How to Use the Openli MCP in OpenAI Agents SDK

Q: How do I configure Openli with the OpenAI Agents SDK?

Install the library using pip, then initialize MCPServerStreamableHttp pointing to your Vinkius endpoint. Pass this instance into the mcpservers list when instantiating your agent.

Q: Can OpenAI Agents SDK automatically check the Openli system status?

Yes. Your agent invokes checkopenlistatus during initialization to confirm the API is online. If the check fails, the SDK raises an exception before any compliance workflows execute.

Q: How does Openli handle multi-agent handoffs in OpenAI Agents SDK?

You can build a dedicated privacy agent equipped with listvendors and getvendor. When a user asks about data processors, your main agent passes the conversation to this compliance specialist.

Q: Can I audit changes made by OpenAI Agents SDK tools?

Yes, the server provides listauditlogs to track every modification. Your agent can pull this list to generate compliance reports or verify that an agreement update was recorded.

Build production-safe compliance agents with the OpenAI Agents SDK and Openli to automate privacy workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Openli MCP to OpenAI Agents SDK

Create your Vinkius account to connect Openli to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Openli with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automate DSAR handling with OpenAI Agents SDK

The `create_dsar` tool lets your OpenAI Agents SDK agent spin up new data subject access requests when users ask to delete or export their information. The agent flags requests, updates the status, and monitors the queue using `list_dsars` to keep your legal operations organized. Because the OpenAI Agents SDK supports safety guardrails, you can block the agent from executing `create_dsar` until a human operator signs off. This prevents rogue deletions while keeping the bulk of the workflow hands-off.

Push live cookie consent to Openli

Your AI agent uses `save_consent` to log user preferences directly to the compliance registry the moment they click accept. It queries existing records via `get_consent` to verify if a returning visitor already has active settings on file. When deploying with the OpenAI Agents SDK, you can route these consent checks through a specialized compliance agent. This agent handles the heavy lifting, then hands off the conversation back to your main customer-facing agent.

Generate legal agreements via MCP Server

This MCP Server exposes `create_agreement` to build updated privacy policies and terms of service based on changing regulatory requirements. The agent fetches template details through `get_agreement` to ensure the generated text matches your exact corporate specifications. By setting `cacheToolsList=True` in your OpenAI Agents SDK configuration, your agent instantly accesses these document tools without repeating schema lookups on every single turn. This keeps response latency low during high-traffic agreement updates.

Setup guide

Set up Openli 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 Openli tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the library using pip, then initialize `MCPServerStreamableHttp` pointing to your Vinkius endpoint. Pass this instance into the `mcp_servers` list when instantiating your agent.

Yes. Your agent invokes `check_openli_status` during initialization to confirm the API is online. If the check fails, the SDK raises an exception before any compliance workflows execute.

You can build a dedicated privacy agent equipped with `list_vendors` and `get_vendor`. When a user asks about data processors, your main agent passes the conversation to this compliance specialist.

Yes, the server provides `list_audit_logs` to track every modification. Your agent can pull this list to generate compliance reports or verify that an agreement update was recorded.

All transmission of consent tokens and DSAR payloads occurs over encrypted HTTPS connections managed by the Vinkius sandbox. No local logs of these sensitive records are stored on the host, ensuring compliance with strict privacy standards.

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