How to Use the Nestoria MCP in Pydantic AI

Q: How do I initialize the Nestoria toolset in Pydantic AI?

Instantiation is simple. Use the unified MCPToolset pointing to your server URL, and pass it into the toolsets argument when defining your Pydantic AI agent. This registers searchlistings automatically.

Build type-safe real estate workflows with Pydantic AI and the Nestoria MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nestoria MCP to Pydantic AI

Create your Vinkius account to connect Nestoria 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 Nestoria with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Nestoria Data at Runtime with Pydantic AI

Stop letting malformed API responses break your production pipelines. When your agent calls `search_listings`, this MCP Server returns structured data that Pydantic AI validates against strict Python type models before your code runs. If the real estate API returns an unexpected data type, your agent fails loudly and immediately. This guarantees that no corrupted pricing or missing location fields slip into your database.

Connect Any LLM to Global Real Estate Markets

Run your property searches with Anthropic, OpenAI, or local models. Because Pydantic AI is completely model-agnostic, this MCP Server lets you swap models without changing how you call `search_listings`. You can use a cheaper model for initial property filtering and a smarter model for final recommendations. The underlying search tool remains completely consistent across your entire stack.

Avoid Deprecated HTTP Clients in Your Codebase

Keep your Python codebase modern and clean. This integration uses the unified `MCPToolset` class, avoiding deprecated HTTP client classes while exposing `search_listings` directly to your Pydantic AI agents. It supports both Streamable HTTP and SSE transports out of the box. You get a reliable connection to the property index without writing custom network logic.

Setup guide

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

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

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

Instantiation is simple. Use the unified `MCPToolset` pointing to your server URL, and pass it into the `toolsets` argument when defining your Pydantic AI agent. This registers `search_listings` automatically.

Pydantic AI will catch the mismatch at the validation layer. If `search_listings` returns data that violates your model's schema, a validation error is raised immediately, stopping silent failures.

Yes. The unified toolset integrates cleanly with async Python environments, allowing your Pydantic AI agent to process multiple concurrent property searches without blocking execution.

Yes. The MCP Server must be running externally. Your Pydantic AI agent connects to it via HTTP or SSE transports to execute the `search_listings` tool.

All search criteria, including target postal codes and maximum pricing, are protected by end-to-end encryption. The Vinkius gateway handles authentication securely, ensuring your search history never leaks.

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