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 Pydantic AI 12 tools — connect in under 2 minutes

Name: Help Scout
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 12 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Help Scout through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

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 pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Help Scout "
            "(12 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Help Scout?"
    )
    print(result.data)

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.

Pydantic AI validates every Help Scout tool response against typed schemas, catching data inconsistencies at build time. Connect 12 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

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 Pydantic AI 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 Pydantic AI via MCP

Follow these steps to integrate the Help Scout MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 12 tools from Help Scout with type-safe schemas

Why Use Pydantic AI with the Help Scout MCP Server

Pydantic AI provides unique advantages when paired with Help Scout through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Help Scout integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Help Scout connection logic from agent behavior for testable, maintainable code

Help Scout + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Help Scout MCP Server delivers measurable value.

Type-safe data pipelines: query Help Scout with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Help Scout tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Help Scout and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Help Scout responses and write comprehensive agent tests

Help Scout MCP Tools for Pydantic AI (12)

These 12 tools become available when you connect Help Scout to Pydantic AI 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 Pydantic AI

Ready-to-use prompts you can give your Pydantic AI 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 Pydantic AI

Common issues when connecting Help Scout to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Help Scout + Pydantic AI FAQ

Common questions about integrating Help Scout MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Help Scout MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.