How to Use the Dub.co MCP in OpenAI Agents SDK

Q: How do I add the Dub.co MCP Server to my OpenAI Agents SDK project?

Install the packages with pip install openai-agents and initialize the MCP server using MCPServerStreamableHttp. Pass the server object inside the mcpservers list to your Agent constructor to let it auto-discover your link tools.

Q: Can my OpenAI Agents SDK agent update existing Dub.co links?

Yes, your OpenAI Agents SDK agent uses the updateshortlink tool to modify destinations or change UTM parameters. You can set up guardrails in the SDK to inspect and validate the new URL before the agent executes the update.

Spin up production-grade OpenAI Agents SDK systems that instantly control your Dub.co short links and track redirect performance.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dub.co MCP to OpenAI Agents SDK

Create your Vinkius account to connect Dub.co 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 Dub.co with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated link generation with OpenAI Agents SDK

The `create_short_link` tool lets your OpenAI Agents SDK agent deploy new redirection targets on the fly without manual dashboard work. When a user creates a campaign in your app, the OpenAI Agents SDK agent registers the destination, sets up UTM parameters, and returns the short URL instantly. You configure this by adding an MCP server to your OpenAI Agents SDK setup using `MCPServerStreamableHttp`. Setting `cacheToolsList=True` keeps your OpenAI Agents SDK agent fast, ensuring it does not waste API latency on redundant tool discovery passes when generating thousands of links.

Deep workspace analytics for OpenAI Agents SDK

The `get_workspace_analytics` tool feeds live performance data directly into your OpenAI Agents SDK agent's reasoning loop. Your OpenAI Agents SDK agent checks click counts, geographic distributions, and referrer data to make immediate campaign optimization decisions. This MCP Server runs inside Vinkius's isolated sandbox, meaning your workspace analytics remain secure. The OpenAI Agents SDK agent requests data, evaluates the performance metrics, and updates poor performers using the `update_short_link` tool without human intervention.

Safe domain management in OpenAI Agents SDK

The `list_domains` tool allows specialized domain-monitoring MCP agents to verify active routing rules before launching new links. If a domain is missing, the OpenAI Agents SDK agent hands off the task to a system administrator agent to prevent broken redirects. We write these guardrails directly into the OpenAI Agents SDK agent definitions. Your agent uses `list_tags` to organize links dynamically, keeping your workspace clean while enforcing safety rules at the SDK layer.

Setup guide

Set up Dub.co 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 Dub.co tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the packages with `pip install openai-agents` and initialize the MCP server using `MCPServerStreamableHttp`. Pass the server object inside the `mcp_servers` list to your Agent constructor to let it auto-discover your link tools.

Yes, your OpenAI Agents SDK agent uses the `update_short_link` tool to modify destinations or change UTM parameters. You can set up guardrails in the SDK to inspect and validate the new URL before the agent executes the update.

The OpenAI Agents SDK relies on standard HTTP error responses from the server, but you can build retry logic inside your agent's execution loop. The `get_workspace_analytics` tool handles the heavy lifting of pulling the raw data from your workspace.

You control tool exposure by configuring the server stream or filtering the discovered tools inside your Python initialization code. This prevents the agent from calling destructive tools like `delete_short_link` if you only want it to read analytics.

Vinkius runs the server in an ephemeral V8 sandbox that never persists your Dub.co API tokens or redirect logs. All data transit is zero-trust, meaning your workspace ID and API secrets are strictly isolated from other tenant environments.

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