How to Use the BoldDesk MCP in Pydantic AI

Q: How do I initialize the BoldDesk toolset in Pydantic AI?

Use the unified MCPToolset class in Pydantic AI pointing to your Vinkius BoldDesk URL and pass it to your Agent's toolsets argument. Avoid using the deprecated MCPServerHTTP class, as the unified toolset is the modern standard for Pydantic AI workflows.

Run type-safe BoldDesk ticket operations using Pydantic AI to guarantee valid customer data in your agent workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BoldDesk MCP to Pydantic AI

Create your Vinkius account to connect BoldDesk 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 BoldDesk with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate BoldDesk updates with Pydantic AI

Executing the `update_ticket` tool modifies BoldDesk support records while enforcing strict schema validation at the Pydantic AI runtime level. This MCP Server works with Pydantic AI to ensure that BoldDesk status codes, priorities, and custom fields match your exact data models before hitting the API. If your Pydantic AI model tries to pass an invalid status or a malformed ticket ID to BoldDesk, the framework catches the error instantly. This prevents corrupted data from polluting your BoldDesk support dashboard during automated Pydantic AI operations.

Safe ticket creation and message replies

Starting new requests with the `create_ticket` tool instantiates BoldDesk customer records using validated Pydantic AI input schemas. Pydantic AI parses the incoming customer query, extracts the required fields, and ensures `reply_to_ticket` only executes in BoldDesk when all required parameters are present. This strict type checking inside Pydantic AI eliminates silent failures when writing to BoldDesk. Your Pydantic AI agent will never send empty replies or draft BoldDesk tickets with missing contact information.

Inspect support agents and customer contacts safely

Querying staff with the `get_agent` tool retrieves internal BoldDesk profiles, validating the returned JSON against your Pydantic AI type hints. Your Pydantic AI agent can safely query `list_agents` to find active BoldDesk support staff without risking runtime crashes from unexpected API payloads. The same validation applies to `get_contact` and `list_contacts` when Pydantic AI interacts with BoldDesk. Your Pydantic AI agent processes customer contact records with absolute structural certainty, making your automated BoldDesk workflows incredibly resilient.

Setup guide

Set up BoldDesk 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": {
        "bolddesk-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent BoldDesk 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 BoldDesk. 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 BoldDesk 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 BoldDesk MCP in Pydantic AI

Use the unified `MCPToolset` class in Pydantic AI pointing to your Vinkius BoldDesk URL and pass it to your Agent's `toolsets` argument. Avoid using the deprecated `MCPServerHTTP` class, as the unified toolset is the modern standard for Pydantic AI workflows.

The Pydantic AI framework will fail loudly by raising a validation error instead of passing malformed BoldDesk data to your model. This ensures your Pydantic AI agent never hallucinates fields based on incomplete or modified BoldDesk API responses.

Yes, the MCP server supports both Streamable HTTP and SSE transports for BoldDesk inside Pydantic AI. You can configure your Pydantic AI connection based on whether your agent runs in a serverless environment or a long-running container.

Yes, Pydantic AI is model-agnostic, allowing you to run BoldDesk tools with Anthropic, Gemini, or local models. You retain full Pydantic AI type-safety across all BoldDesk endpoints regardless of the underlying LLM.

Vinkius executes the BoldDesk server within an ephemeral V8 Isolate sandbox, meaning no customer support tickets are ever cached or stored on disk. All communication between Pydantic AI and the BoldDesk MCP endpoints is encrypted, keeping your customer support interactions secure.

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