How to Use the Neon MCP in Google ADK

Q: How do I configure Neon tools inside Google ADK?

Use McpToolset with the HTTP transport pointing to your Vinkius endpoint inside your Google ADK setup. This registers all seventeen tools for your Gemini models immediately using this MCP Server.

Q: Can Google ADK manage multiple Neon projects?

Yes, your agent uses listprojects to get all project IDs. It can then switch contexts and run operations on different database instances.

Q: How does Google ADK retrieve connection strings for Neon?

The agent calls getconnectionuri to fetch the host, database name, and credentials. Google ADK can then feed this string to other cloud components.

Q: Can my agent delete projects to save costs?

Yes, the agent calls deleteproject via the MCP interface to wipe resources that are no longer needed. The project remains recoverable in the console for seven days if you make a mistake.

Run serverless Postgres databases alongside BigQuery using your Google ADK agents for fast data operations.

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 Google ADK

Create your Vinkius account to connect Neon 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 with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Branch Postgres from your Google ADK agent

The `create_branch` tool allows your Google ADK agent to clone Neon databases instantly with zero storage overhead. Your Google ADK workflow can spin up isolated Neon branches to test SQL migrations before pushing them to your main branch. The agent uses `list_branches` to monitor active Neon environments and verify status. This MCP Server lets you run safely without manually configuring Neon infrastructure in the cloud console.

Provision databases inside Google ADK pipelines

The `create_database` tool adds a new database to any Neon branch instantly. Your Google ADK agent can partition customer data on the fly based on incoming BigQuery events. The agent can then use `list_databases` to confirm the Neon database exists before starting raw SQL operations. This automation keeps your schema management fast and predictable.

Manage serverless compute endpoints via MCP Server

The `create_endpoint` tool lets your Google ADK agent configure read-only replicas or read-write compute for any Neon branch. This helps your Google ADK agent route analytical workloads away from your transactional database. To keep things clean, your agent can call `list_endpoints` to check if a Neon compute node is active or suspended. This saves money by ensuring you only run compute when your Google ADK pipeline needs it.

Setup guide

Set up Neon 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 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_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Neon 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 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 Google ADK

Use `McpToolset` with the HTTP transport pointing to your Vinkius endpoint inside your Google ADK setup. This registers all seventeen tools for your Gemini models immediately using this MCP Server.

Yes, your agent uses `list_projects` to get all project IDs. It can then switch contexts and run operations on different database instances.

The agent calls `get_connection_uri` to fetch the host, database name, and credentials. Google ADK can then feed this string to other cloud components.

Yes, the agent calls `delete_project` via the MCP interface to wipe resources that are no longer needed. The project remains recoverable in the console for seven days if you make a mistake.

All database metadata, branch configurations, and connection credentials stay isolated within sandboxed environments. Vinkius strips passwords from logs, ensuring your Google ADK workflows never expose database secrets.

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