How to integrate Short io MCP with LangChain

This guide walks you through connecting Short io to LangChain using the Composio tool router. By the end, you'll have a working Short io agent that can show click stats for your latest short links, list most popular short urls this month, get opengraph settings for a specific link through natural language commands. This guide will help you understand how to give your LangChain agent real control over a Short io account through Composio's Short io MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Short io logoShort io
Api Key

Short.io is a URL shortening service that lets you create and manage branded short links. Easily track link performance and analytics for every campaign.

41 Tools

Introduction

This guide walks you through connecting Short io to LangChain using the Composio tool router. By the end, you'll have a working Short io agent that can show click stats for your latest short links, list most popular short urls this month, get opengraph settings for a specific link through natural language commands.

This guide will help you understand how to give your LangChain agent real control over a Short io account through Composio's Short io MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Short io with

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Connect your Short io project to Composio
  • Create a Tool Router MCP session for Short io
  • Initialize an MCP client and retrieve Short io tools
  • Build a LangChain agent that can interact with Short io
  • Set up an interactive chat interface for testing

What is LangChain?

LangChain is a framework for developing applications powered by language models. It provides tools and abstractions for building agents that can reason, use tools, and maintain conversation context.

Key features include:

  • Agent Framework: Build agents that can use tools and make decisions
  • MCP Integration: Connect to external services through Model Context Protocol adapters
  • Memory Management: Maintain conversation history across interactions
  • Multi-Provider Support: Works with OpenAI, Anthropic, and other LLM providers

What is the Short io MCP server, and what's possible with it?

The Short io MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Short io account. It provides structured and secure access to your branded short links, so your agent can create and manage links, retrieve analytics, organize domains, and optimize your link campaigns automatically.

  • Automated branded link creation and management: Instantly generate new short links, fetch details, update metadata, and organize your links by domain—all on demand.
  • Comprehensive click analytics and statistics: Retrieve detailed click metrics for individual links or aggregated data by domain to track performance and measure engagement.
  • Popular path and traffic insights: Analyze the most visited short link paths in your domains over time to understand which content resonates with your audience.
  • Granular permissions and access control: Check and manage user permissions on links within your domains, ensuring secure collaboration and streamlined workflows.
  • Open Graph and targeting customization: Review and adjust Open Graph properties for better link previews and set up advanced targeting rules by region or country to maximize reach.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step10 STEPS
1

Prerequisites

Before starting this tutorial, make sure you have:
  • Python 3.10 or higher installed on your system
  • A Composio account with an API key
  • An OpenAI API key
  • Basic familiarity with Python and async programming
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install dependencies

npm install @composio/langchain @langchain/core @langchain/openai @langchain/mcp-adapters dotenv

Install the required packages for LangChain with MCP support.

What's happening:

  • @composio/langchain provides Composio integration for LangChain
  • @langchain/mcp-adapters enables MCP client connections
  • @langchain/core is the core agent framework
  • dotenv/config loads environment variables
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_composio_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your requests to Composio's API
  • COMPOSIO_USER_ID identifies the user for session management
  • OPENAI_API_KEY enables access to OpenAI's language models
5

Import dependencies

import { Composio } from '@composio/core';
import { LangchainProvider } from '@composio/langchain';
import { MultiServerMCPClient } from "@langchain/mcp-adapters";
import { createAgent } from "langchain";
import * as readline from 'readline';
import 'dotenv/config';

dotenv.config();
What's happening:
  • We're importing LangChain's MCP adapter and Composio SDK
  • The dotenv/config import loads environment variables from your .env file
  • This setup prepares the foundation for connecting LangChain with Short io functionality through MCP
6

Initialize Composio client

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.COMPOSIO_USER_ID;

if (!composioApiKey) throw new Error('COMPOSIO_API_KEY is not set');
if (!userId) throw new Error('COMPOSIO_USER_ID is not set');

async function main() {
    const composio = new Composio({
        apiKey: composioApiKey as string,
        provider: new LangchainProvider()
    });
What's happening:
  • We're loading the COMPOSIO_API_KEY from environment variables and validating it exists
  • Creating a Composio instance that will manage our connection to Short io tools
  • Validating that COMPOSIO_USER_ID is also set before proceeding
7

