Can my agent keep track of incremental updates to my CMS items?

Yes. The agent has tools specifically designed to fetch incremental updates using a sync token. It can request only the CMS items or pages that have changed (created, updated, or deleted) since the last automated sync, optimizing fetch latency.

How do I find the correct Reference Name to query content?

Reference Names match the identifiers predefined in your Agility CMS Models architecture (such as 'articles', 'authors', or 'posts'). If you are unsure, ask the agent to scan common variables based on your company's naming conventions.

Can my agent preview unpublished drafting content?

That depends on the API Token you supply during the integration. If you provide a Preview API Key, the agent will have read-access to the staging and drafted documents. If you provide a Fetch API key, it will only see published items.

Agility CMS MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Agility CMS
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Agility CMS through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Agility CMS Assistant",
            instructions=(
                "You help users interact with Agility CMS. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Agility CMS"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Agility CMS MCP Server

Connect your Agility CMS instance to your AI agent and turn it into the ultimate Headless CMS assistant. Skip manual API queries and interact directly with your content architecture using natural language.

The OpenAI Agents SDK auto-discovers all 10 tools from Agility CMS through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Agility CMS, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Sitemap & Routing — Retrieve nested sitemap trees or flat router architectures to understand how your channels are structured
Content Lists — Search, list, and count items across specific CMS references like articles, authors, or products
Page Layouts — Fetch exact page modules, UI components mapping, and structural layout definitions using Page IDs
Content Operations — Read full content payloads for individual items and synchronize granular CMS updates over time
Media Galleries — Fetch specific media asset groups and tracking galleries for imagery

The Agility CMS MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Agility CMS to OpenAI Agents SDK via MCP

Follow these steps to integrate the Agility CMS MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Agility CMS

Why Use OpenAI Agents SDK with the Agility CMS MCP Server

OpenAI Agents SDK provides unique advantages when paired with Agility CMS through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Agility CMS + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Agility CMS MCP Server delivers measurable value.

Automated workflows: build agents that query Agility CMS, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Agility CMS, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Agility CMS tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Agility CMS to resolve tickets, look up records, and update statuses without human intervention

Agility CMS MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Agility CMS to OpenAI Agents SDK via MCP:

count_reference_items

Get the total size/count of items in a specific Reference List

get_media_gallery

Retrieve a specific media gallery mapping containing photos

get_page_layout

Retrieve the layout and structural modules of a single Page

get_single_item

g., an article body) knowing its numeric content ID. Retrieve a single Agility CMS content item by its ID

get_site_flat_router

Retrieve the exact flat list of all CMS routes/pages

get_site_tree

Requires the target channel name. Retrieve the nested sitemap architecture of a digital channel

list_content_items

g. blog posts, articles, authors). The items are retrieved from the Headless CMS environment. List content items from an Agility CMS Reference list

search_content_reference

Search for specific keywords inside a Content Reference List

sync_incremental_items

Start with 0 for full backup. Get incrementally updated items since the last sync token

sync_incremental_pages

Start with 0 for a full fetch. Get incrementally updated pages since the last sync token

Example Prompts for Agility CMS in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Agility CMS immediately.

"Get the flat sitemap for our website to see all registered routes."

"Search the 'blog_posts' reference list for the keyword 'announcement'."

"Retrieve the full page layout and modules for page ID 12."

Troubleshooting Agility CMS MCP Server with OpenAI Agents SDK

Common issues when connecting Agility CMS to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Agility CMS + OpenAI Agents SDK FAQ

Common questions about integrating Agility CMS MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.