4,500+ servers built on MCP Fusion
Vinkius
ArcXP logo
Vinkius
OpenAI Agents SDK logo

How to Use the ArcXP MCP in OpenAI Agents SDK

Build production-ready ArcXP publishing agents with the OpenAI Agents SDK. Manage your newsroom content with built-in safety checks.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

ArcXP MCP on Cursor AI Code Editor MCP Client ArcXP MCP on Claude Desktop App MCP Integration ArcXP MCP on OpenAI Agents SDK MCP Compatible ArcXP MCP on Visual Studio Code MCP Extension Client ArcXP MCP on GitHub Copilot AI Agent MCP Integration ArcXP MCP on Google Gemini AI MCP Integration ArcXP MCP on Lovable AI Development MCP Client ArcXP MCP on Mistral AI Agents MCP Compatible ArcXP MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
OpenAI Agents SDK

Connect ArcXP MCP to OpenAI Agents SDK

Create your Vinkius account to connect ArcXP 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

Manage Your Entire Content Lifecycle

This MCP Server gives your agent direct control over the ArcXP CMS. You can create, update, and fetch articles using `create_ans_content`, `update_ans_content`, and `get_ans_content`. It's not just text, either — the server includes tools for managing media assets like `get_photo_asset` and `get_video_asset`. The OpenAI Agents SDK automatically discovers these tools. You just point it at the server endpoint. Its guardrails are critical here, especially before calling a destructive tool like `delete_ans_content`, giving you a chance to require human approval before an agent deletes a live article.

Search and Discover Assets with Your OpenAI Agent

Stop digging through the ArcXP UI. Give your agent the `search_ans_content` tool to find articles based on keywords or other criteria. It can also find specific media with `search_photo_assets` or look up author profiles with `get_content_author`. This works great for building specialized agents. For example, one agent could be responsible for finding relevant photos for a draft article written by another. The SDK's handoff feature lets them collaborate, passing ArcXP content IDs between them.

Production-Grade Newsroom Automation

This isn't for one-off scripts. It's for building systems that run your publishing workflow. Your agent can ingest a draft from another source, create the story in ArcXP with `create_ans_content`, find and attach a photo with `search_photo_assets`, and then stage it for an editor. The full tracing in the OpenAI dashboard is key. You see every tool call your agent makes to the ArcXP MCP Server, including the exact ANS JSON payloads. This makes debugging complex agent interactions much simpler when you're trying to figure out why a story didn't publish correctly.

Setup guide

Set up ArcXP 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. 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. 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 ArcXP tools at runtime.

  3. 3

    Create your Agent

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

  4. 4

    Run the agent

    Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate ArcXP 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="ArcXP Agent",
            instructions="You have access to ArcXP tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by ArcXP. 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.

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 ArcXP MCP in OpenAI Agents SDK

It connects through this Vinkius-managed MCP Server. You instantiate an `MCPServerStreamableHttp` object with the server URL and pass it to your Agent constructor. The SDK then auto-discovers all the ArcXP tools.
Yes. While the SDK discovers all tools, you can implement custom logic or use the built-in guardrails to restrict which tools an agent can execute. This is essential for preventing accidental use of `delete_ans_content`.
The main benefit is the agentic framework. Instead of writing procedural code, you give the agent a goal, and it decides which ArcXP tools to use. The guardrails and tracing provide a safety and observability layer you'd have to build yourself otherwise.
No, the tool definitions on the MCP server are clear enough for the agent to understand what data to send. For `create_ans_content`, the agent knows it needs to construct a valid ANS JSON payload to create a new story.
Your agent's requests go through Vinkius's ephemeral, zero-trust sandbox to the ArcXP server. Vinkius handles the authentication token, but it never stores your actual content data, like article text or photo assets. The connection is stateless and logs are purged.

Start using the ArcXP MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 10 tools

We've already built the connector for ArcXP. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 10 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.