Overpass (OpenStreetMap) MCP. Query global data for facilities and points of interest.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Overpass (OpenStreetMap) MCP Server lets you query the world's largest free map database directly through your AI client. Find anything from restaurants and hospitals to EV chargers or custom-tagged features anywhere globally.
No API key needed—just talk to it.
What your AI agents can do
Custom query
Runs any custom Overpass QL query you write against the map, returning JSON output for data elements.
Search amenities
Searches a bounding box for general amenities like cafes, schools, or banks using predefined criteria.
Search atms
Returns all ATM locations in a box, including the bank name, address, and if it's available 24/7.
Search for general categories like restaurants, schools, or hospitals within a defined map area.
Identify amenities (like cafes or ATMs) close to any given GPS coordinate without defining a large search box.
Run complex, developer-defined queries using specific OpenStreetMap Query Language syntax for niche data sets.
Pinpoint specialized services like EV charging stations or gas/fuel pumps in a target area.
Filter results to narrow searches using common tags, such as looking only for 'Italian' restaurants or 'Supermarket' shops.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Overpass (OpenStreetMap): 16 Tools for Geospatial Queries
Use these specialized tools to query every type of location data from OpenStreetMap—from specific shops to nearby amenities—all through a structured, reliable interface.
019d8469custom query
Runs any custom Overpass QL query you write against the map, returning JSON output for data elements.
019d8469search amenities
Searches a bounding box for general amenities like cafes, schools, or banks using predefined criteria.
019d8469search atms
Returns all ATM locations in a box, including the bank name, address, and if it's available 24/7.
019d8469search by name
Finds specific OpenStreetMap elements by their recorded name, returning full details like phone numbers or websites.
019d8469search by tag
Filters results in a bounding box using specific OSM tags (key/value), letting you find highly specialized features.
019d8469search charging stations
Searches for EV charging stations, detailing connector types, speeds, and operator info within a given area.
019d8469search fuel stations
Provides names, brands, addresses, and fuel type availability for gas pumps in a bounding box.
019d8469search hospitals
Retrieves hospital and clinic details, including phone numbers, specialties, and emergency services info.
019d8469search hotels
Finds hotels in a box, giving star ratings, addresses, websites, and room information.
019d8469search nearby
Locates any OpenStreetMap element near specific coordinates without needing to define a full search rectangle.
019d8469search nearby amenities
Finds common amenities (like pharmacies or ATMs) close to a location using only coordinates, skipping the box definition.
019d8469search parks
Lists green spaces and parks in a bounding box, detailing their size, features, and operator contact info.
019d8469search pharmacies
Searches for drugstores in a bounding box, giving opening hours, phone numbers, and dispensing details.
019d8469search restaurants
Finds restaurants in a bounding box. You can narrow the search by cuisine (e.g., 'Italian' or 'Mexican').
019d8469search schools
Retrieves school locations and details, including capacity, phone numbers, and addresses.
019d8469search shops
Searches for retail outlets in a bounding box. You can filter by shop type, such as 'Supermarket' or 'Electronics'.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Overpass (OpenStreetMap), then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
You connect your AI client directly to Overpass, which lets you query the massive OpenStreetMap database. You're looking at a global map of data—everything from restaurants and hospitals to EV chargers and custom-tagged features. No API key needed; you just talk to it.
Finding Specific Facilities:
- Need to know what's around? Use
search_restaurantsto find dining spots, narrowing the search by cuisine like 'Mexican' or 'Italian.' You can check out local shops usingsearch_shops, filtering results for things like 'Supermarket' or 'Electronics'. If you’re looking for education,search_schoolspulls up locations with details on capacity and phone numbers. For medical needs,search_hospitalsgives you clinic info, specialties, and emergency service contacts, whilesearch_pharmaciestracks drugstores, showing opening hours and dispensing specifics. - Need to find a hotel?
search_hotelspulls up local accommodations, giving you star ratings, addresses, websites, and room details. Want to stick to the basics?search_amenitiessearches a defined area for general spots like banks or cafes. For something more specific,search_atmsreturns all ATM locations in a box, detailing the bank name, address, and whether it's open 24/7. - Don't want to search by type? You can narrow down results using
search_by_name, finding elements based on their recorded names and getting full details like phone numbers or websites. For super specialized searches, usesearch_by_tagto filter a bounding box using specific OSM tags (key/value) that general searches miss.
Pinpointing Assets Near Coordinates:
- Don't have a perfect search area? Use
search_nearbywhen you know coordinates; it locates any OpenStreetMap element near those points without needing a full rectangle. For common amenities like pharmacies or ATMs, usesearch_nearby_amenities, which finds these spots using only GPS coordinates. You can also find green spaces withsearch_parksin a bounding box, getting details on size and operator contacts.
Tracking Specialized Infrastructure:
- You're looking at infrastructure?
search_charging_stationspinpoints EV charging points, giving you connector types, speeds, and the operator's info for that area. For gas pumps,search_fuel_stationsprovides names, brands, addresses, and which fuel types are available in a bounding box.
Advanced Mapping Queries:
- Got complex data needs? You can run any custom query you write using
custom_query, feeding your own Overpass QL syntax to get JSON output for specific data elements. For finding dining spots or shops, you can also use the more general search tools:search_restaurantsfinds eating places andsearch_shopssearches retail outlets. - If you want to find basic points of interest without a strict box,
search_nearby_amenitieshandles that for common amenities like pharmacies. If you just need to know what's generally around coordinates, usesearch_nearby. These tools give your agent direct access to the world’s map data.
