How to Use the ncScale MCP in Mastra AI

Q: How do I connect the ncScale MCP Server to a Mastra AI agent?

You register the server using the MCPClient class in Mastra and pass its URL. Once registered, you spread the tools into your agent's configuration, allowing it to call listalerts and listlogs during workflow execution.

Q: Can Mastra AI workflows trigger actions based on ncScale alerts?

Yes, you can set up a Mastra workflow that polls listalerts at regular intervals. If an active alert is returned, the workflow uses conditional branching to analyze the alert severity via getalert and execute recovery steps.

Q: How do I implement human-in-the-loop validation for ncScale tools in Mastra AI?

You configure requireToolApproval on your Mastra agent for sensitive operations. This ensures the MCP Server doesn't execute actions like querying workspace details using getworkspaceinfo without admin approval.

Q: How does this server secure my workspace metadata and user list?

All requests to listusers and getworkspaceinfo are processed inside isolated, ephemeral V8 sandboxes. Your credentials are encrypted in transit and never persisted, keeping your user directories and workspace configurations completely safe from external exposure.

Build resilient, self-healing no-code pipelines using Mastra AI workflows and ncScale observability.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ncScale MCP to Mastra AI

Create your Vinkius account to connect ncScale 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 ncScale with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated incident triage with Mastra AI

When an integration breaks, you cannot rely on manual triage. This MCP Server lets your Mastra AI agents monitor system issues using `list_alerts` and trigger automated workflows the second a failure occurs. Mastra's workflow engine can branch based on the severity of the alert, routing urgent issues directly to your team. If a critical Bubble node fails, the workflow calls `get_node` to pinpoint the exact failure point. The agent can then automatically create a support ticket using `list_tickets` to track the issue, ensuring no silent failure is missed.

Self-healing no-code integrations

Mastra AI excels at handling multi-step tasks that might fail. By exposing `list_integrations` to your agent using this MCP Server, you can build a system that detects a failing Airtable connection and automatically initiates a retry loop. The agent checks the health of the connection using `list_logs`. If the logs show a rate-limit error, Mastra's built-in backoff engine pauses execution before attempting to check the status again via `get_workspace_info`.

Automated dashboard health checks

Use Mastra's cron triggers to run scheduled audits of your entire no-code setup. The agent calls `list_dashboards` and `list_nodes` to collect performance metrics across all active workspaces. If a specific dashboard reports a drop in sync speeds, the agent analyzes the node data. It compiles a summary of the affected nodes and updates your internal team dashboard, keeping your operations transparent.

Setup guide

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

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

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

You register the server using the `MCPClient` class in Mastra and pass its URL. Once registered, you spread the tools into your agent's configuration, allowing it to call `list_alerts` and `list_logs` during workflow execution.

Yes, you can set up a Mastra workflow that polls `list_alerts` at regular intervals. If an active alert is returned, the workflow uses conditional branching to analyze the alert severity via `get_alert` and execute recovery steps.

You configure `requireToolApproval` on your Mastra agent for sensitive operations. This ensures the MCP Server doesn't execute actions like querying workspace details using `get_workspace_info` without admin approval.

Mastra AI has built-in retry mechanisms with exponential backoff. If your agent hits a rate limit while running `list_logs`, the workflow automatically backs off and retries the request without crashing your monitoring script.

All requests to `list_users` and `get_workspace_info` are processed inside isolated, ephemeral V8 sandboxes. Your credentials are encrypted in transit and never persisted, keeping your user directories and workspace configurations completely safe from external exposure.

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