How to Use the Nuclino MCP in Google ADK

Q: Can I limit which Nuclino tools the Google ADK can access?

Yes, you can use the toolnames filter when initializing your MCP Server toolset in Python. This lets you restrict your Gemini agent to read-only tools like getitem and listitems while blocking write or delete actions.

Q: How does Google ADK handle large Nuclino file attachments?

The listfiles tool returns pure URL bindings mapping binary data records back to object storage. This allows your Gemini agent to reference the files or download them for processing within your Google Cloud pipeline.

Q: How does Gemini search across my entire Nuclino team structure?

The agent first calls listteams to find your root organizational unit, then drills down using listworkspaces. This structural traversal gives Gemini a complete map of your knowledge base hierarchy.

Q: How is my Nuclino team directory data secured during execution?

Your team directory information, including user lists from listusers, is processed inside isolated, ephemeral execution environments. No persistent storage is used, ensuring your organization's internal structure remains strictly private.

Feed your Nuclino knowledge base directly into Gemini long-context reasoning pipelines using the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nuclino MCP to Google ADK

Create your Vinkius account to connect Nuclino 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 Nuclino with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-Context Wiki Digestion via Google ADK

`list_items` pulls all document UUIDs, titles, and creation metadata from a specific workspace layer to feed your Gemini models. Because Gemini handles over a million tokens, your agent can digest your entire Nuclino knowledge base in a single pass. This integration lets you combine your BigQuery telemetry data with your internal docs. The Google ADK combines these datasets, allowing the agent to write analytical summaries directly back to Nuclino workspaces.

Semantic Workspace Discovery with MCP Server Tools

`search_items` runs indexed semantic searches across your team to locate documents without needing exact title matches. This allows your Google Cloud enterprise agents to find relevant contextual information instantly. Once the search locates the right targets, `get_item` extracts the raw Markdown payload for deep analysis. The agent can then use `list_fields` to map customizable structured property fields globally binding your team.

Structured Knowledge Archiving

`create_item` builds permanent wiki pages in real-time, allowing your Google Cloud pipelines to archive log reports or pipeline statuses automatically using our managed MCP Server. If an environment fails, your agent writes the post-mortem directly to the correct workspace. To keep the workspace clean, the agent can use `update_item` to append new edits to existing documents rather than cluttering your team with duplicate pages. This keeps your documentation accurate and synchronized.

Setup guide

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

Yes, you can use the `tool_names` filter when initializing your MCP Server toolset in Python. This lets you restrict your Gemini agent to read-only tools like `get_item` and `list_items` while blocking write or delete actions.

The `list_files` tool returns pure URL bindings mapping binary data records back to object storage. This allows your Gemini agent to reference the files or download them for processing within your Google Cloud pipeline.

Yes, this MCP Server supports both transport protocols. You can run it locally via Stdio or connect to Vinkius over a secure, managed HTTP stream using a single authorization token.

The agent first calls `list_teams` to find your root organizational unit, then drills down using `list_workspaces`. This structural traversal gives Gemini a complete map of your knowledge base hierarchy.

Your team directory information, including user lists from `list_users`, is processed inside isolated, ephemeral execution environments. No persistent storage is used, ensuring your organization's internal structure remains strictly private.

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