How to Use the Help Scout MCP in Pydantic AI

Q: How do I register the Help Scout MCP Server in Pydantic AI?

Use the MCPToolset class pointing to your Vinkius server URL and pass it to your agent's toolsets argument. This registers all twelve tools with full runtime schema validation automatically.

Q: Can Pydantic AI search through my Help Scout conversations?

Yes, the agent calls searchconversations with your search query. The resulting list of conversations is validated against your Pydantic models before the agent processes them.

Build type-safe Help Scout agents with Pydantic AI to validate support tickets and customer profiles at runtime.

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 Pydantic AI

Create your Vinkius account to connect Help Scout to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Ticket Management with Pydantic AI

`list_conversations` returns support tickets that Pydantic AI validates against strict Python type schemas. This MCP Server ensures that if Help Scout returns an unexpected payload structure, the runtime raises an immediate validation error instead of letting your agent hallucinate. This strict validation ensures that when your agent executes `update_convo_status`, the status string matches allowed values exactly. No more silent failures or corrupted ticket states in your production support database.

Strict Customer Profile Validation

`get_customer` fetches customer details which are immediately parsed into typed models. Your agent reads verified email addresses, names, and custom fields, ensuring that automated actions are based on clean data. If the agent needs to lookup multiple records, it runs `list_customers` to process profiles in bulk. The validation engine ensures every single customer record complies with your application's data schemas before processing continues.

Verified Internal Notes and Tags

`create_convo_note` requires specific parameters that Pydantic AI validates before sending the request. Your agent cannot post empty notes or malformed text, keeping your internal Help Scout communications clean. The agent uses `list_tags` to get the allowed taxonomy. It then applies these verified tags to incoming threads, keeping your mailbox organized without introducing typos or duplicate tags.

Setup guide

Set up Help Scout MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "help-scout-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Help Scout tools.",
)

result = await agent.run("List recent Help Scout transactions")
print(result.output)

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 Pydantic AI

Use the `MCPToolset` class pointing to your Vinkius server URL and pass it to your agent's `toolsets` argument. This registers all twelve tools with full runtime schema validation automatically.

The framework catches the schema mismatch immediately and raises a validation error. This prevents your agent from making decisions based on corrupted or parsed-incorrectly support ticket data.

Yes, the agent calls `search_conversations` with your search query. The resulting list of conversations is validated against your Pydantic models before the agent processes them.

Yes, the managed MCP setup supports both Streamable HTTP and SSE transports. You can configure your toolset to connect using the protocol that fits your network setup.

The server operates under a zero-trust model where ticket data and customer ratings are never cached. Your API tokens are encrypted at rest, and all transit data is discarded the moment the HTTP request completes.

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