How to Use the Magicplan MCP in AutoGen

Q: How do AutoGen agents access Magicplan floor plans?

You register our MCP Server tools using the mcpservertools helper. This allows your AssistantAgent to call getprojectfloorplan during its conversational steps to analyze spatial layouts.

Q: How does AutoGen handle tool schemas from the Magicplan MCP Server?

The McpToolAdapter converts the server schemas into the format AutoGen expects. Your agents can immediately understand how to query tools like getplanmeasurements without manual mapping.

Run multi-agent AutoGen debates to audit Magicplan estimates and verify spatial dimensions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Magicplan MCP to AutoGen

Create your Vinkius account to connect Magicplan 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 Magicplan with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Magicplan estimates with AutoGen agents

This MCP integration lets you set up a multi-agent debate where one agent pulls spatial data using `get_plan_measurements` and another pulls pricing via `list_project_estimates`. The financial agent proposes a budget, while the spatial agent challenges it based on physical room dimensions. Relying on consensus-driven processes ensures that your cost estimates are always realistic before they get sent to clients. The agents debate back and forth, resolving discrepancies in your Magicplan data without you writing a single line of reconciliation logic.

Verify plan forms via multi-agent consensus

Field checklists are prone to human error, but AutoGen agents can cross-reference them programmatically. One agent calls `get_plan_form_data` to inspect the checklist answers, while a supervisor agent checks `get_project_details` to verify the project status. If the checklist claims work is complete but the project status says otherwise, the agents flag the mismatch. This multi-agent verification loop operates autonomously, flagging anomalies in your workspace records instantly.

Automate workspace user audits with an MCP Server

Managing permissions across large construction projects requires constant vigilance. An admin agent can call `list_workspace_users` to get the roster, while a security agent checks `get_workspace_info` to ensure only authorized domains have access. They negotiate the final access list, proposing removals or additions based on your corporate policies. You get a self-auditing workspace management pipeline that runs entirely on AutoGen's conversational framework.

Setup guide

Set up Magicplan 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 Magicplan 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="Magicplan_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

    result = await agent.run("List recent Magicplan 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 Magicplan. 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 Magicplan 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 Magicplan MCP in AutoGen

You register our MCP Server tools using the `mcp_server_tools` helper. This allows your `AssistantAgent` to call `get_project_floor_plan` during its conversational steps to analyze spatial layouts.

Yes, you can configure an estimator agent and a auditor agent. They will use `list_project_estimates` and `get_estimate_details` to debate and agree on the final project cost.

The `McpToolAdapter` converts the server schemas into the format AutoGen expects. Your agents can immediately understand how to query tools like `get_plan_measurements` without manual mapping.

We support both stdio and Streamable HTTP transports. You pass the connection URL to `StreamableHttpServerParams` to expose the project management tools to your agents.

All tool execution happens within an isolated, ephemeral V8 sandbox. Your workspace user lists and project cost breakdowns are processed in memory and never stored on our servers, keeping your business data private.

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