How to Use the ConnectWise MCP in Pydantic AI

Q: How do I configure Pydantic AI to use the ConnectWise MCP Server?

Import MCPToolset and point it at your Vinkius HTTP server. Pass this toolset into your Agent constructor to expose the ConnectWise actions.

Q: Can my Pydantic AI agent list internal staff members?

Yes, the agent calls listmembers to retrieve the staff roster. The output is validated against your Pydantic schemas for safe routing.

Get type-safe access to your ConnectWise PSA data using the Pydantic AI framework to prevent silent validation failures.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ConnectWise MCP to Pydantic AI

Create your Vinkius account to connect ConnectWise 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 ConnectWise with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe ticket creation via Pydantic AI

The `create_ticket` MCP tool allows your Pydantic AI agent to generate service records with guaranteed schema compliance. Because the framework validates all inputs at runtime, you avoid database corruption from malformed ticket fields. If your agent attempts to write a ticket with missing required fields, the system rejects the call instantly. This keeps your ConnectWise Manage board clean and free of broken entries.

Validated company lookups

The `get_company` tool returns structured client profiles including territory and status details. Pydantic AI parses this JSON payload against strict schemas to ensure your agent never processes corrupt data. This strict validation prevents your model from hallucinating contact details. Your application gets clean, verified data every time it queries a customer account.

Secure ticket search pipelines

The `search_tickets_by_summary` tool searches ConnectWise records using keyword queries. The returning list is validated by the MCP Server integration before your model even reads the text. If you need to inspect a specific issue, `get_ticket` pulls the full priority and notes. Your Pydantic AI agent can safely parse these notes without risking parser crashes.

Setup guide

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

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

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

Import `MCPToolset` and point it at your Vinkius HTTP server. Pass this toolset into your Agent constructor to expose the ConnectWise actions.

The framework raises a validation error immediately. This prevents your model from acting on corrupted ticket or company data.

Yes, the agent calls `list_members` to retrieve the staff roster. The output is validated against your Pydantic schemas for safe routing.

Yes, the framework handles async calls natively. Your agent can query multiple tickets or companies concurrently without blocking the main loop.

Yes, Vinkius uses zero-trust architecture to run the MCP connector. Your customer contacts and support logs are processed in memory and never written to persistent storage.

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