Create a Tool Router session

const session = await composio.create(
    userId as string,
    {
        toolkits: ['short_io']
    }
);

const url = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Short io tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use
  • This approach allows the agent to dynamically load and use Short io tools as needed
8

Configure the agent with the MCP URL

const client = new MultiServerMCPClient({
    "short_io-agent": {
        transport: "http",
        url: url,
        headers: {
            "x-api-key": process.env.COMPOSIO_API_KEY
        }
    }
});

const tools = await client.getTools();

const agent = createAgent({ model: "gpt-5", tools });
What's happening:
  • We're creating a MultiServerMCPClient that connects to our Short io MCP server via HTTP
  • The client is configured with a name and the URL from our Tool Router session
  • getTools() retrieves all available Short io tools that the agent can use
  • We're creating a LangChain agent using the GPT-5 model
9

Set up interactive chat interface

let conversationHistory: any[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log("Ask any Short io related question or task to the agent.\n");

const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: 'You: '
});

rl.prompt();

rl.on('line', async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (['exit', 'quit', 'bye'].includes(trimmedInput.toLowerCase())) {
        console.log("\nGoodbye!");
        rl.close();
        process.exit(0);
    }

    if (!trimmedInput) {
        rl.prompt();
        return;
    }

    conversationHistory.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    const response = await agent.invoke({ messages: conversationHistory });
    conversationHistory = response.messages;

    const finalResponse = response.messages[response.messages.length - 1]?.content;
    console.log(`Agent: ${finalResponse}\n`);
        
        rl.prompt();
    });

    rl.on('close', () => {
        console.log('\n👋 Session ended.');
        process.exit(0);
    });
What's happening:
  • We initialize an empty conversationHistory list to maintain context across interactions
  • A readline interface is used to continuously accept user input from the command line
  • When a user types a message, it's added to the conversation history and sent to the agent
  • The agent processes the request using the invoke() method with the full conversation history
  • Users can type 'exit', 'quit', or 'bye' to end the chat session gracefully
10

Run the application

main().catch((err) => {
    console.error('Fatal error:', err);
    process.exit(1);
});
What's happening:
  • We call the main() function to start the application

Complete Code

Here's the complete code to get you started with Short io and LangChain:

import { Composio } from '@composio/core';
import { LangchainProvider } from '@composio/langchain';
import { MultiServerMCPClient } from "@langchain/mcp-adapters";  
import { createAgent } from "langchain";
import * as readline from 'readline';
import 'dotenv/config';

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.COMPOSIO_USER_ID;

if (!composioApiKey) throw new Error('COMPOSIO_API_KEY is not set');
if (!userId) throw new Error('COMPOSIO_USER_ID is not set');

async function main() {
    const composio = new Composio({
        apiKey: composioApiKey as string,
        provider: new LangchainProvider()
    });

    const session = await composio.create(
        userId as string,
        {
            toolkits: ['short_io']
        }
    );

    const url = session.mcp.url;
    
    const client = new MultiServerMCPClient({
        "short_io-agent": {
            transport: "http",
            url: url,
            headers: {
                "x-api-key": process.env.COMPOSIO_API_KEY
            }
        }
    });
    
    const tools = await client.getTools();
  
    const agent = createAgent({ model: "gpt-5", tools });
    
    let conversationHistory: any[] = [];
    
    console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
    console.log("Ask any Short io related question or task to the agent.\n");
    
    const rl = readline.createInterface({
        input: process.stdin,
        output: process.stdout,
        prompt: 'You: '
    });

    rl.prompt();

    rl.on('line', async (userInput: string) => {
        const trimmedInput = userInput.trim();
        
        if (['exit', 'quit', 'bye'].includes(trimmedInput.toLowerCase())) {
            console.log("\nGoodbye!");
            rl.close();
            process.exit(0);
        }
        
        if (!trimmedInput) {
            rl.prompt();
            return;
        }
        
        conversationHistory.push({ role: "user", content: trimmedInput });
        console.log("\nAgent is thinking...\n");
        
        const response = await agent.invoke({ messages: conversationHistory });
        conversationHistory = response.messages;
        
        const finalResponse = response.messages[response.messages.length - 1]?.content;
        console.log(`Agent: ${finalResponse}\n`);
        
        rl.prompt();
    });

    rl.on('close', () => {
        console.log('\nSession ended.');
        process.exit(0);
    });
}

main().catch((err) => {
    console.error('Fatal error:', err);
    process.exit(1);
});

Conclusion

You've successfully built a LangChain agent that can interact with Short io through Composio's Tool Router.

