How to Use the Precisely MCP in Pydantic AI

Q: Can I use Precisely with Pydantic AI for complex property lookups?

Yes. You can chain getpropertyinfo and getlocaltax calls. Pydantic AI manages the state, and Precisely provides the high-fidelity data needed for the final output.

Use the Precisely MCP Server with Pydantic AI for type-safe location intelligence and validated property data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Precisely MCP to Pydantic AI

Create your Vinkius account to connect Precisely to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Precisely with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Type-safe address validation in Pydantic AI

Every response from `verify_address` is validated against your Pydantic models. If the API returns malformed data, your agent stops immediately, preventing corrupted records from entering your database. Use `autocomplete_address` to provide structured suggestions. Because the tool output is coerced into your models, you can guarantee that the address components are always correctly typed and ready for use.

Risk enrichment with Pydantic AI constraints

Call `enrich_flood_risk` and map the output to a strict schema. Pydantic AI will catch any missing fields or unexpected types, ensuring your flood risk assessment logic never receives partial data. Apply the same rigor to `enrich_crime_risk`. Your agent will only process the data if it meets your schema requirements, keeping your underwriting calculations safe from silent failures.

Property and tax data for Pydantic AI

Extract property attributes with `get_property_info` and define a Pydantic model for the response. This gives you full IDE completion and runtime safety when working with lot sizes or valuation data. Use `get_local_tax` to calculate tax rates. By validating the response against a schema, you ensure that your tax calculations are always based on accurate, well-formed jurisdiction data.

Setup guide

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

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

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

Pydantic AI validates every tool output against your predefined models. Precisely provides the data, and your models ensure it fits your application's requirements perfectly.

Your agent will throw a validation error immediately. Precisely data is checked at the boundary, ensuring your Pydantic AI logic never operates on hallucinated or malformed fields.

Yes. You can chain `get_property_info` and `get_local_tax` calls. Pydantic AI manages the state, and Precisely provides the high-fidelity data needed for the final output.

The server is built for async Python. Precisely integrates natively with your existing Pydantic AI async event loop, ensuring non-blocking performance during data retrieval.

Precisely uses encrypted communication for all property lookups. Your Pydantic AI agent keeps the data in memory only for the duration of the request, preventing persistent exposure.

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