How to Use the Dropbox Paper MCP in Google ADK

Q: Can I use Gemini to write new Dropbox Paper documents using the Google ADK?

Yes. The Google ADK uses the createdocument tool to write markdown content directly to a new file. You can feed data from BigQuery or Vertex AI into Gemini, then have the model structure it and save it as a document.

Q: How do I set up the Dropbox Paper MCP Server with Google ADK?

Install the ADK and initialize McpToolset with your Vinkius HTTP endpoint URL. Pass this toolset object to your LlmAgent constructor, and the Gemini model will instantly gain the ability to search, read, and organize your files.

Q: How does the Google ADK handle large file searches in Dropbox Paper?

The agent executes the searchfiles tool to scan your entire document directory for specific keywords. Because Gemini has a massive context window, you can feed the search results and file metadata directly into the model to extract complex insights.

Q: Can I limit the tools exposed to my Google ADK agent?

Yes. You can pass a filtered list of tool names to the McpToolset constructor to restrict access. For example, you can block deletefile while keeping search and document creation tools active.

Q: What happens to my shared links and document metadata during execution?

The MCP runtime processes metadata queries through getmetadata and shared link checks via listsharedlinks in real-time. This sensitive information is passed directly to your Google Cloud environment over an encrypted, ephemeral connection, ensuring zero data persistence on Vinkius.

Connect Dropbox Paper to your Google ADK pipelines and feed team knowledge directly into Gemini's long-context window.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dropbox Paper MCP to Google ADK

Create your Vinkius account to connect Dropbox Paper 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 Dropbox Paper with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed team documents directly to Gemini

The `dropbox-paper-mcp` integration lets your Gemini agent read and write files directly from your cloud storage. Your agent uses `list_files` to discover team updates and pulls the raw content into its million-token context window. This lets you run complex reasoning over your entire document archive without chunking. You write clean Python code using the Google ADK to parse these files. If your pipeline needs to organize output, it calls `create_folder` and `move_file` to structure the results. The agent handles the file operations while Gemini processes the natural language.

Connect enterprise data with this MCP Server

This `dropbox-paper-mcp` server links your collaborative documents to Google Cloud tools like BigQuery. Your agent can run a database query, format the results, and call `create_document` to write a fresh report. This eliminates the manual copy-paste work between your data warehouse and team wikis. You manage the connection using the `McpToolset` class in the Google ADK. The toolset exposes actions like `list_shared_folders` so your agent can verify which departments have access to specific reports. It keeps your enterprise data pipelines synchronized with your actual team operations.

Track storage and metadata at scale

Large enterprise teams generate thousands of documents that quickly clutter shared spaces, requiring `get_space_usage` to monitor limits. Your Google ADK agent calls this tool to monitor account limits and flags folders that take up too much space. It uses `get_metadata` to identify abandoned files that have not been modified in months. When it finds obsolete files, the agent can call `delete_file` to clean up the directory. Because the ADK supports standard enterprise logging, every single file modification is tracked. You maintain a clean, organized workspace without manual auditing.

Setup guide

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

Yes. The Google ADK uses the `create_document` tool to write markdown content directly to a new file. You can feed data from BigQuery or Vertex AI into Gemini, then have the model structure it and save it as a document.

Install the ADK and initialize `McpToolset` with your Vinkius HTTP endpoint URL. Pass this toolset object to your `LlmAgent` constructor, and the Gemini model will instantly gain the ability to search, read, and organize your files.

The agent executes the `search_files` tool to scan your entire document directory for specific keywords. Because Gemini has a massive context window, you can feed the search results and file metadata directly into the model to extract complex insights.

Yes. You can pass a filtered list of tool names to the `McpToolset` constructor to restrict access. For example, you can block `delete_file` while keeping search and document creation tools active.

The MCP runtime processes metadata queries through `get_metadata` and shared link checks via `list_shared_links` in real-time. This sensitive information is passed directly to your Google Cloud environment over an encrypted, ephemeral connection, ensuring zero data persistence on Vinkius.

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