How to Use the Elevio MCP in OpenAI Agents SDK

Q: How can the OpenAI Agents SDK use Elevio to find outdated drafts?

Your agent calls the listdraftknowledgearticles tool. This returns a list of all articles in "Draft" status, which the agent can then process, review, or flag for a human to look at.

Q: Does this work with specialized agents in the OpenAI Agents SDK?

Absolutely. You could have one agent that only runs quickcontenthealthaudit and hands off a report to another agent responsible for fetching details with getarticledetails. The Elevio tools fit right into that model.

Give your OpenAI Agents SDK a direct line to your Elevio knowledge base for automated content audits and management.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Elevio MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Find and Fix Content Rot

Stop guessing about your knowledge base health. Give your agent a toolset to find problems before your users do. It can run a `quick_content_health_audit` to get a baseline, then dig deeper by checking for stale drafts with `list_draft_knowledge_articles`. Your agent can also find orphaned content by flagging empty categories using `list_empty_knowledge_categories`. This turns a manual, weekly chore into a scheduled job that just reports back what needs fixing. It's a much better use of everyone's time.

Give Agents Full Article Access

Your agent can now read and understand your documentation. Use `search_knowledge_articles` to find relevant content, then pull the full text and metadata with `get_article_details`. This is perfect for building a support agent that provides real answers, not just links. You can also have an agent monitor for changes. By checking `list_latest_article_updates`, your agent can trigger other workflows, like posting update notifications to a Slack channel or re-indexing content for an internal search engine.

Your Elevio MCP Server

This isn't just about articles. Your agent gets visibility into your Elevio setup. It can `list_knowledge_categories` to understand the content structure or `list_active_modules` to confirm your support widget is configured correctly. You can even build a monitoring agent that periodically calls `get_elevio_account_metadata` to check your API limits. If you're getting close to a threshold, the agent can send an alert before anything breaks. It's about proactive control.

Setup guide

Set up Elevio 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 Elevio tools at runtime.
3

Create your Agent

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

Run the agent

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

Your agent calls the `list_draft_knowledge_articles` tool. This returns a list of all articles in "Draft" status, which the agent can then process, review, or flag for a human to look at.

It lets you automate knowledge base maintenance. Instead of a person clicking through the Elevio admin panel, you write an agent that uses tools from this MCP server, like `quick_content_health_audit`, to do the work for you.

Yes. While this MCP server exposes all the tools, you can configure your agent's permissions within the SDK to only grant it access to specific functions, like read-only search or audit tools.

Absolutely. You could have one agent that only runs `quick_content_health_audit` and hands off a report to another agent responsible for fetching details with `get_article_details`. The Elevio tools fit right into that model.

Vinkius sends Elevio article content and metadata to your agent over a secure connection. The data is processed in-memory by your agent. OpenAI's platform doesn't store this content unless you explicitly log it in your traces.

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