How to Use the Dub.co MCP in LangChain

Q: Can a LangChain ReAct agent use Dub.co to create and update links in one run?

Yes, the agent uses createshortlink first, reads the response, and can immediately run updateshortlink to modify the destination URL or tags. LangChain manages this loop using the tool definitions we provide automatically.

Q: How does LangSmith trace Dub.co analytics tools?

Every time your agent calls getworkspaceanalytics, LangSmith logs the input parameters, execution latency, and JSON payload. You get complete visibility into how much data your model is pulling from your dashboard.

Get your LangChain agents to spin up, trace, and analyze short links without leaving your python execution chains.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run sequential link pipelines in LangChain

`create_short_link` lets your ReAct agents build redirection pathways during live execution runs. The output gets passed directly to the next chain link, letting you generate custom URLs on the fly based on dynamic user actions. We feed these runtime variables straight into LangGraph nodes so your agent can react to link generation failures. You get raw JSON responses back, making it easy to parse the short URL and send it to your downstream messaging chains.

Track workspace metrics inside LangSmith tracing

`get_workspace_analytics` retrieves raw performance data that you can pipe directly into your LangSmith observability dashboard. This lets you track API latency, token overhead, and click metrics in a single, unified execution graph. Your agent analyzes traffic spikes by pulling real-time click data during specific pipeline runs. You see exactly which chain step triggered the analytics call and how the model interpreted the traffic trends.

Automate domain routing via this MCP Server

`list_domains` gives your LangChain agent a clean array of verified domains to select from before deploying a new campaign link. The agent checks the list, picks the right brand domain, and passes it to the next tool in the sequence. This setup eliminates hardcoded domain values in your python codebase. Your chains dynamically adjust to whatever domains are active in your dashboard, keeping your automated routing logic clean and modular.

Setup guide

Set up Dub.co MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Dub.co tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "dubco-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Dub.co transactions"
    })
    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 LangChain

You configure your credentials in the Vinkius platform, which exposes the Dub.co tools to your LangChain setup via a single secure endpoint. Your local python code just calls MultiServerMCPClient and doesn't store any raw tokens.

Yes, the agent uses `create_short_link` first, reads the response, and can immediately run `update_short_link` to modify the destination URL or tags. LangChain manages this loop using the tool definitions we provide automatically.

Every time your agent calls `get_workspace_analytics`, LangSmith logs the input parameters, execution latency, and JSON payload. You get complete visibility into how much data your model is pulling from your dashboard.

It does. You can combine this server with database or CRM servers in a single MultiServerMCPClient instance, letting your agent fetch customer data from one source and generate a personalized link with `create_short_link` in the next step.

The server runs in an isolated V8 sandbox on Vinkius and only accesses the specific workspace ID you define. Your link data, analytics click logs, and domain configurations are encrypted in transit and never stored on our host platform.

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