How to Use the Nhost MCP in Mastra AI

Q: How do I handle Nhost signup failures inside a Mastra AI workflow?

Use signupotpemail or signupemailpassword inside a Mastra step block. If the registration fails, the built-in workflow engine catches the error and triggers a retry or redirects the flow to an error-handling branch.

Q: Can Mastra AI process file uploads to Nhost storage asynchronously?

Yes, you can register uploadfile as an agent tool and run it as an asynchronous background step. The workflow continues executing other tasks while the file is being processed by the storage backend.

Q: How does this MCP Server handle credential rotation during Mastra AI workflows?

The agent monitors the life of the JWT and calls refreshtoken before executing subsequent steps. This prevents workflow interruptions during complex, multi-minute automated processes.

Run multi-step auth and storage workflows with Mastra AI and the Nhost MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nhost MCP to Mastra AI

Create your Vinkius account to connect Nhost 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 Nhost with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate user onboarding in Mastra AI

The `signup_email_password` tool registers new users and triggers downstream onboarding workflows inside your agent pipeline. If the signup succeeds, the workflow automatically transitions to setting up default user profiles. No need to write custom error handling for every single network hiccup. If the registration fails due to network issues, Mastra retries the call with exponential backoff.

Conditional storage flows via MCP Server

The `upload_file` tool sends raw assets to your storage buckets as part of a structured agent workflow. If the file is an image, the pipeline branches to call `get_file` with transformation parameters to generate thumbnails. When a file fails validation, the agent executes `delete_file` to clean up the storage bucket instantly. This prevents orphaned files from cluttering your backend and inflating your storage bill.

Self-healing authentication workflows

The `refresh_token` tool maintains continuous session access during long-running background tasks. If a token expires mid-workflow, the agent automatically runs this tool to fetch a new JWT and resumes the pending operations. When suspicious activity is detected, the workflow triggers `change_email` or initiates a password reset with `reset_password`. The agent executes these security actions sequentially, ensuring user accounts remain locked down.

Setup guide

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

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

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

Use `signup_otp_email` or `signup_email_password` inside a Mastra step block. If the registration fails, the built-in workflow engine catches the error and triggers a retry or redirects the flow to an error-handling branch.

Yes, you can register `upload_file` as an agent tool and run it as an asynchronous background step. The workflow continues executing other tasks while the file is being processed by the storage backend.

The agent monitors the life of the JWT and calls `refresh_token` before executing subsequent steps. This prevents workflow interruptions during complex, multi-minute automated processes.

Yes, you can configure Mastra to require human approval before executing sensitive tools like `change_email`. The workflow pauses and alerts an admin before modifying any user records.

All session tokens and JWTs are stored in-memory during workflow execution and wiped once the run completes. No persistent storage or logging of these credentials occurs within the execution environment.

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