How do I correctly generate a Contentstack Delivery Token?

Log into your core Contentstack account dashboard securely. Access the specific Stack you wish to query and navigate toward the technical 'Settings' header before clicking on 'Tokens'. Within this specific submenu, specifically select 'Delivery Tokens'. Generate a new one with an identifying name, assigning it distinctly to your intended 'Environment'. Note down the produced Token safely to input along with the matching Stack API key below.

Can the agent update entries or publish content directly to the CMS?

No. The integration exclusively relies upon Contentstack's globally distributed 'Delivery API' rather than their 'Management API', deliberately restricting operations to a secure read-only modality focused on retrieving already published entries, preventing accidental automated or unauthorized payload mutations from impacting live production data stores.

Do I need to type the exact environment name as it appears in Contentstack?

Yes, accuracy is strictly required. Providing the exact environment name (e.g., 'production' or 'staging') matching the internal naming correctly ensures the endpoint filters accurately out published iterations of records belonging only to those targeted distribution layers you are aiming specifically at querying reliably during chat prompts.

Contentstack MCP Server for OpenAI Agents SDK 9 tools — connect in under 2 minutes

Name: Contentstack
Availability: InStock
Author: Vinkius

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

Built by Vinkius GDPR 9 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Contentstack 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="Contentstack Assistant",
            instructions=(
                "You help users interact with Contentstack. "
                "You have access to 9 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Contentstack"
        )
        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 Contentstack MCP Server

Empower your conversational AI with secure and instant read access to your Contentstack headless CMS. Utilizing the Contentstack Delivery API, your agent can efficiently fetch published entries, retrieve asset URLs, and audit content type schema structures in real-time.

The OpenAI Agents SDK auto-discovers all 9 tools from Contentstack through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Contentstack, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Entry Retrieval — Instruct the agent to query and read live content entries by searching for specific title tags or matching query filters.
Asset Discovery — Request exact URLs from the media library to find specific images, PDFs, or files needed in your conversational context.
Schema Inspections — Ask for a detailed structural breakdown of any Content Type before utilizing it in an external application.

The Contentstack MCP Server exposes 9 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 Contentstack to OpenAI Agents SDK via MCP

Follow these steps to integrate the Contentstack 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 9 tools from Contentstack

Why Use OpenAI Agents SDK with the Contentstack MCP Server

OpenAI Agents SDK provides unique advantages when paired with Contentstack 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

Contentstack + OpenAI Agents SDK Use Cases

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

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

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

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

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

Contentstack MCP Tools for OpenAI Agents SDK (9)

These 9 tools become available when you connect Contentstack to OpenAI Agents SDK via MCP:

get_asset_details

Get details for a specific asset

get_content_type_details

Get the schema for a specific content type

get_entry

Get detailed content for a specific entry

get_stack_summary

Get high-level metadata about the current stack

list_assets

List all published assets

list_content_types

List all content types in the stack

list_entries

List published entries for a specific content type

search_entries

Search for entries using a JSON query

sync_content

Retrieve delta of changes since last sync

Example Prompts for Contentstack in OpenAI Agents SDK

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

"Retrieve the published blog post entry with the title 'Future Trends in AI' from our primary environment."

"Describe the content model schema required for 'Hero Banner' items in my stack."

"List the most recent image assets uploaded to our Contentstack library."

Troubleshooting Contentstack MCP Server with OpenAI Agents SDK

Common issues when connecting Contentstack 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.

Contentstack + OpenAI Agents SDK FAQ

Common questions about integrating Contentstack 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.