How to Use the Drata MCP in OpenAI Agents SDK

Run multi-agent OpenAI Agents SDK workflows with this Drata MCP Server to pull real-time SOC 2 evidence.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Drata MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run continuous compliance checks in OpenAI Agents SDK

Run continuous compliance checks by letting your agent call `drata_list_tests` and `drata_list_controls` directly. This setup connects your OpenAI agents to your compliance database to audit cloud environments without manual script writing. You can build autonomous compliance guards with this integration. Your agent can pull the exact failing resource details using `drata_list_assets` and ping the responsible engineer before an external auditor ever sees the gap.

Automate personnel onboarding reviews

Query `drata_list_personnel` to find out which employees are missing critical security training milestones. HR compliance is usually a manual mess of spreadsheets and Slack pings, but your agent can run this check on a schedule. The agent can inspect individual records via `drata_get_person` to verify MDM enrollment or background check dates. It handles the boring follow-ups so your security team can focus on actual threat modeling.

Validate policy updates with strict agent guardrails

Inspect active security documents using `drata_list_policies` to verify current acknowledgment rates before updating corporate records. Your OpenAI agent checks if the CISO approved the latest draft before pushing changes live. Using `drata_get_policy`, the agent inspects renewal dates and version histories. Because OpenAI Agents SDK supports strict runtime validation, your agent won't accidentally overwrite active policies with malformed compliance data.

Setup guide

Set up Drata 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 Drata tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK first. Initialize the server using the Streamable HTTP transport pointing to your Vinkius endpoint, then pass that server instance directly into your Agent constructor.

Yes. You can design one agent to fetch raw asset lists and another to analyze control failures, passing context between them using native SDK handoffs.

The SDK runs your agentic loop, allowing the model to call tests to pinpoint failures. If a critical check fails, you can write custom guardrails in Python to halt deployment pipelines.

No. Vinkius handles the connection. This MCP configuration keeps your production environment variables clean.

All personnel queries executed through the server run in an ephemeral, zero-trust sandbox. Your employees' background check dates and MDM enrollment details are processed in memory and never stored on the Vinkius platform.

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