Key features of this implementation:

  • Dynamic tool loading through Composio's Tool Router
  • Conversation history maintenance for context-aware responses
  • Async Python provides clean, efficient execution of agent workflows
You can extend this further by adding error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.
TOOLS

Supported Tools

Every Short io action and event your agent gets out of the box.

Add Tag to Links in Bulk

Tool to append a single tag to multiple short links in one call.

Archive Link

Archive a short link, hiding it from the dashboard while keeping it accessible.

Create Folder

Tool to create a new folder for organizing links within a domain.

Create Short Link

Tool to create a new short link from a long URL on your branded domain.

Delete Link

Tool to permanently delete a short link by its unique ID.

Delete Link Permission

Revokes a specific user's access permission for a short link.

Delete Links in Bulk

Delete multiple short links in a single API call (up to 150 links).

Duplicate Link

Tool to duplicate an existing short link by its ID.

Generate QR Code for Link

Tool to generate a QR code for a short link.

Get Bundle Templates

Tool to retrieve all available bundle templates.

Get Domain Details by ID

Tool to retrieve detailed information for a specific domain by its ID.

Get Domain Link Clicks

Tool to get click statistics for specific links in a domain.

Get Domain Paths

Tool to list the most popular paths in a domain over time.

Get Domain Statistics

Tool to get comprehensive statistics for a domain over a specified period.

Get Folder

Tool to retrieve folder details by ID.

Get Link by Original URL

Tool to get link info by original URL.

Get Link Countries

Tool to get country targeting rules for a short link.

Get Link Info by Link ID

Retrieves comprehensive metadata for a short link using its unique ID.

Get Link Info by Path

Tool to get link info by its path and domain.

Get Link OpenGraph Properties

Tool to retrieve OpenGraph settings for a link.

Get Link Permissions

Retrieves all user access permissions for a specific short link within a domain.

Get Link Regions by Country

Tool to list all regions available for a country.

Get Link Regions

Retrieves all region-based targeting rules configured for a specific short link.

Get Links by Original URL

Tool to get multiple links info by original URL.

Get Links List

Tool to list short links on a domain with optional filters.

Get Link Statistics

Tool to get click statistics for a specific link.

Get Link (Tweetbot)

Create a short link using the simplified Tweetbot GET endpoint.

List Domains

Tool to retrieve all domains associated with the Short.

List Folders

Tool to list all folders for a specific domain.

Post Domain Link Clicks

Tool to get click statistics for specific links in a domain using POST method.

Get Domain Statistics by Interval

Tool to retrieve domain statistics over a custom interval.

Post Domains Last Clicks

Tool to retrieve the latest raw click events for a domain.

Get Domain Statistics

Tool to get detailed statistics for a domain over a specified period.

Get Domain Top Values

Retrieves top values for a specified analytics column ranked by click count for a domain.

Archive Links in Bulk

Archive multiple short links in a single API call (up to 150 links).

Create Links in Bulk

Tool to create up to 1000 short links in one call.

Generate QR Codes in Bulk

Tool to generate QR codes for multiple links in bulk.

Unarchive Links in Bulk

Unarchive multiple short links in bulk (up to 150 links per request).

Unarchive Link

Unarchive a previously archived short link to restore it to active status.

Update Domain Settings

Tool to update domain settings for a Short.

Update Link

Tool to update an existing short link by its ID.

FAQ

Frequently asked questions

With a standalone Short io MCP server, the agents and LLMs can only access a fixed set of Short io tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Short io and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. LangChain fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Short io tools.

Yes, absolutely. You can configure which Short io scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Short io data and credentials are handled as safely as possible.

Start with Short io.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Short io tool your agent needs.Free to start.

Start building