How to Use the Evernote MCP in Google ADK

Q: How do I connect the Evernote MCP to Google ADK?

Install the google-adk package. Wrap your endpoint in StreamableHttpServerParameters and pass it to McpToolset. Hand that toolset straight to your LlmAgent.

Q: Can Google ADK filter which tools this MCP server exposes?

Yes. You can pass a toolnames list to the toolset configuration. If you only want your agent to read data, just expose getnote and searchnotes.

Q: How does the Google ADK agent find specific Evernote files without knowing the GUID?

It starts with a query. The agent runs searchnotes using standard query syntax to find matching items. It reads the returned GUIDs and then fetches the full text.

Plug this Evernote MCP server into Google ADK. Let your Gemini agents read, search, and update your personal notebooks.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Evernote MCP to Google ADK

Create your Vinkius account to connect Evernote 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 Evernote with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed your Gemini models with this MCP Server.

The `get_note` tool pulls full Evernote Markup Language directly into Gemini's massive context window. You can dump dozens of long-form notes into your agent's memory at once. It reads the raw ENML and understands exactly how your documents are structured. The `create_note` tool pushes a summary back to your account after an agent cross-references a project brief with BigQuery tables. This bridges your personal notes with your enterprise data. The new document syncs instantly to all your Evernote apps.

Navigate complex notebook structures.

The `list_notebooks` tool gives your Google ADK agent a complete map of your Evernote account. It discovers available folders before it even attempts to read specific files. The `list_notes` tool grabs up to 50 items from a specific notebook. If that returns too much noise, the agent uses `list_tags` to filter the results. You get precise retrieval without hallucinating document locations.

Execute precise searches and updates.

The `search_notes` tool taps directly into Evernote's native query syntax. Instead of relying on a basic keyword match, your agent runs complex searches to find exactly the right metadata. The `update_note` tool changes the text of an existing document. This immediately bumps the updateSequenceNum and triggers a cloud sync. If a workspace is missing, your agent calls `create_notebook` to build it on the fly.

Setup guide

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

Install the `google-adk` package. Wrap your endpoint in `StreamableHttpServerParameters` and pass it to `McpToolset`. Hand that toolset straight to your `LlmAgent`.

Yes. You can pass a `tool_names` list to the toolset configuration. If you only want your agent to read data, just expose `get_note` and `search_notes`.

It starts with a query. The agent runs `search_notes` using standard query syntax to find matching items. It reads the returned GUIDs and then fetches the full text.

Yes. When the agent builds a new folder, the tool returns the fresh GUID and metadata. The agent immediately uses that ID to start dropping files into it.

Your private ENML bodies, tags, and account quotas are routed through a zero-trust architecture. Vinkius processes the developer token authentication in a temporary sandbox, ensuring your Gemini agents get the raw text while no persistent logs remain on our infrastructure.

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