How to Use the Mapflow MCP in AutoGen

Q: Can AutoGen agents collaborate on a single Mapflow project?

Yes, that's the core idea. One agent can createproject, share the project ID with another agent in the chat, and that second agent can then run createprocessing within that same project.

Q: How does an AutoGen group decide which Mapflow model to use?

The agents debate. An Analyst might call listmodels and propose one, but a QA agent could argue for another based on predefined criteria. They converge on a choice through conversation.

Deploy a team of AutoGen agents to debate, plan, and execute geospatial analysis with Mapflow.

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 AutoGen

Create your Vinkius account to connect Mapflow 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 Mapflow with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let Agents Debate Analysis Strategy

Assign roles. An "Analyst" agent proposes a plan: call `list_models` to find a road detection model, then run `create_processing`. A "QA" agent can challenge this, checking if the model is suited for the target region's topography before any credits are spent. The agents reach a consensus before acting. Once they agree, one agent executes the plan, polling `get_processing_status` for completion. This multi-agent review prevents costly mistakes from a single point of failure.

Build a Multi-Agent Review System

Create an automated QA workflow. One agent's job is to periodically call `list_projects` to find completed analyses. It then passes the processing IDs to a "Validator" agent for review. The Validator agent calls `get_processing_result` and checks the output GeoJSON against a set of business rules or ground-truth data. If it spots anomalies, it can flag the project and notify a human supervisor, all without manual intervention.

Simulate a GIS Team with this AutoGen MCP Server

You're not just running a tool, you're directing a digital team. A "Manager" agent can start a job with `create_project`. A "Technician" agent then runs the heavy-lifting with `create_processing`, using parameters the team agreed on. Meanwhile, a "Finance" agent can keep an eye on costs by calling `list_processings` to monitor the workload. This MCP server gives each specialized agent the exact tools needed to perform its function within the group.

Setup guide

Set up Mapflow 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 Mapflow 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="Mapflow_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You provide a filtered list of tools from the Mapflow MCP server when you initialize each agent. For example, your "Finance" agent might only get `list_processings`, while the "Technician" gets `create_processing`.

Yes, that's the core idea. One agent can `create_project`, share the project ID with another agent in the chat, and that second agent can then run `create_processing` within that same project.

The agents debate. An Analyst might call `list_models` and propose one, but a QA agent could argue for another based on predefined criteria. They converge on a choice through conversation.

Definitely. This agent's function would be to take a processing ID, call `get_processing_result`, and run checks on the returned data. It can then report its findings back to the group.

No, the data is not shared between agents. Your imagery is sent directly to the Mapflow server for processing. Agents typically only pass around references like project or processing IDs, not the raw geospatial data itself.

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