How to Use the Neon (Serverless PostgreSQL) MCP in Mastra AI

Q: How do I integrate Neon (Serverless PostgreSQL) tools into Mastra AI agents?

Instantiate the MCPClient in Mastra and pass the server URL. Call mcpClient.listTools() and spread them into your agent's tools array to give it full database management capabilities.

Q: How do I require approval before a Mastra AI agent runs deleteproject?

Use Mastra's requireToolApproval option when registering the deleteproject tool. The agent pauses the workflow and waits for your confirmation before destroying the Postgres workspace.

Build resilient database automation workflows that branch, audit, and clean up Neon (Serverless PostgreSQL) instances via Mastra AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Neon (Serverless PostgreSQL) MCP to Mastra AI

Create your Vinkius account to connect Neon (Serverless PostgreSQL) 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 Neon (Serverless PostgreSQL) with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate conditional database branching in Mastra AI workflows

`create_branch` duplicates your database instantly, so your Mastra AI agents spin up isolated testing environments as part of automated CI steps. If the branch creation fails, Mastra's built-in workflow engine triggers automatic retries with exponential backoff. You spread the tools from `listTools()` into your Mastra agent configuration. The agent evaluates the branch state and routes subsequent workflow steps based on whether the copy-on-write clone is ready.

Self-healing database project provisioning

`create_project` provisions empty serverless workspaces, allowing Mastra AI agents to spin up clean databases for new tenant signups. If a step in your deployment pipeline fails, Mastra handles the rollback logic to keep your infrastructure clean. This MCP Server exposes the workspace creation tools directly to your agent's toolset. The agent verifies the project using `get_project` before proceeding to schema migration steps.

Human-in-the-loop approvals for project deletion

`delete_project` destroys connection strings and evaporates physical storage blocks, which you guard using Mastra AI's human-in-the-loop approval system. Your agent drafts the deletion request but halts execution until an administrator approves the action. This prevents accidental loss of critical data during automated cleanups. Once approved, the workflow resumes and executes the deletion, ensuring safe infrastructure management.

Setup guide

Set up Neon (Serverless PostgreSQL) 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 Neon (Serverless PostgreSQL) 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: "neon-serverless-postgresql-mcp-client",
  servers: {
    "neon-serverless-postgresql-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Neon (Serverless PostgreSQL) 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 Neon. 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 Neon (Serverless PostgreSQL) 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 Neon (Serverless PostgreSQL) MCP in Mastra AI

Instantiate the `MCPClient` in Mastra and pass the server URL. Call `mcpClient.listTools()` and spread them into your agent's tools array to give it full database management capabilities.

Yes. Mastra AI features a built-in workflow engine that automatically manages rate limits and retries when executing `list_branches` across multiple projects.

Use Mastra's `requireToolApproval` option when registering the `delete_project` tool. The agent pauses the workflow and waits for your confirmation before destroying the Postgres workspace.

Yes. Mastra AI auto-detects the transport type, allowing you to connect to this server over SSE or Streamable HTTP using a single Vinkius endpoint token.

The framework processes all database operations server-side through a secure V8 sandbox. This ensures that sensitive project IDs, Postgres roles, and connection strings never leak into client-facing logs.

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