Do I need an API key?

No! Overpass API is completely free and open. No authentication required. Please be respectful with query sizes — avoid queries returning more than 10,000 elements.

What is a bounding box?

A bounding box defines a geographic area using min_latitude, min_longitude, max_latitude, max_longitude. Example: "40.70,-74.01,40.72,-73.98" covers Lower Manhattan, NYC.

Can I search near my current location?

Yes! Use search_nearby or search_nearby_amenities with your GPS coordinates and a radius in meters (e.g. lat=40.7128, lon=-74.0060, radius=1000 for 1km around NYC).

What amenities can I search for?

Common amenities: restaurant, cafe, fast_food, bar, pub, hospital, clinic, pharmacy, school, university, library, atm, bank, fuel, parking, police, fire_station, post_office, toilets, cinema, theatre, nightclub, museum.

Overpass (OpenStreetMap) MCP Server for OpenAI Agents SDK 16 tools — connect in under 2 minutes

Name: Overpass (OpenStreetMap)
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 16 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Overpass (OpenStreetMap) through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Overpass (OpenStreetMap) Assistant",
            instructions=(
                "You help users interact with Overpass (OpenStreetMap). "
                "You have access to 16 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Overpass (OpenStreetMap)"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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 Overpass (OpenStreetMap) MCP Server

Connect to Overpass API (OpenStreetMap) and query the world's largest free geographic database through natural conversation — no API key needed.

The OpenAI Agents SDK auto-discovers all 16 tools from Overpass (OpenStreetMap) through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Overpass (OpenStreetMap), another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Amenity Search — Find restaurants, cafes, hospitals, schools, pharmacies, ATMs, fuel stations and more
Shop Search — Discover shops, supermarkets, bakeries, clothing stores and retail outlets
Nearby Search — Find any amenity within a radius of any GPS coordinate
Hotel Search — Locate hotels, hostels and tourist accommodation
Park Search — Find parks, gardens and green spaces
EV Charging — Locate electric vehicle charging stations
Custom Queries — Execute custom Overpass QL queries for any OSM data

The Overpass (OpenStreetMap) MCP Server exposes 16 tools through the Vinkius. Connect it to OpenAI Agents SDK 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 Overpass (OpenStreetMap) to OpenAI Agents SDK via MCP

Follow these steps to integrate the Overpass (OpenStreetMap) MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 16 tools from Overpass (OpenStreetMap)

Why Use OpenAI Agents SDK with the Overpass (OpenStreetMap) MCP Server

OpenAI Agents SDK provides unique advantages when paired with Overpass (OpenStreetMap) through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Overpass (OpenStreetMap) + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Overpass (OpenStreetMap) MCP Server delivers measurable value.

Automated workflows: build agents that query Overpass (OpenStreetMap), process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Overpass (OpenStreetMap), another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Overpass (OpenStreetMap) tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Overpass (OpenStreetMap) to resolve tickets, look up records, and update statuses without human intervention

Overpass (OpenStreetMap) MCP Tools for OpenAI Agents SDK (16)

These 16 tools become available when you connect Overpass (OpenStreetMap) to OpenAI Agents SDK via MCP:

custom_query

The query should be valid Overpass QL syntax. The output format is automatically set to JSON. If no out statement is included, "out geom;" is appended automatically. Example: `node["amenity"="cafe"](51.5,-0.15,51.51,-0.14); out geom;` Execute a custom Overpass QL query

search_amenities

Common amenities: "restaurant", "cafe", "school", "hospital", "pharmacy", "bank", "atm", "fuel", "parking", "toilets", "library", "police", "fire_station", "post_office", "cinema", "theatre", "nightclub", "bar", "pub", "fast_food", "ice_cream". Bbox format: lat_min,lon_min,lat_max,lon_max. Search for amenities (restaurants, schools, hospitals, etc.) in a bounding box

search_atms

Returns ATM locations, operator/bank names, addresses, 24/7 availability and network info. Bbox format: lat_min,lon_min,lat_max,lon_max. Search for ATMs in a bounding box

search_by_name

Optional amenity filter to narrow results. Returns matching elements with full details including addresses, phone numbers and websites. Search for OSM elements by name

search_by_tag

Bbox format: lat_min,lon_min,lat_max,lon_max (e.g. "51.249,-0.15,51.251,-0.10" for central London). Useful for finding specific OSM-tagged features. Search OpenStreetMap elements by tag key/value in a bounding box

search_charging_stations

Returns station names, addresses, connector types, charging speeds, operator info and access details. Bbox format: lat_min,lon_min,lat_max,lon_max. Search for EV charging stations in a bounding box

search_fuel_stations

Returns station names, brands, addresses, fuel types offered, opening hours and operator info. Bbox format: lat_min,lon_min,lat_max,lon_max. Search for fuel/gas stations in a bounding box

search_hospitals

Returns facility names, addresses, phone numbers, emergency services info, specialties and operator info. Bbox format: lat_min,lon_min,lat_max,lon_max. Search for hospitals and clinics in a bounding box

search_hotels

Returns hotel names, addresses, star ratings, phone numbers, websites and room info. Bbox format: lat_min,lon_min,lat_max,lon_max. Search for hotels in a bounding box

search_nearby

Useful for finding nearby amenities without defining a full bounding box. Returns names, addresses, distances and details. Search for OSM elements near a specific location

search_nearby_amenities

Common amenities: "restaurant", "cafe", "pharmacy", "atm", "bank", "hospital", "school", "supermarket", "fuel", "charging_station", "parking", "toilets", "police", "fire_station", "post_office". Search for specific amenities near a location

search_parks

Returns park names, addresses, area sizes, features (playgrounds, sports facilities) and operator info. Bbox format: lat_min,lon_min,lat_max,lon_max. Search for parks and green spaces in a bounding box

search_pharmacies

Returns pharmacy names, addresses, phone numbers, opening hours, dispensing info and operator info. Bbox format: lat_min,lon_min,lat_max,lon_max. Search for pharmacies in a bounding box

search_restaurants

Optional cuisine filter: "italian", "chinese", "japanese", "indian", "mexican", "thai", "french", "american", "pizza", "burger", "sushi", "vegan", "vegetarian". Bbox format: lat_min,lon_min,lat_max,lon_max. Search for restaurants in a bounding box

search_schools

Returns school names, addresses, phone numbers, websites, student capacity and operator info. Bbox format: lat_min,lon_min,lat_max,lon_max. Search for schools in a bounding box

search_shops

Optional shop type filter: "supermarket", "convenience", "clothes", "bakery", "butcher", "electronics", "furniture", "hardware", "jewelry", "mall", "bookmaker", "car", "car_repair", "chemist", "florist", "gift", "hairdresser", "mobile_phone", "shoes", "sports", "toys". Bbox format: lat_min,lon_min,lat_max,lon_max. Search for shops in a bounding box

Example Prompts for Overpass (OpenStreetMap) in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Overpass (OpenStreetMap) immediately.

"Find all restaurants in Lower Manhattan."

"Find ATMs within 500m of Times Square (40.7580, -73.9855)."

"Find EV charging stations in downtown San Francisco."

Troubleshooting Overpass (OpenStreetMap) MCP Server with OpenAI Agents SDK

Common issues when connecting Overpass (OpenStreetMap) to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Overpass (OpenStreetMap) + OpenAI Agents SDK FAQ

Common questions about integrating Overpass (OpenStreetMap) MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.