How to Use the Notion MCP in Google ADK

Q: How do I register the Notion MCP server inside Google ADK?

Instantiate McpToolset with StreamableHttpServerParameters pointing to your Vinkius URL. Pass this toolset into your LlmAgent constructor. The Gemini model will automatically detect and call the workspace tools.

Q: Can I restrict Google ADK to read-only access on Notion?

Yes. You can pass a toolnames filter to McpToolset containing only getpage, getblocks, and querydatabase. This blocks the agent from running destructive actions like deleteblock.

Q: How do I find workspace user IDs for assignments?

Use the listusers tool to get a full list of workspace members and bots. Your agent can then use these IDs to populate person properties when calling updatepageproperties.

Connect Gemini models to your workspace using Google ADK and this Notion MCP Server to analyze databases with million-token context windows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Notion MCP to Google ADK

Create your Vinkius account to connect Notion 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 Notion with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deep workspace search and analysis

The `search_pages` and `search_databases` tools let Gemini scan your entire workspace to locate relevant data sources. This allows your agent to pull context from multiple documents into Gemini's massive context window. You get complete workspace awareness without manual file exports. Once located, `get_blocks` pulls the raw text hierarchy directly into your cloud pipeline. This makes it easy to feed long-form documentation into Vertex AI models.

Run SQL-to-Notion pipelines with Google ADK

Here's the thing: manually syncing data is a waste of time. The `query_database` tool retrieves structured rows that you can map directly to BigQuery tables using this MCP Server. Your agent reads database schemas with `get_database` to align data types before running sync jobs. This connects your corporate data warehouse to your team's tracking pages. You write simple Python scripts that pull from Google Cloud and update your team's workspace. It keeps everyone aligned without manual status updates.

Automated page creation and updates

The `create_page` and `update_page_properties` tools allow your enterprise agent to log automated reports. When a cloud pipeline finishes, the agent creates a database row or updates an existing page title with `update_page_title`. To add detailed logs, the agent uses `append_block_children` to write structured paragraphs. This builds clean, readable execution logs automatically.

Setup guide

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

Instantiate `McpToolset` with `StreamableHttpServerParameters` pointing to your Vinkius URL. Pass this toolset into your `LlmAgent` constructor. The Gemini model will automatically detect and call the workspace tools.

Yes. You can pass a `tool_names` filter to `McpToolset` containing only `get_page`, `get_blocks`, and `query_database`. This blocks the agent from running destructive actions like `delete_block`.

Yes, the toolset supports both Stdio and HTTP transports. For production cloud agents, we recommend using the Vinkius hosted HTTP endpoint to avoid managing local subprocesses.

Use the `list_users` tool to get a full list of workspace members and bots. Your agent can then use these IDs to populate person properties when calling `update_page_properties`.

All transferred Notion pages, databases, blocks, and user lists are protected by TLS 1.3 in transit. The server runs in an ephemeral, single-tenant container that destroys itself after execution. No data is cached on disk.

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