How to Use the Dub.co MCP in AutoGen

Q: How do I register Dub.co tools with my AutoGen assistant?

You use the mcpservertools helper to fetch the tool definitions from the Vinkius endpoint. Pass this list to your AssistantAgent constructor to give your agents instant access to your link management suite.

Q: Can AutoGen agents modify Dub.co links autonomously?

Yes, you can authorize agents to run updateshortlink after they complete their internal review loop. They can alter destination URLs or update tags based on the rules you write in their system prompts.

Q: How do AutoGen agents resolve conflicts when managing Dub.co domains?

When calling listdomains, one agent might prefer a brand domain while another flags a restriction. They debate the options in the chat thread and only execute the tool once they reach a programmatic agreement.

Let your AutoGen agents debate and optimize your Dub.co redirection campaigns autonomously.

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 AutoGen

Create your Vinkius account to connect Dub.co to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run consensus-driven link creation in AutoGen

`create_short_link` executes only after your marketing agent and your security agent agree on the target URL and UTM parameters. AutoGen manages this debate, ensuring no unverified links get created in your workspace. Once the agents reach a consensus, the tool generates the short URL and returns the JSON payload. This automated check stops broken or malicious links from ever reaching your production domains.

Debating campaign performance using Dub.co analytics

`get_workspace_analytics` feeds raw click and conversion metrics directly into your agent conversation threads. A performance agent reviews the data, while a budget agent analyzes costs, allowing them to debate your next marketing move. The agents use this tool to pull real-time performance updates. They write their optimization recommendations directly back to your team, backed by hard dashboard metrics.

Manage workspace tags via this MCP Server

`list_tags` allows your AutoGen agents to organize your tracking links into clean, searchable categories. The agents query your existing tag structure to ensure new links match your team's naming conventions. If a tag is missing, the agents flag the discrepancy in their chat feed. This keeps your dashboard clean and prevents duplicate or messy tag configurations across large marketing efforts.

Setup guide

Set up Dub.co MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Dub.co tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Dub.co_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Dub.co data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Dub.co_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Dub.co data")
    print(result.messages[-1].content)

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 AutoGen

You use the `mcp_server_tools` helper to fetch the tool definitions from the Vinkius endpoint. Pass this list to your AssistantAgent constructor to give your agents instant access to your link management suite.

Yes, you can authorize agents to run `update_short_link` after they complete their internal review loop. They can alter destination URLs or update tags based on the rules you write in their system prompts.

When calling `list_domains`, one agent might prefer a brand domain while another flags a restriction. They debate the options in the chat thread and only execute the tool once they reach a programmatic agreement.

Yes, the server handles parallel requests, allowing multiple agents to query tools like `get_url_metatags` and `get_link_details` at the same time during a multi-turn conversation.

The server only processes the short link configurations, domain lists, and aggregate analytics you authorize. It runs in an ephemeral, zero-trust sandbox, meaning your API tokens and raw tracking metrics are never exposed or stored.

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