How to Use the Nominatim MCP in Pydantic AI

Q: Can my Pydantic AI agent check if the Nominatim server is available?

Yes, just call the getstatus tool. It returns a simple object with a status message that Pydantic AI will also validate, so you can reliably check if the service is up.

Q: When using Pydantic AI, what's the practical difference between Nominatim's search and lookuposm tools?

Use search when you have a text address and need coordinates. Use lookuposm when you already have a specific OpenStreetMap ID (like 'N12345') and need to retrieve its data.

Add type-safe geocoding to any LLM with Pydantic AI. Get structured, validated geographic data from Nominatim every time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nominatim MCP to Pydantic AI

Create your Vinkius account to connect Nominatim 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 Nominatim with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Validated Geocoding Results

The `search` tool converts an address string into structured location data. It finds the coordinates, bounding box, and OSM ID for a given place name. Here's the thing: Pydantic AI validates the response against a Pydantic model. If Nominatim returns something unexpected, your code will raise a `ValidationError` immediately. No more silent bugs from malformed API data.

Reliably Reverse-Geocode Coordinates

Your agent can use the `reverse_geocode` tool to turn latitude/longitude pairs into a human-readable address. You can specify the zoom level to control how detailed the resulting address is. Because Pydantic AI is model-agnostic, you can use this tool with OpenAI, Anthropic, or even a local model. The geocoding logic remains the same, and the output is always validated, regardless of which LLM is driving the agent.

Look Up OSM Data with Your Pydantic AI Agent

This MCP Server provides `lookup_osm` and `get_details` for querying OpenStreetMap objects directly. Just give your agent an OSM ID, and it can fetch the object's properties. This is where type safety really shines. The nested data from `get_details`, with its hierarchy and extratags, is parsed directly into a Pydantic model. You get clean, predictable Python objects to work with, not a messy dictionary.

Setup guide

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

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

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

You don't have to. Pydantic AI automatically validates that the JSON response from the `search` tool matches the expected Pydantic model. If it doesn't, your code throws an error.

Yes, just call the `get_status` tool. It returns a simple object with a status message that Pydantic AI will also validate, so you can reliably check if the service is up.

Use `search` when you have a text address and need coordinates. Use `lookup_osm` when you already have a specific OpenStreetMap ID (like 'N12345') and need to retrieve its data.

Pydantic AI is model-agnostic. Just configure it with your local LLM's client, like Ollama or LiteLLM, and then add the Nominatim MCPToolset. The tool-calling and validation work exactly the same.

No. The Vinkius platform processes your geocoding requests—like an address for `search`—in a zero-trust, ephemeral environment. The server instance handling your request is destroyed after it's done, and no part of your query is ever logged or stored.

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