How to Use the Neon (Serverless PostgreSQL) MCP in Google ADK

Q: Can I use Gemini's long context to analyze schemas retrieved from Neon (Serverless PostgreSQL) using the Google ADK?

Yes, the agent can call listdatabases and feed the entire schema layout into Gemini's context window. This allows the model to generate highly accurate queries tailored to your specific database structures.

Manage your Neon (Serverless PostgreSQL) databases using Gemini models and Google ADK enterprise workflows.

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 Google ADK

Create your Vinkius account to connect Neon (Serverless PostgreSQL) to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fast Branching for BigQuery Pipelines

By invoking `create_branch` through this MCP Server, your Google ADK agent instantly duplicates production tables. Enterprise data workflows often require moving operational data into analytics warehouses, and this tool lets you stage those environments without any storage overhead. This allows Gemini to analyze complex transactional states alongside BigQuery datasets. The agent handles the staging database lifecycle automatically, cleaning up temporary resources once the analytical pipeline finishes.

Automated Project Provisioning

The Gemini agent uses `create_project` to deploy fresh serverless workspaces whenever your cloud infrastructure demands a new tenant database. This allows you to spin up isolated environments for new enterprise clients on demand. You can inspect these newly created workspaces using `get_project` to verify storage quotas and regional settings. This automation eliminates the manual overhead of clicking through cloud consoles to provision resources.

Dynamic Schema Inspection

Gemini's massive context window allows it to reason over entire database structures fetched via `list_databases`. The agent calls this tool to ingest your complete database configuration in a single prompt. This gives your Google ADK system the exact context it needs to write precise SQL queries. It maps active endpoints using `list_endpoints` to execute these queries against the correct serverless branch without routing errors.

Setup guide

Set up Neon (Serverless PostgreSQL) MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Neon (Serverless PostgreSQL) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Neon (Serverless PostgreSQL)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Neon (Serverless PostgreSQL) tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

You supply your Neon API token to the server configuration. The Google ADK agent then securely executes commands like `list_projects` on your behalf without exposing credentials to the model.

Yes, the agent can call `list_databases` and feed the entire schema layout into Gemini's context window. This allows the model to generate highly accurate queries tailored to your specific database structures.

Yes, you can run the server locally using Stdio transport or host it on Vinkius using HTTP. Both methods let your Google ADK agent discover tools like `list_branches` instantly.

You can restrict tool access by passing a specific list of allowed tools to your agent constructor. For example, omit `delete_project` from the toolset to prevent any accidental destructive actions.

All database connection strings, project configurations, and query traffic metadata are processed within an isolated V8 sandbox on Vinkius. Your sensitive credentials never touch Google's training loops or external logging systems.

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