How to Use the Digify MCP in OpenAI Agents SDK

Q: How do I connect the Digify MCP Server to the OpenAI Agents SDK?

Install the package via pip install openai-agents and initialize MCPServerStreamableHttp with your Vinkius endpoint. Pass this server instance inside the mcpservers list when instantiating your Agent.

Q: Can my OpenAI Agents SDK setup handle high-volume calls to Digify?

Yes, by setting cacheToolsList=True in your Python configuration. This prevents the SDK from querying the MCP server for tool definitions on every turn, speeding up tools like listactivities and getfile.

Q: How do agent handoffs work when managing a Digify data room in OpenAI Agents SDK?

You define one agent to monitor access with listdataroomguests and another to modify permissions. The OpenAI Agents SDK manages the state handoff, letting the security agent run inviteguest based on the auditor's findings.

Run secure document workflows in production with OpenAI Agents SDK using our managed MCP Server for real-time tracking.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Digify MCP to OpenAI Agents SDK

Create your Vinkius account to connect Digify 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 Digify with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate secure data rooms with OpenAI Agents SDK

The `create_dataroom` tool initializes isolated document environments programmatically based on agent decisions. Your OpenAI agent spins up these rooms instantly, then runs `invite_guest` to grant access to external partners without human intervention. The SDK handles the heavy lifting by caching these tool definitions. By setting `cacheToolsList=True`, your agent triggers these API calls in milliseconds, bypassing discovery overhead during high-volume document requests.

Audit document engagement via agent handoffs

The `get_dataroom_stats` tool pulls granular reader metrics directly into your agent's context window. One specialized agent can fetch these raw stats, analyze viewer attention spans, and hand off the task to a follow-up agent to adjust access levels. Tracing this workflow on your OpenAI dashboard exposes the exact step where `list_activities` was called. You see the raw payload, the agent's reasoning, and the exact timestamp when a guest opened a protected PDF.

Enforce strict file policies using built-in guardrails

The `protect_file` tool applies watermarks and dynamic access controls to files before they leave your secure boundary. Your Python agent executes this tool under strict guardrails, verifying that security parameters match company policy before the file is shared. If the agent attempts an unauthorized file modification, the SDK's validation layer blocks the execution. You maintain tight control over `list_files` through this secure MCP interface without custom wrapper code.

Setup guide

Set up Digify 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 Digify tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Digify 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="Digify Agent",
            instructions="You have access to Digify 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 Digify. 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 Digify 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 Digify MCP in OpenAI Agents SDK

Install the package via `pip install openai-agents` and initialize `MCPServerStreamableHttp` with your Vinkius endpoint. Pass this server instance inside the `mcp_servers` list when instantiating your Agent.

Yes, by setting `cacheToolsList=True` in your Python configuration. This prevents the SDK from querying the MCP server for tool definitions on every turn, speeding up tools like `list_activities` and `get_file`.

You define one agent to monitor access with `list_dataroom_guests` and another to modify permissions. The OpenAI Agents SDK manages the state handoff, letting the security agent run `invite_guest` based on the auditor's findings.

The SDK's built-in guardrails intercept the tool call before execution. If the agent generates an invalid payload for `create_dataroom`, the SDK blocks the call and logs the validation error in your dashboard.

Your PDF and office document metadata, along with viewer IP logs fetched by `list_activities`, stay inside Vinkius's ephemeral sandboxed MCP environment. The SDK only transmits the specific tool inputs and outputs required to execute the action, keeping your underlying files isolated from public model training.

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