How to Use the Help Scout MCP in LlamaIndex

Q: How do I use Help Scout tools inside a LlamaIndex query engine?

After installing llama-index-tools-mcp, you create a BasicMCPClient pointing to your Vinkius URL. Then, you use McpToolSpec to generate a list of tools that you pass directly to your LlamaIndex agent.

Q: Can LlamaIndex agents update Help Scout tickets?

Yes. The agent has access to updateconvostatus to change a ticket's state and createconvonote to add internal comments. Your agent logic determines when to use these tools.

Q: What's the difference between searchconversations and indexing in LlamaIndex for Help Scout?

searchconversations is a direct keyword search on Help Scout's servers. Building a LlamaIndex index lets you perform semantic searches on conversation data you've already fetched, finding conceptually similar tickets even if the keywords don't match.

Q: Does this work with both async and sync LlamaIndex code?

Yes. The tool spec provides both totoollist() for synchronous use and totoollistasync() for asynchronous applications.

Ground your LlamaIndex RAG apps in live Help Scout data. Turn support history into a queryable knowledge base.

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 LlamaIndex

Create your Vinkius account to connect Help Scout to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Conversations for Smarter RAG

Use the `McpToolSpec` to load all 12 Help Scout tools. Your LlamaIndex agent can now call `list_conversations` and `get_conversation` to fetch ticket history. This isn't just for one-off lookups. LlamaIndex turns the results of these tool calls into indexed objects. Your agent can then perform semantic searches over past support interactions to find relevant solutions for new, incoming questions. It's building a brain from your own data.

Enrich Queries with Live Customer Data

When a query comes in, your agent doesn't have to operate blind. It can use the `get_customer` tool to fetch the user's profile from Help Scout in real time. It sees their history, status, and even recent feedback via `list_customer_ratings`. This context is automatically injected into the prompt, giving the LLM a much better shot at providing a useful, personalized answer. The agent can even use `search_conversations` to find that specific customer's past tickets.

Build a Fact-Based Help Scout MCP Server

An agent built with this MCP Server and LlamaIndex answers questions based on actual data, not just its training set. It can list available mailboxes with `list_mailboxes` or check support staff with `list_staff_users`. You're building a system that can answer "Who is handling tickets for the sales mailbox?" by actually checking, right now. This MCP connection gives your agent the tools to find facts and ground its responses.

Setup guide

Set up Help Scout MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Help Scout MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Help Scout tools.",
)
response = await agent.run("List recent Help Scout data")

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 LlamaIndex

After installing `llama-index-tools-mcp`, you create a `BasicMCPClient` pointing to your Vinkius URL. Then, you use `McpToolSpec` to generate a list of tools that you pass directly to your LlamaIndex agent.

Yes. The agent has access to `update_convo_status` to change a ticket's state and `create_convo_note` to add internal comments. Your agent logic determines when to use these tools.

`search_conversations` is a direct keyword search on Help Scout's servers. Building a LlamaIndex index lets you perform semantic searches on conversation data you've already fetched, finding conceptually similar tickets even if the keywords don't match.

Yes. The tool spec provides both `to_tool_list()` for synchronous use and `to_tool_list_async()` for asynchronous applications.

The MCP server itself is ephemeral; it doesn't store your data. When LlamaIndex ingests data like customer profiles or conversation text to create an index, that data lives in your chosen vector store. You are responsible for securing that index.

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