How to Use the Neon MCP in Mastra AI

Q: How do I configure Mastra AI to use the Neon MCP Server?

Install @mastra/mcp@latest and initialize a new MCPClient with your Vinkius URL. Call mcpClient.listTools() and spread the results directly into your Mastra Agent's tool array.

Q: Can Mastra AI automatically retry failed Neon branch creations?

It handles this out of the box. If createbranch fails due to a temporary Neon API limit, Mastra uses exponential backoff to re-attempt the clone without breaking the workflow.

Q: How do I prevent the agent from accidentally deleting Neon projects?

Flag deleteproject and deletebranch with Mastra's requireToolApproval. The agent will halt execution and wait for explicit human confirmation before dropping any databases.

Automate Postgres infrastructure workflows with Mastra AI. Build resilient database provisioning pipelines with automatic retries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Neon MCP to Mastra AI

Create your Vinkius account to connect Neon 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 with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Resilient Neon MCP Server Workflows

`create_project` and `create_branch` act as the foundation for automated database provisioning inside Mastra AI. You feed these tools into an agent to handle complex infrastructure setups. If a developer requests a new testing environment, the agent executes the branch creation and waits for the API response before proceeding to the next workflow step. Network hiccups happen, but Mastra's workflow engine catches them. If a call to `create_endpoint` times out, the built-in exponential backoff automatically retries the operation. You get reliable, hands-off Postgres provisioning without writing custom error handling for every single API call.

Conditional Database Operations

`list_branches` and `list_databases` let your agents make decisions based on live infrastructure state. Your workflow checks if a specific feature branch exists. If it does, the agent triggers `update_project` or fetches connection details. If it doesn't, the agent shifts paths and provisions a new environment from scratch. This logic replaces manual ticketing. You string together `create_role` and `get_connection_uri` to automatically generate credentials for new hires. The workflow evaluates the user's department, assigns the correct read-only or read-write endpoint, and delivers the connection string over Slack.

Human-in-the-Loop Destructive Actions

`delete_project` and `delete_branch` wipe out entire Postgres environments and all associated data. You do not want agents running these autonomously through an MCP integration. By using Mastra's `requireToolApproval` feature, you pause the workflow right before execution. A human reviews the target project ID, approves it, and the agent finishes the job. You avoid accidental data loss while still automating the cleanup process. The agent finds stale branches using `list_endpoints` to check for idle states, queues them for deletion, and pings an admin. Once approved, the infrastructure shrinks, saving you money without risking production data.

Setup guide

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

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

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

Install `@mastra/mcp@latest` and initialize a new `MCPClient` with your Vinkius URL. Call `mcpClient.listTools()` and spread the results directly into your Mastra Agent's tool array.

It handles this out of the box. If `create_branch` fails due to a temporary Neon API limit, Mastra uses exponential backoff to re-attempt the clone without breaking the workflow.

Flag `delete_project` and `delete_branch` with Mastra's `requireToolApproval`. The agent will halt execution and wait for explicit human confirmation before dropping any databases.

Yes. The tools return immediate metadata. The agent parses the result of `create_endpoint` and can conditionally proceed to run migrations or seed data based on the active state.

The MCP Server processes highly sensitive PostgreSQL passwords and host addresses via `get_connection_uri`. Vinkius isolates this operation in a zero-trust execution environment, meaning your database credentials are never logged, stored, or exposed outside the immediate tool execution cycle.

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