How do I securely obtain my ConnectWise API Keys and Company ID?

Log into your ConnectWise Manage instance. Note your 'Company ID' prominently displayed on the login screen. Then navigate securely via the internal system module down under 'System' > 'Members', find the specialized sub-tab marked 'API Members'. Create a new specific role API member for this AI, and within its configuration, strictly establish a new API Key generation. This will output a matched pair containing your 'Public Key' and your strictly secured 'Private Key'. Securely provide all thre

Will the agent close tickets automatically, or must I specifically instruct it to change the status?

The AI remains tightly compliant to your direct prompts. It will not spontaneously close unprompted tickets or mutate parameters heavily without instruction. You must expressly request 'Change ticket X status to Closed' ensuring governance, compliance, and accurate logging remains strictly under your control at all times during interactive use.

Can I query client configurations or passwords with this active integration?

Configurational details such as device types and basic network data models are queryable if permissions via API permit, but sensitive field extraction like retrieving unencrypted passwords directly inside the dialog typically stays strictly masked or gated, abiding exclusively by your ConnectWise native security role allowances configured previously inside the specific 'API Member' settings during your setup.

ConnectWise MCP Server for Pydantic AI 9 tools — connect in under 2 minutes

Name: ConnectWise
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 9 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect ConnectWise through 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 ConnectWise "
            "(9 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in ConnectWise?"
    )
    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 ConnectWise MCP Server

Empower your conversational AI with deep integration into ConnectWise Manage (PSA). Enhance technical support operations by enabling your agent to triage issues, update existing service tickets, and retrieve critical client environment data without leaving your conversational interface.

Pydantic AI validates every ConnectWise tool response against typed schemas, catching data inconsistencies at build time. Connect 9 tools through 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

Ticketing Operations — Rapidly inspect queue statuses, assign incoming tickets, or update internal notes naturally.
Asset & Configuration Retrieval — Look up devices, configurations, and agreements associated with a specific managed client.
Billing & Time Entries — Log billable technical time or adjust status workflows directly through the chat.

The ConnectWise MCP Server exposes 9 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 ConnectWise to Pydantic AI via MCP

Follow these steps to integrate the ConnectWise 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 9 tools from ConnectWise with type-safe schemas

Why Use Pydantic AI with the ConnectWise MCP Server

Pydantic AI provides unique advantages when paired with ConnectWise 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 ConnectWise integration code

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

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

ConnectWise + Pydantic AI Use Cases

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

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

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

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

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

ConnectWise MCP Tools for Pydantic AI (9)

These 9 tools become available when you connect ConnectWise to Pydantic AI via MCP:

create_ticket

Create a new service ticket in ConnectWise Manage

get_company

Returns name, contact info, territory, and status. Retrieve detailed information about a specific company

get_ticket

Returns summary, priority, status, assigned member, and notes. Retrieve detailed information about a specific service ticket

list_companies

Use to discover company identifiers for ticket creation. Retrieve a list of companies/clients in ConnectWise

list_contacts

Use to find external contact details. Retrieve a list of individual contacts within companies

list_members

Retrieve a list of internal staff members

list_sales_activities

Retrieve a list of sales and service activities

list_service_tickets

Supports pagination via pageSize. Retrieve a list of service tickets from ConnectWise Manage

search_tickets_by_summary

Useful for finding tickets by keyword. Find service tickets matching a keyword in the summary

Example Prompts for ConnectWise in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with ConnectWise immediately.

"Show me the top 3 open critical tickets currently on the 'Helpdesk' board."

"Enter a time entry of 1.5 hours for ticket #13988 with the notes 'Reconfigured firewall rules to establish stable VPN tunnels.' and mark the ticket as closed."

"Retrieve the billing details and active agreements for the client 'Globex Corporation' to prepare for an audit."

Troubleshooting ConnectWise MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

ConnectWise + Pydantic AI FAQ

Common questions about integrating ConnectWise 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 ConnectWise MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.