Nominatim MCP Server for Pydantic AI 5 tools — connect in under 2 minutes
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Nominatim through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP
async def main():
# Your Vinkius token — get it at cloud.vinkius.com
server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
agent = Agent(
model="openai:gpt-4o",
mcp_servers=[server],
system_prompt=(
"You are an assistant with access to Nominatim "
"(5 tools)."
),
)
result = await agent.run(
"What tools are available in Nominatim?"
)
print(result.data)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Nominatim MCP Server
Connect to Nominatim and search the world's most comprehensive open-source geographic database through natural conversation — no API key needed.
Pydantic AI validates every Nominatim tool response against typed schemas, catching data inconsistencies at build time. Connect 5 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.
What you can do
- Address Search — Find any place by name, address or type of place (restaurants, schools, hospitals)
- Reverse Geocoding — Convert GPS coordinates to human-readable addresses
- OSM Lookup — Look up detailed info for any OpenStreetMap object by its ID
- Structured Addresses — Get detailed address components (street, city, state, postal code, country)
- Multi-language Names — Retrieve place names in different languages
- Bounding Boxes — Get geographic boundaries for cities, countries and regions
The Nominatim MCP Server exposes 5 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Nominatim to Pydantic AI via MCP
Follow these steps to integrate the Nominatim MCP Server with Pydantic AI.
Install Pydantic AI
Run pip install pydantic-ai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save to agent.py and run: python agent.py
Explore tools
The agent discovers 5 tools from Nominatim with type-safe schemas
Why Use Pydantic AI with the Nominatim MCP Server
Pydantic AI provides unique advantages when paired with Nominatim through the Model Context Protocol.
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Nominatim integration code
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
Dependency injection system cleanly separates your Nominatim connection logic from agent behavior for testable, maintainable code
Nominatim + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the Nominatim MCP Server delivers measurable value.
Type-safe data pipelines: query Nominatim with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple Nominatim tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query Nominatim and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock Nominatim responses and write comprehensive agent tests
Nominatim MCP Tools for Pydantic AI (5)
These 5 tools become available when you connect Nominatim to Pydantic AI via MCP:
get_details
Returns the object's full name, display name, place rank, importance score, bounding box, parent place hierarchy, linked Wikipedia/Wikidata articles and optional extratags. OSM type: N (node), W (way), R (relation). Get detailed info for an OSM object
get_status
Returns status message and response latency. Useful for verifying the service is operational before making other requests. Get Nominatim server status
lookup_osm
IDs are formatted as "type{id}" where type is N (node), W (way) or R (relation). Multiple IDs are comma-separated. Returns the object's display name, coordinates, bounding box and properties. Look up OSM objects by ID
reverse_geocode
Returns the nearest address, city, state, country and other location details. Supports different zoom levels for varying detail granularity. Convert coordinates to an address
search
Returns results with coordinates, bounding box, display name, address components and OSM type/id. Supports structured searches with country codes and viewbox for region prioritization. Rate limited to 1 request/second. Search for places by name or address
Example Prompts for Nominatim in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with Nominatim immediately.
"Find the coordinates for the Eiffel Tower."
"What address is at coordinates 40.7128, -74.0060?"
"Search for 'Central Park' and show me its bounding box."
Troubleshooting Nominatim MCP Server with Pydantic AI
Common issues when connecting Nominatim to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiNominatim + Pydantic AI FAQ
Common questions about integrating Nominatim MCP Server with Pydantic AI.
How does Pydantic AI discover MCP tools?
MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.Does Pydantic AI validate MCP tool responses?
Can I switch LLM providers without changing MCP code?
Connect Nominatim with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Nominatim to Pydantic AI
Get your token, paste the configuration, and start using 5 tools in under 2 minutes. No API key management needed.