How to Use the Amplenote MCP in Google ADK

Q: What's the process for adding this Amplenote toolset to a Google ADK agent?

First, pip install google-adk. Then, you create an McpToolset instance, pointing it to your Vinkius server URL. You pass this toolset into the LlmAgent constructor's tools list.

Q: Can I limit which Amplenote tools my Google ADK agent can use?

You can. When you create the McpToolset, you can pass an optional toolnames filter. This lets you expose only a specific subset of tools, like searchnotes and getnote, while hiding others like deletenote.

Build enterprise agents on Google Cloud with the Google ADK that reason over your entire Amplenote knowledge base.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amplenote MCP to Google ADK

Create your Vinkius account to connect Amplenote 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 Amplenote with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Reason Over Your Entire Workspace

The Google ADK is built for Gemini's massive context window. Your agent can use `list_notes` to get a full directory of your workspace, then pull in dozens of documents using `get_note`. This lets it reason about projects and find connections across your entire knowledge base at once. Imagine asking your agent to summarize a project's history. It can fetch every related note and task, feed it all to the Gemini model, and give you a coherent summary. That's not possible with smaller context windows that force you to process notes one by one.

Connect Notes to Enterprise Data

This MCP Server gives your agent read/write access to Amplenote. You can use tools like `get_note` to pull meeting minutes and then have the agent cross-reference that information with sales data from a BigQuery table, all within the same session. This turns Amplenote into an active part of your Google Cloud workflow. An agent could see a new customer record in BigQuery, then automatically use `create_note` and `create_task` to set up a new project plan and onboarding checklist in your Amplenote workspace.

Build Google Cloud-Native Agents

The Google ADK is the native way to build agents for Google Cloud, and this Amplenote MCP Server plugs right in. Your agent can manage project plans by creating new documents with `create_note` or updating progress with `update_task`. Because it's all integrated, you can trigger these agents from other Google Cloud services. A new file in Cloud Storage could kick off a workflow where an agent reads the file, summarizes it, and saves that summary to Amplenote using `update_note`.

Setup guide

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

Google ADK works with Gemini models, which have a very large context window. Your agent can use `list_notes` and `get_note` to load many notes into context, allowing it to analyze and find patterns across your whole Amplenote workspace in a single prompt.

Yes, that's a primary use case. Your agent can query BigQuery for new data, then use the `create_task` tool from this MCP Server to add corresponding action items to your Amplenote account.

First, `pip install google-adk`. Then, you create an `McpToolset` instance, pointing it to your Vinkius server URL. You pass this toolset into the `LlmAgent` constructor's `tools` list.

You can. When you create the `McpToolset`, you can pass an optional `tool_names` filter. This lets you expose only a specific subset of tools, like `search_notes` and `get_note`, while hiding others like `delete_note`.

The server only accesses the note and task content within your Amplenote workspace. Your credentials are never seen. Vinkius provides a single endpoint token for authentication, and all requests are processed in a zero-trust, ephemeral environment that's torn down after each use.

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