How to Use the MasterGo MCP in OpenAI Agents SDK

Q: How do I connect the OpenAI Agents SDK to MasterGo?

You instantiate an MCPServerStreamableHttp client with your Vinkius endpoint URL. Pass that server instance into your Agent's constructor. The SDK discovers all the MasterGo tools automatically.

Q: Can my OpenAI agent find specific design components in MasterGo?

Yes. Your agent can use the listnodes tool to get a flat list of all layers on a canvas. You can then instruct it to filter that list to find components, frames, or any other node type you need.

Q: What's the best way to get all comments from a MasterGo file with the OpenAI Agents SDK?

The getcomments tool is what you need. Your agent can call it with a file key to get every comment thread. It's useful for summarizing feedback or creating tasks from design reviews.

Build production-ready design agents for MasterGo with the OpenAI Agents SDK. Safe, traceable, and ready for your users.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MasterGo MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Automated Design Audits

Connect your OpenAI Agent to MasterGo and start auditing design files instantly. Your agent can pull a complete inventory of a project using `list_projects` and `get_project_files`, then dig into specific canvases. It's perfect for checking design system compliance across dozens of files without manual work. Because the OpenAI SDK has built-in guardrails, you can safely let your agent check for issues. It can use `list_nodes` to find every component instance and `list_styles` to verify color and text styles match your tokens. The agent can also pull existing feedback with `get_comments` to see what's already been flagged.

Keep Your Team and Files in Sync

Give your agent the job of managing project history and team access. It can fetch the entire version history of a file with `get_file_versions` to create a changelog or to find out when a specific change was made. This is way faster than clicking through the UI. You can also build an agent to report on user access. Use `list_teams` and `get_org_members` to generate reports on who has access to what. The agent can't change permissions, but it gives you a clear picture for security audits.

Generate Design System Reports with your MCP Server

Your agent can become a dedicated design system librarian. Point it at a MasterGo file and have it document everything. It will use `get_file` to get metadata and then `list_styles` to export every color, font, and effect. This isn't just a simple export. Because you're using an agent, it can cross-reference styles with component usage from `list_nodes`. You get a report that shows not just what your styles are, but where they're actually being used—or not used. It's a solid way to find and clean up unused design tokens.

Setup guide

Set up MasterGo 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 MasterGo tools at runtime.
3

Create your Agent

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

Run the agent

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

You instantiate an `MCPServerStreamableHttp` client with your Vinkius endpoint URL. Pass that server instance into your Agent's constructor. The SDK discovers all the MasterGo tools automatically.

Yes. Your agent can use the `list_nodes` tool to get a flat list of all layers on a canvas. You can then instruct it to filter that list to find components, frames, or any other node type you need.

The `get_comments` tool is what you need. Your agent can call it with a file key to get every comment thread. It's useful for summarizing feedback or creating tasks from design reviews.

No, this MCP server provides read-only access. Your agent can get data with tools like `get_file` and `list_nodes`, but it cannot change the design file itself. This is a safety feature.

The server only accesses the data your agent explicitly requests. This includes design file content, node structures, comments, project lists, and team member information. Your Vinkius token is the only credential needed, and all operations are logged.

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