How to Use the Mapflow MCP in LangChain

Q: Can a LangChain agent choose a Mapflow model automatically?

Yes. Your agent can call listmodels, parse the descriptions, and select the best model ID to use in a subsequent createprocessing call. This is a classic ReAct agent pattern.

Q: What's the best way to handle long-running Mapflow jobs with LangChain?

Build a loop in your chain that periodically calls getprocessingstatus. Only when the status is 'SUCCESS' should the agent proceed to call getprocessingresult.

Q: How can I monitor Mapflow API usage from my LangChain agent?

Your agent can use listprojects and listprocessings to count active and completed jobs. You can then log this information or use it to make decisions about starting new tasks.

Build autonomous geospatial analysis chains with LangChain to turn satellite imagery into structured data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mapflow MCP to LangChain

Create your Vinkius account to connect Mapflow 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 Mapflow with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Geospatial Pipelines

Build agents that think in steps. A LangChain agent can call `list_models` to find the right building detection model, then `create_project` to set up a workspace, and finally `create_processing` to start the analysis. It's a logical sequence, not just a blind script. The agent doesn't just fire and forget. It can intelligently poll `get_processing_status` to wait for the job to finish. Once done, it pulls the structured GeoJSON using `get_processing_result` to pass to the next link in your chain.

Manage Active Analysis Projects

Give your agent visibility into all ongoing work. Using `list_projects` and `list_processings`, your agent gets a real-time dashboard of your team's Mapflow activity. It knows what's running, what's finished, and what might be stuck. This lets you build management agents that do more than just run tasks. Imagine an agent that automatically retries failed processing jobs, archives old projects, or flags jobs that are running for too long.

Build Custom Agents with this LangChain MCP Server

The Mapflow MCP server exposes each operation as a separate tool for your agent. This granularity is key. Your agent can decide to `create_project` first, then evaluate options before committing resources with `create_processing`. This approach gives your agent control. It can check on a job with `get_processing_status` and decide whether to wait longer or move on to another task. It's how you build resilient systems that adapt to real-world conditions.

Setup guide

Set up Mapflow 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 Mapflow 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({
    "mapflow-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 Mapflow 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 Mapflow. 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 Mapflow 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 Mapflow MCP in LangChain

You pass the tools from this MCP server to a LangChain agent. The agent then decides the order, like calling `create_processing` and then using the output processing ID to call `get_processing_status`.

Yes. Your agent can call `list_models`, parse the descriptions, and select the best model ID to use in a subsequent `create_processing` call. This is a classic ReAct agent pattern.

Build a loop in your chain that periodically calls `get_processing_status`. Only when the status is 'SUCCESS' should the agent proceed to call `get_processing_result`.

Your agent can use `list_projects` and `list_processings` to count active and completed jobs. You can then log this information or use it to make decisions about starting new tasks.

The Mapflow server runs in a Vinkius security sandbox. Your satellite imagery and the resulting GeoJSON data are processed ephemerally and are only accessible via the auth token tied to your LangChain agent's session.

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