How to Use the Help Scout MCP in LangChain

Q: Can a LangChain agent close a Help Scout ticket for me?

Yes. The agent can use the updateconvostatus tool with the status set to "closed". You build the logic in your chain to decide when a conversation is actually ready to be closed.

Q: What's the best way to search for Help Scout conversations with LangChain?

Use the searchconversations tool. Your LangChain agent can formulate the search query based on the user's request and then execute the search against your Help Scout data.

Build autonomous support agents for Help Scout using LangChain's composable chains and your Vinkius MCP endpoint.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Help Scout MCP to LangChain

Create your Vinkius account to connect Help Scout 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 Help Scout with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Tools for Ticket Triage

An agent can run `list_conversations` to find new tickets, then loop through them. For each one, it calls `get_conversation` to check the details and decides if it needs escalation. This isn't just a simple script. You're building a reasoning chain where the output of one tool becomes the input for the next. The agent can use `list_tags` to see available categories and then apply the right one based on the conversation content.

Give Agents Full Customer Context

Stop making your agents guess. Before drafting a reply, a chain can call `get_customer` to pull the full user profile. It can also run `list_customer_ratings` to see if they're a happy camper or a known detractor. This data directly informs the agent's next action, whether it's adding a private note with `create_convo_note` for a human teammate or changing the ticket status with `update_convo_status`. It's all part of the same execution flow.

Your Help Scout MCP Server in LangChain

This MCP Server exposes 12 Help Scout actions as callable tools. In LangChain, you just pass these tools to your agent constructor. The agent then decides which to call, and when. You can build agents that monitor specific mailboxes with `list_mailboxes`, assign tickets to the right person from `list_staff_users`, or even trigger complex internal processes with `list_workflows`. It's all managed through your Vinkius endpoint.

Setup guide

Set up Help Scout 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 Help Scout 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({
    "help-scout-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 Help Scout 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 Help Scout. 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 Help Scout 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 Help Scout MCP in LangChain

You don't connect them directly. You subscribe to this MCP server on Vinkius, get one endpoint token, and use the `langchain-mcp-adapters` library. Your LangChain agent calls Vinkius, and Vinkius securely handles the Help Scout connection.

Yes. The agent can use the `update_convo_status` tool with the status set to "closed". You build the logic in your chain to decide when a conversation is actually ready to be closed.

Use the `search_conversations` tool. Your LangChain agent can formulate the search query based on the user's request and then execute the search against your Help Scout data.

Absolutely. You can build a chain that gets Help Scout data, looks up related information in a SQL database, and then sends a Slack message. The Help Scout tools become just another component in your agent's toolkit.

Vinkius runs this server in an ephemeral sandbox. Your agent's requests, including conversation content and customer data, pass through Vinkius to Help Scout but are not stored. If you use LangSmith, traces of the tool calls—not the full data payloads—are logged for debugging.

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