How to Use the Capsulink MCP in LangChain

Q: How do I use Capsulink with LangChain via MCP?

Install langchain-mcp-adapters. Setup a MultiServerMCPClient pointing to the Vinkius URL, then pass the tools to createagent.

Q: Can LangChain agents edit Capsulink destinations automatically?

Yes. The agent calls editlinkdestination with the link ID and new target URL. You control the logic determining when that swap happens.

Q: How do I track Capsulink click stats in a LangChain pipeline?

Give the agent access to getlinkdailystats. It pulls the breakdown and passes the JSON output to the next step in your chain.

Build multi-step reasoning chains that create, route, and track Capsulink short URLs directly through your LangChain agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Capsulink MCP to LangChain

Create your Vinkius account to connect Capsulink 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 Capsulink with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

LangChain routing for link management

The `shorten_url` and `edit_link_destination` MCP tools let your ReAct agents manipulate redirects on the fly. You feed a long destination URL into a chain, and the agent decides if it needs a new short link or an update to an existing one based on context. This removes manual link updates from your workflow. A script can pull a new article URL, pass it to the agent, and have the agent swap out the destination of your main promotional link without human intervention.

Chain-driven analytics tracking

Agents extract click metrics mid-chain using the `get_link_stats` and `get_link_daily_stats` tools. Your pipeline grabs the raw click data, processes it, and decides the next action based on traffic volume. If a specific campaign drops below a threshold, the agent spots it immediately. It can then trigger a downstream tool to alert your marketing Slack channel or pause a related ad spend.

Account auditing via LangSmith

Running `get_account_info` or `list_links` through this MCP Server gives your agents full visibility into your link infrastructure. Every token spent and API call made gets logged in LangSmith for debugging. You track exactly why an agent chose to call `delete_link` on an old URL. The trace shows the exact inputs and outputs, so you never guess how a decision happened.

Setup guide

Set up Capsulink 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 Capsulink 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({
    "capsulink-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 Capsulink 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 Capsulink. 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 Capsulink 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 Capsulink MCP in LangChain

Install `langchain-mcp-adapters`. Setup a `MultiServerMCPClient` pointing to the Vinkius URL, then pass the tools to `create_agent`.

Yes. The agent calls `edit_link_destination` with the link ID and new target URL. You control the logic determining when that swap happens.

Give the agent access to `get_link_daily_stats`. It pulls the breakdown and passes the JSON output to the next step in your chain.

You need a separate client instance for each account. The multi-server aggregation handles routing between them if you pass distinct endpoints.

The tools expose destination URLs, click timestamps, and folder names. Vinkius runs the server in a V8 Isolate Sandbox, meaning those link metrics disappear the moment the session ends.

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