How to Use the Dropbox Paper MCP in OpenAI Agents SDK

Q: How do I connect the Dropbox Paper MCP Server to my OpenAI Agents SDK?

Install the SDK via pip and use the MCPServerStreamableHttp class to point to your Vinkius endpoint. Pass this server instance inside the mcpservers list when initializing your Agent. The SDK auto-discovers all 12 tools, making them instantly available for your agent to call.

Q: Can an agent built with OpenAI Agents SDK search inside my Dropbox Paper docs?

Yes. The agent uses the searchfiles tool to run full-text searches across all your .paper files. It returns matching document paths and metadata, which the agent can then read or modify based on your instructions.

Q: How does the OpenAI Agents SDK handle pagination when listing Dropbox Paper files?

The agent first calls listfiles to get the initial batch of documents from your folder. If the result contains a cursor, the agent automatically invokes listfilescontinue to fetch the remaining records. This prevents memory limits from crashing your runtime.

Spin up production-grade OpenAI Agents SDK systems that manage your team docs without manual API integration.

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 OpenAI Agents SDK

Create your Vinkius account to connect Dropbox Paper to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build production-grade agents with guardrails

The `dropbox-paper-mcp` toolset exposes 12 distinct operations directly to your agent workflows. Your system uses `create_document` to write markdown files and `move_file` to keep your team directory structured. Because these run inside the OpenAI Agents SDK, you can set strict schema checks to ensure the agent never writes corrupted markdown. You get immediate access to real-time document search through `search_files`. The SDK handles the underlying API calls, while your agent coordinates complex tasks like updating shared links using `list_shared_links`. This setup ensures your production bots work within safe, predefined boundaries.

Auto-discover tools using this MCP Server

Connecting the `dropbox-paper-mcp` server to your OpenAI Agents SDK takes seconds with the streamable HTTP transport. The SDK queries the endpoint and immediately registers capabilities like `list_files` and `get_metadata` without manual schema definitions. Your agents immediately know how to query document directories. When your agent needs to paginate through large document folders, it automatically calls `list_files_continue`. You do not have to write custom loop logic or handle token refresh cycles. The Vinkius platform manages the authentication layer, passing clean payloads back to your Python runtime.

Multi-agent handoffs for document curation

You can split tasks between specialized agents to handle large-scale documentation updates using `list_shared_folders`. One agent scans your directory to find outdated access lists. It then hands off the list to a writer agent that uses `create_document` to draft updated guides. If an agent attempts an unauthorized action, the OpenAI tracing dashboard flags it immediately. You track every call to `get_space_usage` or `delete_file` down to the millisecond. This gives your engineering team full visibility into how agents interact with your team's knowledge base.

Setup guide

Set up Dropbox Paper MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Dropbox Paper tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Dropbox Paper tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Dropbox Paper tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Dropbox Paper Agent",
            instructions="You have access to Dropbox Paper tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the SDK via pip and use the `MCPServerStreamableHttp` class to point to your Vinkius endpoint. Pass this server instance inside the `mcp_servers` list when initializing your Agent. The SDK auto-discovers all 12 tools, making them instantly available for your agent to call.

Yes. The agent uses the `search_files` tool to run full-text searches across all your `.paper` files. It returns matching document paths and metadata, which the agent can then read or modify based on your instructions.

The agent first calls `list_files` to get the initial batch of documents from your folder. If the result contains a cursor, the agent automatically invokes `list_files_continue` to fetch the remaining records. This prevents memory limits from crashing your runtime.

You configure these restrictions directly in your agent's system instructions or by wrapping the tools in custom Python guardrails. This prevents the agent from executing critical tools like `delete_file` unless specific validation conditions are met.

Vinkius runs the integration inside an isolated V8 sandbox. Your actual document content, file paths, and metadata never persist on Vinkius servers. The MCP integration acts as a secure, ephemeral proxy that passes OAuth tokens directly to the official API.

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