How to Use the Ninox MCP in Google ADK

Q: How do I set up Ninox with the Google ADK?

Install the google-adk package, define your McpToolset with the Vinkius URL, and pass it to your LlmAgent to expose Ninox tools like listdatabases directly to Gemini.

Q: Does Google ADK support Ninox script execution?

Yes, executeninoxscript runs custom Ninox formulas directly from your Google ADK agent. This lets you trigger complex backend database calculations using Gemini.

Q: How do I restrict write access on my Ninox MCP database?

Use the toolnames filter in your Google ADK setup to exclude updaterecord or deleterecord from the Ninox tools.

Connect Gemini's million-token context with your Ninox databases using the Google ADK 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 Ninox MCP to Google ADK

Create your Vinkius account to connect Ninox 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 Ninox with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deep Ninox schema analysis for Gemini agents

`get_database_schema` pulls raw Ninox table configurations into Gemini's massive context window via the Google ADK. This tool lets your enterprise agent understand complex relational structures across multiple Ninox databases instantly. Combining this Ninox schema data with Google ADK's native BigQuery integration allows your agent to cross-reference cloud analytics with live Ninox records. You get unified data reasoning without writing manual migration scripts.

Filtered Ninox data retrieval with Google ADK

`list_records` queries specific tables inside your Ninox workspace based on runtime parameters generated by Google ADK. The Google ADK passes these parameters directly from Gemini prompts, returning structured Ninox rows for your agent to analyze. You can restrict the Ninox tools exposed to Google ADK by setting the `tool_names` filter on your `McpToolset`. This prevents Gemini from calling write tools when it only needs to read.

Update Ninox records using this MCP Server

`update_record` modifies existing rows in your Ninox tables when your Google ADK agent detects changes in external Google Cloud data sources. This keeps your relational database in sync with your Google Cloud infrastructure. The MCP Server manages the HTTP transport to execute these Ninox updates securely for Google ADK. Your Gemini agent receives confirmation of the update, which it can then log to Vertex AI tracing.

Setup guide

Set up Ninox 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 Ninox 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="Ninox_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Ninox 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 Ninox. 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 Ninox 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 Ninox MCP in Google ADK

Install the google-adk package, define your `McpToolset` with the Vinkius URL, and pass it to your `LlmAgent` to expose Ninox tools like `list_databases` directly to Gemini.

Yes, Gemini's long context easily holds the entire output of `get_database_schema` retrieved by Google ADK. This allows the agent to reason over complex Ninox relationships.

Yes, `execute_ninox_script` runs custom Ninox formulas directly from your Google ADK agent. This lets you trigger complex backend database calculations using Gemini.

Use the `tool_names` filter in your Google ADK setup to exclude `update_record` or `delete_record` from the Ninox tools.

Your Ninox table structures and record payloads are transmitted via secure HTTPS and processed in ephemeral, isolated runtimes before reaching Google ADK. Vinkius never persists your relational schemas or database contents.

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