How to Use the Magicplan MCP in Mastra AI

Q: How do I register Magicplan tools in Mastra AI?

Install @mastra/mcp. Initialize the MCPClient with your Vinkius server URL. Call listTools and spread the returned array directly into your agent's configuration.

Q: Can Mastra AI retry failed Magicplan API calls?

It does this automatically. If an MCP call to getworkspaceinfo fails due to network lag, Mastra catches the error. The workflow engine applies exponential backoff and tries again.

Q: How do I handle form data pipelines with Magicplan and Mastra AI?

You build a workflow that runs listavailableforms first. The agent passes the form IDs to getplanformdata. If the checklist is incomplete, Mastra branches the logic to email the contractor.

Q: Does this setup support human-in-the-loop workflows?

Yes. You flag specific tools like getestimatedetails with approval requirements. The Mastra agent halts execution until a supervisor manually signs off on the financial pull.

Wire up resilient real estate workflows. Connect the Magicplan MCP server to Mastra AI to automate spatial data extraction.

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 Mastra AI

Create your Vinkius account to connect Magicplan to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Complex Project Syncs

The `list_magicplan_projects` tool pulls every active job site in your account. Mastra AI takes this list and feeds it into a conditional workflow. If a new project appears, the agent automatically triggers the next step to extract the details. It immediately calls `get_project_details` to read the metadata. If the API hits a rate limit, Mastra's built-in exponential backoff catches the 429 error and retries. Your sync job finishes without manual intervention.

Magicplan MCP Server Spatial Pipelines

The `get_project_floor_plan` tool extracts the full spatial layout for a given property. You drop this into a Mastra AI workflow step designed for architectural review. The agent reads the coordinates and hands them off to your internal database. Next, the workflow triggers `get_plan_measurements` to get the hard numbers. If the measurements reveal a square footage over a specific threshold, Mastra branches the logic. It routes the heavy commercial projects to a senior estimator while sending residential jobs down the standard path.

Resilient Estimate Processing

The `list_project_estimates` tool grabs the active quotes for a job. Mastra pulls these IDs and queues them for deep inspection. You set up a workflow that demands human approval before proceeding. When the agent runs `get_estimate_details`, it pauses. Mastra's `requireToolApproval` flag stops the execution. A human manager reviews the line-item costs, clicks approve, and the workflow resumes to send the final bid to the client.

Setup guide

Set up Magicplan MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Magicplan tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "magicplan-mcp-client",
  servers: {
    "magicplan-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Magicplan Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Magicplan tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Magicplan transactions"
);
console.log(result.text);

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 Mastra AI

Install `@mastra/mcp`. Initialize the `MCPClient` with your Vinkius server URL. Call `listTools` and spread the returned array directly into your agent's configuration.

It does this automatically. If an MCP call to `get_workspace_info` fails due to network lag, Mastra catches the error. The workflow engine applies exponential backoff and tries again.

You build a workflow that runs `list_available_forms` first. The agent passes the form IDs to `get_plan_form_data`. If the checklist is incomplete, Mastra branches the logic to email the contractor.

Yes. You flag specific tools like `get_estimate_details` with approval requirements. The Mastra agent halts execution until a supervisor manually signs off on the financial pull.

Your line-item material costs and labor estimates pass through a strict V8 Isolate Sandbox. Vinkius runs this integration in a zero-trust, ephemeral container. The memory wipes clean the moment Mastra receives the data.

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