Bring Policy Management
to Pydantic AI
Learn how to connect Berg System CRM to Pydantic AI and start using 12 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Berg System CRM MCP Server?
Connect your Berg System account to any AI agent and take full control of your insurance agency operations and customer relationship workflows through natural conversation.
What you can do
- Customer Orchestration — List and search through individual and corporate client directories programmatically, retrieving detailed high-fidelity profile metadata and contact history
- Sales Pipeline Intelligence — Monitor sales opportunities and track deal progress across your entire agency to maintain a perfectly coordinated sales cycle
- Insurance Policy Monitoring — Retrieve active insurance policies and access high-fidelity document metadata directly through your agent to oversee coverage status
- Infrastructure Monitoring — Access system employee lists and manage CRM-related tasks programmatically for instant operational reporting
- Relationship Intelligence — Retrieve complete historical interactions for any record to maintain high-fidelity oversight of your agency's relationship ecosystem
How it works
1. Subscribe to this server
2. Retrieve your Tenant ID and OAuth Access Token from your Berg System instance
3. Start managing your insurance business from Claude, Cursor, or any MCP client
No more manual toggling between CRM tabs or digging through paper policy files. Your AI acts as your dedicated agency administrator and sales coordinator.
Who is this for?
- Insurance Agents — instantly retrieve client coverage details and update lead statuses using natural language commands
- Agency Managers — monitor team productivity and track agency-wide sales trends without leaving your workspace
- Operations Leads — automate the oversight of corporate client directories and task management through simple AI queries
Built-in capabilities (12)
Verify Berg System API status
Add a new business client
Supports forceAdd to bypass duplicates. Add a new customer
Get details for a customer
Retrieve custom sales fields
List corporate clients
List CRM customers
List active tasks and reminders
List active insurance policies
List sales records
List uploaded documents
List organization employees
Why Pydantic AI?
Pydantic AI validates every Berg System CRM tool response against typed schemas, catching data inconsistencies at build time. Connect 12 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.
- —
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 Berg System CRM integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Berg System CRM connection logic from agent behavior for testable, maintainable code
Berg System CRM in Pydantic AI
Berg System CRM and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Berg System CRM to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Berg System CRM in Pydantic AI
The Berg System CRM 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. All 12 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* 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
How Vinkius secures
Berg System CRM for Pydantic AI
Every tool call from Pydantic AI to the Berg System CRM MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I find my Berg System Tenant ID?
Your Tenant ID is the unique identifier for your agency instance, found in your Berg System sub-domain (e.g., yourcompany.bergsystem.pl).
Can I check for duplicates via AI?
Yes! The system automatically checks for existing records, and you can use the forceAdd parameter in creation tools to decide how to handle them.
How do I retrieve insurance policies?
Use the list_insurance_policies tool to retrieve a comprehensive summary of all active policies managed within your CRM programmatically.
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 Berg System CRM MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai