How to Use the Help Scout MCP in AutoGen

Q: How does an AutoGen agent get access to Help Scout tools?

You'll use the autogen-extmcp package. The mcpservertools function connects to your Vinkius endpoint and converts the available Help Scout operations into tools that an AssistantAgent can use.

Q: How can my AutoGen agents find the right person to assign a Help Scout ticket to?

An agent can use the liststaffusers tool to get a list of all available support staff. Your agent's logic can then use that list to decide who is the best fit for the assignment.

Assemble a team of AI agents to manage Help Scout tickets. Let them collaborate and solve problems with AutoGen.

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 AutoGen

Create your Vinkius account to connect Help Scout to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Delegate Tasks to Specialist Agents

Create a "TriageAgent" whose only job is to monitor for new tickets. It uses `list_conversations` with a filter for 'active' status. When it finds one, it passes the ID to a "ResearchAgent". The ResearchAgent then takes over, using `get_conversation` and `get_customer` to gather all the facts. It summarizes its findings and hands off to a "ResolverAgent" to decide the next step, like using `create_convo_note`. It's a digital assembly line for support.

Enable Agents to Debate Solutions

AutoGen's strength is multi-agent conversation. You can have one agent propose closing a ticket with `update_convo_status`, while another agent, acting as a QA check, uses `list_customer_ratings` and argues to keep it open because the customer has a history of dissatisfaction. This isn't a simple if/then script. It's a negotiation. The agents use the tools from this MCP Server to pull evidence and build their arguments, leading to a more considered and reliable outcome.

Equip Your AutoGen Team with this MCP Server

This MCP Server provides the hands and eyes for your agent team. You use `mcp_server_tools` to load the 12 Help Scout functions and pass them to your `AssistantAgent`. The `McpToolAdapter` handles all the schema conversions automatically. Your agents can now do real work. They can check for automated `list_workflows`, look up `list_staff_users` to find an owner, and manage the entire ticket lifecycle from within their conversational group.

Setup guide

Set up Help Scout MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Help Scout tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Help Scout_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Help Scout data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Help Scout_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Help Scout data")
    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 AutoGen

You'll use the `autogen-ext[mcp]` package. The `mcp_server_tools` function connects to your Vinkius endpoint and converts the available Help Scout operations into tools that an `AssistantAgent` can use.

Yes, that's exactly what AutoGen is designed for. One agent can fetch data, another can analyze it, and a third can execute an action like `update_convo_status`. They coordinate through conversation.

An agent can use the `list_staff_users` tool to get a list of all available support staff. Your agent's logic can then use that list to decide who is the best fit for the assignment.

No. This MCP server handles the API calls. You just give the tools to your AutoGen agents, and they decide how and when to call them based on the task you've given them.

The connection to your Help Scout data, like customer info and ticket content, is secured by Vinkius. The agents themselves communicate, but the actual API calls are proxied through your single, ephemeral MCP server instance. No data is stored at rest on the server.

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