How to Use the LandTech MCP in Pydantic AI

Q: How do I configure LandTech for Pydantic AI?

Install pydantic-ai-slimmcp. Initialize an MCPToolset with your HTTP endpoint and assign it to your agent's toolsets parameter.

Q: Why did Pydantic AI deprecate MCPServerHTTP for LandTech?

The framework moved to the unified MCPToolset approach. This simplifies the connection process and handles both Streamable HTTP and SSE transports under one class.

Q: Can Pydantic AI catch errors from LandTech's pricing tools?

Yes. If getpricecomparables returns a null value for a recent sale, your defined Pydantic model catches it. The agent fails loudly rather than hallucinating a property value.

Build type-safe real estate agents with Pydantic AI that validate every LandTech parcel and planning record at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LandTech MCP to Pydantic AI

Create your Vinkius account to connect LandTech 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 LandTech with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Planning Data in Pydantic AI

The `search_urban_planning` tool queries local databases for active development applications. Your agent passes the resulting application IDs to `get_planning_details` to extract the exact status and submission dates. Pydantic AI forces these responses into strict data models. If a local authority returns a malformed date string, the framework throws a validation error immediately instead of passing garbage data to your downstream systems.

Screen Parcels with Type Constraints

Using `search_land_parcels` returns coordinate boundaries for potential development sites. The agent feeds those boundaries into `get_site_constraints` to identify greenbelt restrictions or flood risks. You define the exact schema for a viable site. The MCP Server fetches the raw data, and your agent ensures every required field exists before moving the plot to the review stage.

Extract Ownership and Building Specs

The `get_ownership_title` tool pulls the legal registry information for a specific address. Your system pairs this with `get_building_data` to compile a complete profile of the physical structure and its owner. Because Pydantic AI is model-agnostic, you can use a cheap local model to extract the basic building specs and switch to Anthropic or OpenAI for complex title parsing. The validation layer keeps the output consistent regardless of the LLM.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]`. Initialize an `MCPToolset` with your HTTP endpoint and assign it to your agent's `toolsets` parameter.

The framework moved to the unified `MCPToolset` approach. This simplifies the connection process and handles both Streamable HTTP and SSE transports under one class.

Yes. If `get_price_comparables` returns a null value for a recent sale, your defined Pydantic model catches it. The agent fails loudly rather than hallucinating a property value.

No. The integration works with any model supported by the framework. You can swap providers without rewriting your tool schemas or agent logic.

Your agent sends specific geospatial coordinates to check for development risks. The system operates on ephemeral instances, meaning your proprietary search areas are wiped from memory the second the connection closes.

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