SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Freshservice MCP with LangChain

Connect LangChain to Freshservice MCP. List all open tickets in freshservice, create a new incident ticket for laptop issue, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Freshservice logoFreshservice
Api Key

Freshservice is a cloud-based IT service management (ITSM) platform for incident, asset, and service desk operations. Streamline your IT support with automation and centralized control.

20 Tools

Introduction

This guide walks you through connecting Freshservice to LangChain using the Composio tool router. By the end, you'll have a working Freshservice agent that can create tickets and service requests, list and bulk update tickets, browse the service catalog, and clean up old solution articles through natural language commands.

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

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

Also integrate Freshservice with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKVercel AI SDKMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Connect your Freshservice project to Composio
  • Create a Tool Router MCP session for Freshservice
  • Initialize an MCP client and retrieve Freshservice tools
  • Build a LangChain agent that can interact with Freshservice
  • 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 Freshservice MCP server, and what's possible with it?

The Freshservice MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Freshservice account. It provides structured and secure access to tickets, service catalog items, locations, and form fields, so your agent can create tickets, retrieve ticket details, update multiple tickets, submit service requests, and list locations on your behalf.

  • Ticket creation and tracking: Have your agent create new support tickets, list existing tickets, or retrieve the details of a specific ticket.
  • Bulk ticket updates: Direct your agent to update multiple Freshservice tickets when priorities, statuses, or other ticket details need to change.
  • Service catalog requests: Let the agent browse available service catalog items and submit a service request for the item you need.
  • Location and form field lookup: Instruct your agent to list Freshservice locations or retrieve the available fields for problem and release forms.
  • Release and knowledge base cleanup: Have your agent delete releases, solution articles, or solution categories that are no longer needed.

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 Freshservice 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 Freshservice 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: ['freshservice']
    }
);

const url = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Freshservice 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 Freshservice tools as needed
8

Configure the agent with the MCP URL

const client = new MultiServerMCPClient({
    "freshservice-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 Freshservice MCP server via HTTP
  • The client is configured with a name and the URL from our Tool Router session
  • getTools() retrieves all available Freshservice 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 Freshservice 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 Freshservice 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: ['freshservice']
        }
    );

    const url = session.mcp.url;
    
    const client = new MultiServerMCPClient({
        "freshservice-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 Freshservice 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 Freshservice 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 Freshservice action and event your agent gets out of the box.

Bulk Update Tickets

Updates the same supplied fields on multiple Freshservice tickets identified by ID, using sequential requests.

Create Service Request

Create a service request for a catalog item in Freshservice using the v2 API.

Create Ticket

Create a new Freshservice ticket to log an incident.

Delete Release

Deletes a release from Freshservice.

Delete Solution Article

Deletes a Freshservice knowledge base solution article by ID, moving it to Trash where it can be restored.

Delete Solution Category

Deletes a Freshservice solution category, moving it and its associated folders and articles to Trash.

Get Freshservice Agent

Retrieve one Freshservice support agent profile by its numeric user ID.

Get Problem Form Fields by Workspace

Lists Freshservice problem form field definitions for a specified workspace.

List Release Form Fields

Lists Freshservice release form field definitions for building or validating release forms.

Get Freshservice Requester

Retrieve one Freshservice requester profile by its numeric user ID.

Get Service Catalog Item

Retrieve a service catalog item's details and request form by display ID.

Get Freshservice Ticket

Retrieve a specific Freshservice ticket by ID, including its status, priority, requester ID, and other supported attributes.

List Freshservice Agents

Return Freshservice support agents page by page.

List Freshservice Locations

Lists a page of Freshservice locations, with a choice of page number and page size.

List Project Tasks

Return a page of tasks belonging to one Freshservice project.

List Service Catalog Items

Requests a page of Freshservice service catalog items to help identify items and their display IDs for service requests.

List Ticket Approvals

Return approvals and their current participants for a service request.

List Ticket Conversations

Return a page of replies and notes on one Freshservice ticket.

List Freshservice Tickets

List Freshservice tickets with optional predefined filtering and pagination; on accounts with workspaces, results are limited to the primary workspace.

Search Tickets

Search Freshservice tickets using the provider's filter expression syntax.

FRAMEWORKS

How to build Freshservice MCP Agent with another framework

Claude Code logo

Claude Code

Use Freshservice MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Freshservice MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Freshservice MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Freshservice MCP with Claude Agent SDK

Codex logo

Codex

Use Freshservice MCP with Codex

OpenClaw logo

OpenClaw

Use Freshservice MCP with OpenClaw

Hermes logo

Hermes

Use Freshservice MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Freshservice MCP with Atomic Agent

Google ADK logo

Google ADK

Use Freshservice MCP with Google ADK

Vercel AI SDK logo

Vercel AI SDK

Use Freshservice MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Freshservice MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Freshservice MCP with LlamaIndex

CrewAI logo

CrewAI

Use Freshservice MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Freshservice MCP with Pydantic AI

AutoGen logo

AutoGen

Use Freshservice MCP with AutoGen

FAQ

Frequently asked questions

With a standalone Freshservice MCP server, the agents and LLMs can only access a fixed set of Freshservice tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Freshservice 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 Freshservice tools.

Yes, absolutely. You can configure which Freshservice 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 Freshservice data and credentials are handled as safely as possible.

Start with Freshservice.It takes 30 seconds.

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

Start building