How to Use the Freshworks MCP in LangChain

Q: How do I connect Freshworks to LangChain?

Install langchain-mcp-adapters and pass your server URL to MultiServerMCPClient. Call client.gettools() to expose the Freshworks endpoints to your agent.

Q: Can LangChain agents update Freshworks tickets?

The current tools support reading data via endpoints like getticket and listtickets. Your agents can retrieve and analyze the tickets, but you need a separate action tool to modify them.

Q: Does LangChain track my Freshworks API usage?

Yes. When your chain calls a tool like listdeals, LangSmith logs the exact input parameters and the response latency. You see exactly how much time the agent spends waiting for the CRM.

Q: Are my sales deals secure when the agent reads them?

The server processes raw JSON from listdeals entirely in memory. Vinkius isolates the execution in a V8 sandbox, meaning your pipeline values and account names disappear the moment the chain completes.

Build multi-step sales and support pipelines in LangChain. Your agents read tickets and update deals automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Freshworks MCP to LangChain

Create your Vinkius account to connect Freshworks 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 Freshworks with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect LangChain to Sales Deals via MCP Server

This MCP Server gives your LangChain agents direct access to `list_deals` and `list_accounts`. Instead of writing custom API wrappers, you drop the server URL into your chain and let the agent pull active pipeline data. It reads the current state of a negotiation and feeds that context into your next prompt. You can build a ReAct agent that spots a high-value account and immediately checks `list_crm_contacts` to find the right stakeholder. The output of the contact search becomes the input for your email generation step. You track every token and latency metric through LangSmith.

Automate Helpdesk Triage

Your agents use `list_tickets` and `get_ticket` to pull raw customer support requests straight from the queue. They read the complaint, categorize the severity, and decide what happens next. If a ticket mentions a billing issue, the agent routes it without human intervention. You combine these tools with `list_groups` to assign the ticket to the correct department. The chain evaluates the ticket text against your internal routing rules and picks the right support tier. Everything happens in a predictable, observable loop.

Sync Contacts Across Departments

The MCP tools expose `list_companies` and `list_helpdesk_contacts` to bridge the gap between your sales and support databases. Your LangGraph pipeline can poll the helpdesk for new users and check if they exist in the CRM. It stops duplicate records before they happen. A standard chain pulls a user from the support side and cross-references them against active accounts. If the agent finds a match, it flags the support ticket for the account manager. You define the logic, and the tools handle the data extraction.

Setup guide

Set up Freshworks 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 Freshworks 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({
    "freshworks-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 Freshworks 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 Freshworks. 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 Freshworks 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 Freshworks MCP in LangChain

Install `langchain-mcp-adapters` and pass your server URL to `MultiServerMCPClient`. Call `client.get_tools()` to expose the Freshworks endpoints to your agent.

The current tools support reading data via endpoints like `get_ticket` and `list_tickets`. Your agents can retrieve and analyze the tickets, but you need a separate action tool to modify them.

Yes. When your chain calls a tool like `list_deals`, LangSmith logs the exact input parameters and the response latency. You see exactly how much time the agent spends waiting for the CRM.

The server handles the raw API response. Your ReAct agent reads the returned payload and decides if it needs to request the next page based on the tool's output schema.

The server processes raw JSON from `list_deals` entirely in memory. Vinkius isolates the execution in a V8 sandbox, meaning your pipeline values and account names disappear the moment the chain completes.

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