How to Use the Metorial MCP in Mastra AI

Q: How do I register Metorial MCP tools with a Mastra AI agent?

Use @mastra/mcp to instantiate a client pointing to your serverless endpoint. Call mcpClient.listTools and spread them directly into your agent configuration.

Q: Can I configure Mastra AI to require human approval before running Metorial server deletions?

Yes. Set requireToolApproval on the Mastra AI client before calling metorialdeleteserver to prevent accidental teardowns of production infrastructure.

Q: How does Metorial trace execution failures in Mastra AI workflows?

Call metorialgettracedetails using the transaction ID from the workflow error context. This returns the raw execution boundary logs for immediate post-mortem analysis.

Build resilient agentic workflows with Mastra AI and serverless Metorial infrastructure.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Metorial MCP to Mastra AI

Create your Vinkius account to connect Metorial 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 Metorial with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated failover for MCP Server tools

`metorial_invoke_server_tool` routes execution calls directly to your isolated container instances. Mastra AI wraps these calls in its workflow engine, enabling automatic retries with exponential backoff if a node fails. If a tool remains unresponsive, `metorial_get_server_status` checks the node health to determine if a reboot is necessary. Your workflow branches to a backup server without dropping the active agent session.

Workflow-driven server provisioning

`metorial_deploy_server` spins up a fresh serverless instance when a Mastra AI workflow step demands isolated compute. You pass the server parameters directly through your workflow state. Once the multi-step pipeline completes, `metorial_delete_server` destroys the container. This programmatic cleanup ensures you only pay for the exact seconds your code runs.

Observability-driven branching decisions

`metorial_get_usage_metrics` feeds latency and compute costs back into your workflow engine. Your agent can inspect these metrics to decide whether to run a heavy task or delegate to a cheaper node. Using `metorial_list_traces`, Mastra AI logs every tool execution step to a central audit trail. You get clear visibility into complex agent branching paths without manual logging code.

Setup guide

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

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

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

Use `@mastra/mcp` to instantiate a client pointing to your serverless endpoint. Call `mcpClient.listTools` and spread them directly into your agent configuration.

Yes. Set `requireToolApproval` on the Mastra AI client before calling `metorial_delete_server` to prevent accidental teardowns of production infrastructure.

Call `metorial_get_trace_details` using the transaction ID from the workflow error context. This returns the raw execution boundary logs for immediate post-mortem analysis.

The integration supports both Server-Sent Events and Streamable HTTP. It auto-detects the transport based on the endpoint URL you configure during initialization.

Your container setups and deployment parameters are stored in ephemeral, single-tenant sandboxes. Mastra AI communicates with Metorial using unique token authorization, keeping your execution boundaries 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