tile` to get height data for those same features, building a complete property profile on its own. With LangSmith, you get a full trace of the agent's reasoning, seeing every tool call and result in one place.

Create Complex Geospatial Workflows

LangChain lets you build more than just simple data-fetching chains. You can design an agent that compares property states over time. It starts by using `list_survey_dates` to find imagery from before and after a specific event, like a hailstorm. Then, your agent can pull tiles from both dates using `get_vertical_tile` and run `get_ai_detected_features` on each to spot changes. This is how you automate damage assessment at scale. The agent connects the dots, from date discovery to visual analysis, all within a single chain of thought.

Setup guide

Set up Nearmap (High-Res Aerial Imagery & AI) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Nearmap (High-Res Aerial Imagery & AI) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "nearmap-high-res-aerial-imagery-ai-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Nearmap (High-Res Aerial Imagery & AI) transactions"
    })
    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 LangChain

LangChain creates agents that can call tools in a sequence based on a goal. For example, an agent can call `check_coverage_point` first, and only if the result is positive, it will then call `get_vertical_tile` to fetch the imagery.

Yes. You can equip an agent with both the Nearmap MCP Server tools and tools for your own databases or other APIs. The agent can then pull property data from Nearmap and enrich it with your internal records in the same chain.

A LangChain agent is dynamic; a script is static. The agent can decide which tool to use next based on intermediate results, handle errors, and retry, creating more resilient and intelligent geospatial workflows than a hard-coded script.

Your agent should always start with `check_coverage_point` or `check_coverage_polygon`. Your chain's logic can then route to a different path or end gracefully if the tool returns 'false', preventing wasted calls to imagery tools.

Your agent sends geospatial data like point coordinates and polygon boundaries. All requests from your agent to the MCP Server are executed in an ephemeral, sandboxed container on Vinkius. The platform manages the secure authentication with Nearmap, so your raw credentials are never part of your agent's logic.

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