How to Use the Agility CMS MCP in OpenAI Agents SDK

Q: Can OpenAI Agents SDK search specific Agility CMS lists?

Yes. The server exposes searchcontentreference to find keywords in any reference list. You can also use countreferenceitems to check the size of the list before pulling data.

Connect Agility CMS to your OpenAI Agents SDK system. Build production agents that read content and navigate sitemaps safely.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Agility CMS MCP to OpenAI Agents SDK

Create your Vinkius account to connect Agility CMS 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 Agility CMS with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Agility CMS Architecture with OpenAI Agents SDK

The `get_site_tree` tool hands over the entire nested sitemap architecture directly to your OpenAI agent. Your system needs to know how the digital channel is structured before it acts. This lets the agent understand exactly where content lives without guessing. When the agent drills down into a specific page, `get_page_layout` pulls the structural modules. You get a clear view of the layout. Built-in guardrails validate this data before passing it to specialized agents for further processing.

Sync Content via MCP Server

The `sync_incremental_items` tool grabs only the records updated since your last sync token. Fetching the entire database every time wastes tokens. Your agent stays current with minimal overhead. For structural updates, `sync_incremental_pages` works the exact same way. Pass a 0 for a full backup, then let your OpenAI tracing dashboard monitor the continuous, lightweight updates across your production environment.

Query Reference Lists

The `search_content_reference` tool lets your agent look up specific keywords inside a Content Reference List. Finding exact data matters in a production setup. If you need a specific blog post or author, it finds the match fast. Once located, `get_single_item` fetches the exact article body using its numeric content ID. The OpenAI Agents SDK auto-discovers these tools, meaning you just pass the Vinkius MCP endpoint and start querying.

Setup guide

Set up Agility CMS 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 Agility CMS tools at runtime.
3

Create your Agent

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

Run the agent

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

Install openai-agents via pip. Create an MCPServerStreamableHttp instance pointing to your Vinkius endpoint, then pass it in the mcp_servers list to your Agent constructor.

Yes. The server exposes search_content_reference to find keywords in any reference list. You can also use count_reference_items to check the size of the list before pulling data.

It does. You can configure one agent to map the site with get_site_flat_router and hand off the resulting URLs to a specialized agent that analyzes the content.

Set cacheToolsList=True when configuring the MCP Server connection. This prevents the SDK from re-fetching the 10 available tools on every agent invocation.

This server handles article bodies, media gallery mappings, and page layouts. Vinkius runs the connection inside a zero-trust V8 Isolate Sandbox that destroys itself after the request finishes, leaving no trace of your layout data.

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