How to Use the kvCORE MCP in Pydantic AI

Q: How do I use kvCORE with Pydantic AI?

Install pydantic-ai-slimmcp. Create an MCPToolset using your Vinkius HTTP endpoint and pass it directly to the toolsets array on your Agent.

Q: Can Pydantic AI validate kvCORE lead data?

Yes. When the agent calls getleaddetails, Pydantic forces the response into your defined models. It throws a validation error if the CRM returns unexpected structures.

Build type-safe real estate workflows by connecting kvCORE to 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 kvCORE MCP to Pydantic AI

Create your Vinkius account to connect kvCORE 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 kvCORE with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate kvCORE MCP Server payloads

The `update_lead_info` tool requires strict JSON strings to modify statuses and phone numbers. Pydantic AI catches malformed requests before they hit the server. You define the exact schema, and the framework forces the LLM to comply. If the model hallucinates a field, the execution fails loudly. You connect this by passing `MCPToolset` to your `Agent` constructor. The framework handles the Streamable HTTP transport automatically. Your CRM database stays clean because bad data never makes it past the validation layer.

Audit agent profiles safely

The `get_agent_profile` tool fetches current information for specific team members. Your Pydantic AI agent reads this data and immediately calls `list_agent_tasks` to pull their pending workload. You get a programmatic view of who is falling behind. The framework parses the task lists into structured Python objects. When an agent completes a call, the system triggers `create_lead_note` to log the interaction. The strict typing ensures every note follows your exact corporate format.

Search leads with guaranteed structure

The `search_kvcore_leads` tool returns lead IDs and basic contact details. The agent uses these IDs to execute `get_lead_details` for deeper context. Because Pydantic validates the response, your downstream code never crashes on a missing dictionary key. You can swap underlying models without breaking the integration. Whether you run Anthropic or a local model, the tool execution remains identical. The framework guarantees the outputs match your expectations.

Setup guide

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

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

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

Install pydantic-ai-slim[mcp]. Create an MCPToolset using your Vinkius HTTP endpoint and pass it directly to the toolsets array on your Agent.

Yes. When the agent calls get_lead_details, Pydantic forces the response into your defined models. It throws a validation error if the CRM returns unexpected structures.

It prevents silent failures. If an agent tries to run update_lead_info with a bad JSON string, the framework stops it. You prioritize correctness over speed.

The framework supports both Streamable HTTP and SSE transports. Vinkius provides the external server endpoint you need for the connection.

The system processes phone numbers and email addresses inside a stateless V8 Isolate Sandbox. Vinkius requires only a single endpoint token for access. The environment spins down immediately after the API call completes, leaving zero residual data.

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