How to Use the Makeswift MCP in OpenAI Agents SDK

Q: Can the OpenAI Agents SDK read Makeswift site metadata?

Yes. Your agent runs getsitedetails to pull the active workspace configuration. It can also grab the exact domains tied to the site using listhostnames.

Q: How does the system know which React components to use?

The agent hits the listcomponents endpoint. This returns the exact schema for every registered component so it formats content correctly before insertion.

Connect Makeswift to the OpenAI Agents SDK and let your agents manage Next.js visual content directly in production.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Makeswift MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map out Makeswift pages with OpenAI Agents SDK

Your OpenAI agent needs to understand the site architecture before making changes. It calls `list_pages` to pull down every active Next.js route, mapping out the exact path structures. If you run multiple regions, the agent can immediately follow up with `list_locales` to check language configurations. This setup prevents blind updates. Because the SDK enforces strict tool validation, your agent will not try to edit a missing page. It verifies the target exists using `get_page` and confirms the current routing logic via `list_redirects` before touching any content.

Inspect registered Next.js components

Marketers rely on predefined UI blocks, and your agent needs to know exactly what blocks are available. By executing `list_components`, the MCP server returns the exact props and constraints for every registered React component in your workspace. Handoffs work perfectly here. A discovery agent can map out the available components and pass that schema to a dedicated content-writing agent. They use the precise component definitions to draft content that actually fits your layout parameters.

Trigger visual backups via MCP Server

Pushing changes directly to a live site is dangerous. Your agent handles this by running `create_snapshot` to capture the exact layout state before altering anything. If something breaks, the rollback point is already saved. You can track these backups through the OpenAI dashboard tracing. The agent verifies the backup succeeded by querying `get_snapshot` or scanning the full history with `list_snapshots`. It gives your team a clear audit trail of every automated edit.

Setup guide

Set up Makeswift 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 Makeswift tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package via pip. You instantiate an MCP Server with your endpoint URL and pass it to the `mcp_servers` array in your Agent constructor. Set `cacheToolsList=True` to speed up tool discovery.

Yes. Your agent runs `get_site_details` to pull the active workspace configuration. It can also grab the exact domains tied to the site using `list_hostnames`.

It works out of the box. You can configure one agent to read site structure with `list_pages` and hand off the results to a specialized editing agent. The MCP tools are available across your entire network.

The agent hits the `list_components` endpoint. This returns the exact schema for every registered component so it formats content correctly before insertion.

This integration strictly reads and writes Next.js layout structures, page copy, and component props. The MCP Server runs inside an isolated environment, meaning your agent only accesses the specific visual content you expose through the endpoint token.

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