How to Use the Structured MCP in Mastra AI

Q: How should I start a new project with Structured using mastra-ai?

Use createplan to establish the core structure. This initiates your workflow, and if that fails, Mastra AI can automatically manage retries until the plan is ready.

Q: Does mastra-ai help me track task changes in Structured?

Yes. Your agent can use updatetask to make changes. If the update fails, Mastra AI's built-in logic handles the failure and keeps the workflow running.

Q: What is the best way to list all plans with Structured using mastra-ai?

Call listplans. This action allows your agent to gather a full inventory of existing structures, which can then be fed into another process step.

Q: If I need to check user credentials, what tools should I use with Structured and mastra-ai?

Use getuserprofile first. This ensures the initial state is correct before any complex task management or plan creation attempts are made.

Build complex, self-correcting workflows using Structured and mastra-ai.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Structured MCP to Mastra AI

Create your Vinkius account to connect Structured to Mastra AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Structured with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Initializing Workflows

Use `create_plan` to start a new structured process. If the plan creation fails for any reason, your agent can automatically retry with different parameters. Listing all available plans via `list_plans` lets your workflow check if a foundational structure already exists before proceeding. This prevents unnecessary failure states.

Validation and State Checks

`get_user_profile` allows the agent to validate the user's current credentials at step zero of any complex workflow. If validation fails, it triggers a retry loop with an error message. Calling `get_task_details` lets your system verify task prerequisites before attempting modification or completion.

Iterative Management

If a multi-step process requires adjustment, `update_task` handles it. Your workflow can automatically update due dates or titles based on failure analysis. If the task needs to be removed entirely and no longer relevant, `delete_task` cleans up the record, preventing the system from running into stale data errors down the line.

Setup guide

Set up Structured 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 Structured 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: "structured-mcp-client",
  servers: {
    "structured-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Structured 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 Structured. 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 Structured 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 Structured MCP in Mastra AI

Use `create_plan` to establish the core structure. This initiates your workflow, and if that fails, Mastra AI can automatically manage retries until the plan is ready.

Yes. Your agent can use `update_task` to make changes. If the update fails, Mastra AI's built-in logic handles the failure and keeps the workflow running.

Call `list_plans`. This action allows your agent to gather a full inventory of existing structures, which can then be fed into another process step.

Use `get_user_profile` first. This ensures the initial state is correct before any complex task management or plan creation attempts are made.

This Structured MCP Server touches user profile information via `get_user_profile`, which requires accessing sensitive account details. Treat this data with the highest level of care in your workflows.

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