How do I get my Help Scout Access Token?

You can generate an OAuth2 Access Token by creating an application in the **Help Scout Developer Portal** (developer.helpscout.com). Alternatively, if you are using a personal script, you can use the Client Credentials flow to obtain a token.

Can I add internal notes to conversations?

Yes! Use the `create_convo_note` tool. You must provide the `conversation_id` and the text of your note. This allows you to collaborate with your team without the customer seeing the message.

How do I change the status of a support thread?

Use the `update_convo_status` tool. Provide the conversation ID and the new status (active, pending, or closed). This helps you keep your mailbox organized.

Is the integration secure for managing support data?

Absolutely. The integration uses industry-standard OAuth 2.0 Bearer tokens over HTTPS. Your credentials are encrypted and stored securely within the Vinkius Cloud infrastructure.

Help Scout MCP Server for OpenAI Agents SDK 12 tools — connect in under 2 minutes

Name: Help Scout
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 12 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Help Scout through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Help Scout Assistant",
            instructions=(
                "You help users interact with Help Scout. "
                "You have access to 12 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Help Scout"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Help Scout MCP Server

Connect your Help Scout help desk to any AI agent and take full control of your customer communication and support operations through natural conversation.

The OpenAI Agents SDK auto-discovers all 12 tools from Help Scout through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Help Scout, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Conversation Oversight — List all active support threads, retrieve full transcripts, and monitor response status.
Customer Management — Access detailed customer profiles and historical interactions to provide personalized service.
Team Collaboration — Add internal notes to conversations and update statuses (active, pending, closed) directly from the chat.
Operational Visibility — List all configured mailboxes, tags, and automated workflows to ensure your help desk is correctly set up.
Performance Insights — Retrieve customer satisfaction ratings to monitor the health of your support operations.
Search Capabilities — Perform advanced searches across your entire conversation history to find answers quickly.

The Help Scout MCP Server exposes 12 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Help Scout to OpenAI Agents SDK via MCP

Follow these steps to integrate the Help Scout MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 12 tools from Help Scout

Why Use OpenAI Agents SDK with the Help Scout MCP Server

OpenAI Agents SDK provides unique advantages when paired with Help Scout through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Help Scout + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Help Scout MCP Server delivers measurable value.

Automated workflows: build agents that query Help Scout, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Help Scout, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Help Scout tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Help Scout to resolve tickets, look up records, and update statuses without human intervention

Help Scout MCP Tools for OpenAI Agents SDK (12)

These 12 tools become available when you connect Help Scout to OpenAI Agents SDK via MCP:

create_convo_note

Use this for team collaboration. Add a private note to a conversation

get_conversation

Get detailed information about a specific conversation

get_customer

Get detailed profile information for a specific customer

list_conversations

Useful for monitoring incoming customer queries. List support conversations/tickets

list_customer_ratings

List recent customer satisfaction ratings

list_customers

List all customers registered in the help desk

list_mailboxes

List all configured support mailboxes

list_staff_users

List all support agents/users in the tenant

list_tags

List all available tags for categorizing conversations

list_workflows

List automated support workflows

search_conversations

Search for conversations using a query

update_convo_status

Change the status of a conversation (e.g., active, closed)

Example Prompts for Help Scout in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Help Scout immediately.

"List all active conversations in the 'Main' mailbox."

"Search for conversations from 'john.doe@example.com'."

"Add an internal note to conversation ID 12345: 'Confirmed with engineering, fix arriving tomorrow'."

Troubleshooting Help Scout MCP Server with OpenAI Agents SDK

Common issues when connecting Help Scout to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Help Scout + OpenAI Agents SDK FAQ

Common questions about integrating Help Scout MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.