How to Use the Dub.co MCP in Google ADK

Q: How do I configure the Dub.co MCP Server within Google ADK?

Install the package using pip install google-adk and create an MCP toolset with McpToolset pointing to your Vinkius HTTP endpoint. Pass this toolset into your LlmAgent constructor to expose the link management tools.

Q: Can my Google ADK agent analyze Dub.co link performance alongside BigQuery data?

Yes, your Google ADK agent can call the getworkspaceanalytics tool to fetch live click data and join it with BigQuery datasets. This allows the Gemini model to generate real-time attribution reports directly in your console.

Q: Is it possible to limit Google ADK to read-only Dub.co tools?

Yes, you can pass a list of allowed tools to the toolnames parameter in StreamableHttpServerParameters when initializing Google ADK. This lets you block access to deleteshortlink while keeping tools like listlinks active.

Connect your enterprise Google ADK agents to Dub.co for real-time link creation and BigQuery-aligned analytics tracking.

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 Google ADK

Create your Vinkius account to connect Dub.co to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise link operations with Google ADK

The `create_short_link` tool gives your Google ADK agent the ability to register new marketing targets directly from your enterprise databases. When your data pipelines detect a high-performing product category, the Google ADK agent generates short links to distribute across ad networks. You set this up by passing `McpToolset` with your Vinkius server parameters to the Google ADK `LlmAgent`. The Google ADK agent uses the `list_links` tool to verify existing targets, avoiding duplicate link generation and saving database space.

Long-context analytics parsing via MCP Server

The `get_workspace_analytics` tool outputs raw performance metrics that Gemini models within Google ADK can analyze across long contexts. Because the Google ADK agent handles up to 1M tokens, your agent can ingest months of click data in a single turn to spot trends. This MCP Server integration allows your Google ADK agent to cross-reference Dub.co click data with your BigQuery marketing tables. The Google ADK agent reads the analytics, identifies underperforming paths, and updates them immediately with the `update_short_link` tool.

Automated tag and domain validation in Google ADK

The `list_domains` tool lets your Google ADK agent, acting as an MCP client, check your active custom domains before deploying any redirects. The Google ADK agent cross-references this with the `list_tags` tool to make sure every new link is categorized correctly under your corporate taxonomy. You can restrict tool access in Google ADK by using the `tool_names` filter parameter during initialization. This ensures your Google ADK agent can read meta-tags using `get_url_metatags` without having permission to execute deletions.

Setup guide

Set up Dub.co MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Dub.co tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Dub.co_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Dub.co tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install the package using `pip install google-adk` and create an MCP toolset with `McpToolset` pointing to your Vinkius HTTP endpoint. Pass this toolset into your `LlmAgent` constructor to expose the link management tools.

Yes, your Google ADK agent can call the `get_workspace_analytics` tool to fetch live click data and join it with BigQuery datasets. This allows the Gemini model to generate real-time attribution reports directly in your console.

Yes, you can pass a list of allowed tools to the `tool_names` parameter in `StreamableHttpServerParameters` when initializing Google ADK. This lets you block access to `delete_short_link` while keeping tools like `list_links` active.

Gemini models in Google ADK natively support massive token limits, meaning they can ingest the entire output of `list_links` and `get_workspace_analytics` without truncating data. This allows for deep, multi-turn analysis of your entire link portfolio.

Your API token is held securely in the Vinkius zero-trust vault and is never exposed to the Google Cloud runtime. The server handles all credentials at the gateway level, passing only sanitized JSON responses back to your agent.

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