How to Use the Helpwise MCP in LangChain

Q: Can LangChain use Helpwise tools to send SMS and WhatsApp replies?

Yes, while the sendemail tool manages outgoing email, you can pull SMS and WhatsApp threads using listconversations. Your LangChain agent can draft responses for any channel connected to your shared mailboxes.

Build multi-step LangChain reasoning chains that manage Helpwise shared mailboxes and route customer emails automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Helpwise MCP to LangChain

Create your Vinkius account to connect Helpwise 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 Helpwise with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-step support workflows in LangChain

The `send_email` tool acts as the final action in a multi-step LangChain reasoning loop that handles customer queries without human intervention. Your agent starts by calling `list_conversations` to pull new threads, then passes the text to the next link in your chain to draft replies. You can track every tool call and latency metric inside LangSmith to see exactly how your agent handles support tickets. This means you know which steps of the chain took the longest to resolve a customer issue before sending the message.

Sync customer contacts across systems

The `create_contact` tool updates your Helpwise database directly from your LangChain agent's memory. Instead of manual data entry, your agent compares incoming email metadata against existing records using `list_contacts` to prevent duplicates. This setup lets you build chains that pull CRM data from other integrations and merge it directly into Helpwise. You get clean, updated profiles across all channels without writing custom integration glue code.

Smart assignment using this MCP Server

The `list_team_members` tool lets your agent inspect active support staff before routing a message. By querying `list_mailboxes` first, the LangChain agent decides which shared inbox should receive the conversation based on current team workloads. You get full visibility into these routing decisions through LangSmith tracing. If an agent routes a conversation to the wrong mailbox, you can drill down into the exact tool execution path to fix the prompt.

Setup guide

Set up Helpwise 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 Helpwise 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({
    "helpwise-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 Helpwise 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 Helpwise. 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 Helpwise 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 Helpwise MCP in LangChain

Instantiate the MultiServerMCPClient pointing to your Vinkius endpoint and call the get_tools function. Pass these tools directly into your create_agent configuration block to give your agent mailbox access.

Yes, while the send_email tool manages outgoing email, you can pull SMS and WhatsApp threads using list_conversations. Your LangChain agent can draft responses for any channel connected to your shared mailboxes.

You should configure your LangChain runnable chains with retry logic to handle rate limits on list_conversations calls. LangSmith will flag any throttled API calls so you can adjust your polling intervals.

Absolutely. Because this server exposes standard MCP tools, your LangChain agent can fetch customer data from a SQL database and then call create_contact in a single execution chain.

Your shared inbox emails and SMS logs never persist on Vinkius. The MCP Server executes in an isolated, zero-trust sandbox that handles your API tokens securely and streams raw data directly to your local LangChain runtime.

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