How to Use the Berg System CRM MCP in Pydantic AI

Q: How do I make Pydantic AI work with Berg System CRM?

You'll import MCPToolset and initialize it with your Vinkius server URL for Berg System CRM. Then you pass that toolset into the Agent's toolsets list. Pydantic AI handles the rest.

Q: What happens if the Berg System CRM API returns bad data to my Pydantic AI agent?

Your agent will raise a ValidationError and stop. Pydantic AI's core feature is to prevent your application from working with unexpected or malformed data, so a loud failure is the intended, safe behavior.

Add type-safe access to Berg System CRM in any Python agent. Built for correctness with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Berg System CRM MCP to Pydantic AI

Create your Vinkius account to connect Berg System CRM 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 Berg System CRM with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create Records Without Data Corruption

Your agent can add new clients and companies to the CRM. It uses the `create_new_company` and `create_new_customer` tools to write data, just like a human user would. It's a direct, predictable way to automate data entry. The real value comes from Pydantic AI's validation. When the Berg System CRM API confirms a new record was created, its response is parsed and validated against a Pydantic model at runtime. If the API returns an unexpected field or incorrect data type, your agent raises a `ValidationError` immediately. No silent data corruption.

Get Validated Client Data, Every Time

This MCP server lets your agent read critical client information. It can pull a customer's complete file with `get_customer_details` or get a list of their active insurance policies using `list_insurance_policies`. With Pydantic AI, you're guaranteed that the data your agent receives matches the expected schema. If an API change or bug causes the server to send back malformed JSON, your agent will fail loudly instead of operating on bad data. It's a philosophy of correctness over risky assumptions.

A Reliable MCP Server for Pydantic AI

Give your agent the tools it needs to manage your CRM. It can check for pending work with `list_crm_tasks`, review open deals with `list_sales_opportunities`, and get a list of all clients with `list_crm_customers`. Because Pydantic AI is model-agnostic, you can use these tools with any LLM—from OpenAI to a model running on your own machine. Pydantic AI's job is to ensure that the data flowing between your agent and the Berg System CRM MCP is always well-structured and valid, no matter which language model is driving the conversation.

Setup guide

Set up Berg System CRM 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": {
        "berg-system-crm-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Berg System CRM 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 Berg System. 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 Berg System CRM 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 Berg System CRM MCP in Pydantic AI

You'll import `MCPToolset` and initialize it with your Vinkius server URL for Berg System CRM. Then you pass that toolset into the `Agent`'s `toolsets` list. Pydantic AI handles the rest.

Your agent will raise a `ValidationError` and stop. Pydantic AI's core feature is to prevent your application from working with unexpected or malformed data, so a loud failure is the intended, safe behavior.

Yes. Pydantic AI is model-agnostic, so you can connect it to any local or private LLM that you host. It will still enforce type-safe tool calls to the Vinkius-hosted Berg System CRM server, giving you both data privacy and runtime correctness.

The Berg System CRM distinguishes between individual people and corporate entities. `list_crm_customers` returns a list of individual clients, while `list_crm_companies` returns a list of business clients.

The server works with your Berg System CRM customer records, company lists, and insurance policy data. Pydantic AI's validation ensures data integrity, while the Vinkius platform provides security by running every tool call in a disposable, zero-trust sandbox. No data persists on the server after your request is complete.

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