How to Use the Wing Assistant MCP in Mastra AI

Q: How does Wing Assistant help manage failure in Mastra AI?

By giving you explicit tools like gettaskstatus, your complex workflows can check the status repeatedly. This allows Mastra AI's built-in engine to automatically retry or branch when a job fails.

Q: If I need to know all available assistants using Wing Assistant and Mastra AI, what do I use?

You call listassistants. This gives you the full inventory of virtual agents. Your agent framework uses this list to ensure only authorized assistants are included in the workflow.

Q: Can Wing Assistant handle task updates when using Mastra AI?

Yes, use updatetask. If a job needs different input or parameters after failing, you update it here. This modified state is what allows Mastra AI to continue its complex execution.

Q: How do I check on an existing job using Wing Assistant and Mastra AI?

You call gettaskstatus, passing in the task ID. This provides a direct status report that your workflow engine can read to determine the next step.

Build complex, resilient workflows that handle failures using Mastra AI with Wing Assistant.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Wing Assistant MCP to Mastra AI

Create your Vinkius account to connect Wing Assistant 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 Wing Assistant with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Monitor Task Status

Getting the current status of a unit of work is simple using `get_task_status`. This tool tells your multi-step workflow exactly where a job stands, allowing for conditional branching based on success or failure. You can also use `list_tasks` to pull all assigned jobs. Mastra AI uses this data feed to decide if a full retry loop is necessary because too many tasks are stalled.

Manage Assistant Profiles

To start any workflow, you first need the assistant's details. The `get_assistant` tool pulls all required metadata for a specific virtual agent. This ensures your complex process starts with the correct setup. You can also use `list_assistants` to pull an inventory of every available assistant. Mastra AI uses this list to validate which agents are allowed to participate in the workflow.

Create and Modify Jobs

Start a whole process by calling `create_task`, defining both the title and detailed description. This initiates the unit of work that your complex, failure-proof pipeline needs to handle. If an initial step fails or requires manual input, use `update_task` to adjust the parameters of an existing task. Mastra AI then automatically retries the entire process with these new instructions.

Setup guide

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

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

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

By giving you explicit tools like `get_task_status`, your complex workflows can check the status repeatedly. This allows Mastra AI's built-in engine to automatically retry or branch when a job fails.

You call `list_assistants`. This gives you the full inventory of virtual agents. Your agent framework uses this list to ensure only authorized assistants are included in the workflow.

Yes, use `update_task`. If a job needs different input or parameters after failing, you update it here. This modified state is what allows Mastra AI to continue its complex execution.

This MCP Server deals with task records and assistant metadata. Specifically, it handles the creation and modification of tasks, which are structured by title and description.

You call `get_task_status`, passing in the task ID. This provides a direct status report that your workflow engine can read to determine the next step.

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