How Overpass (OpenStreetMap) MCP Works
- 1 Your agent identifies the location data needed (e.g., a bounding box or coordinates) and the type of facility you want to find.
- 2 The client calls one of the specific tools—like
search_restaurants—passing the necessary geographic parameters. - 3 The server executes the Overpass QL query against OpenStreetMap and returns structured JSON data containing all discovered names, addresses, and details.
The bottom line is, you get raw, reliable location intelligence without needing to write any map-query code yourself.
Who Is Overpass (OpenStreetMap) MCP For?
This server is for anyone who needs real-world data mapped out. Think urban planners analyzing neighborhood flow, travel agencies building itinerary tools, or developers integrating location services into apps. It’s perfect for the ops engineer who's tired of clicking through multiple map layers just to find one piece of required information.
Analyzes patterns by running search_by_tag across large areas, comparing amenity density (e.g., finding if parks correlate with hospitals).
Integrates location context into an app using tools like search_nearby to provide real-time directions or point-of-interest suggestions.
Checks a destination's readiness by running targeted searches, such as finding both search_hotels and search_restaurants in one go.
What Changes When You Connect
- Find everything you need in one go. Instead of running separate queries for hospitals, ATMs, and schools, your agent can combine calls to
search_hospitals,search_atms, andsearch_schoolsto map a full service area. - No more bounding box headaches. If all you have is a GPS coordinate (like the center of a neighborhood), use
search_nearbyorsearch_nearby_amenitiesto get results instantly, without guessing coordinates. - Deep search capability: Use
search_by_tagwhen general searches fail. This lets your agent look for super-specific, niche OSM features that wouldn't show up in a basic amenity query. - Cuisine filtering is built in. When looking for food, don't just use
search_restaurants. You can specify 'Japanese' or 'Vegan' directly to get hyper-focused results via the dedicated tool. - Essential infrastructure tracking: Quickly locate critical assets like EV charging stations (
search_charging_stations) and fuel pumps (search_fuel_stations), making it perfect for logistics planning.
Real-World Use Cases
Planning a cross-country road trip
The agent knows the traveler needs to refuel and find lodging. It automatically runs search_fuel_stations and then, based on proximity, calls search_hotels. Finally, it checks for nearby charging points using search_charging_stations at the destination coordinates.
Analyzing a new neighborhood's amenities
A city planner needs to see if services are evenly distributed. They run search_amenities (general mix) and then layer in specific data using search_parks and search_schools. This provides a full, quantitative view of the area's infrastructure.
Finding specialized medical care
A user needs to find specialty care. The agent first uses search_hospitals, but if that fails, it falls back to the more specific search_pharmacies and then uses search_by_name to confirm a known specialist clinic.
Debugging an application's location logic
A developer needs to test if their app can find services near its starting point. They use the coordinates with search_nearby_amenities. This tests immediate proximity without requiring a large, inaccurate bounding box.
The Tradeoffs
Guessing the Bounding Box
The user tries to find amenities in 'downtown' by guessing coordinates like (40.7,-73.9,40.8,-73.8). This is inefficient and might miss things on the edges.
→
If you have a general area, use search_amenities with the best possible bounding box parameters. If all you have are coordinates, skip the bbox and jump straight to search_nearby_amenities. That's the right call.
Using one search for everything
The user tries to find both gas stations and hotels using only search_shops because it seems like a general purpose tool.
→
Don't mix categories. Use the specific tools: call search_fuel_stations for pumps, and then call search_hotels for lodging. Each one has unique data points you need.
Over-relying on general searches
The user runs a wide search_amenities but the results are too broad (e.g., they get gas stations when they only wanted dentists).
→
Always try to narrow it down first. If you know it's a pharmacy, use search_pharmacies. If you need something highly specific that isn't listed, fall back to the ultimate tool: custom_query.
When It Fits, When It Doesn't
Use this server if your primary goal is locating physical places and services on Earth. You should call it when you need data like 'Where are the nearest schools?' or 'Find all EV charging stations near X.'
Don't use it if you only need to analyze abstract data (like stock market trends) or process text logs. For pure code analysis, stick to dedicated code tools. If your query is too complex for a single tool—for instance, finding the overlap between 'restaurants' and 'parks' in one go—you must chain multiple calls using different tools like search_restaurants followed by search_parks. This server works best when you know what type of data you are looking for.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Overpass API. 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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 16 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Finding local amenities shouldn't require cross-referencing three separate government websites.
Today, finding basic infrastructure information is a manual mess. You might start on Google Maps to find restaurants, then open the city planning website for school locations, and finally check a different utility site just for ATM details. This means copying addresses back and forth, opening six tabs, and assembling fragments of data.
With this MCP server, you pass one prompt: 'Map all amenities in this area.' The agent handles the calls to `search_amenities`, `search_schools`, and `search_atms` automatically. You get a single, structured JSON payload with everything you need—names, addresses, and details—without lifting a finger.
Overpass (OpenStreetMap) MCP Server: Get actionable location data.
The old way meant accepting limited views. You were stuck with whatever API or database you paid for, missing the global context provided by OpenStreetMap's massive, community-sourced dataset.
Now, your agent taps into a single source of truth that covers everything from niche shops (`search_shops`) to high-level infrastructure (`search_charging_stations`). You get raw data power, instantly.
Common Questions About Overpass (OpenStreetMap) MCP
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.
How should I format the query when using the `custom_query` tool? +
The input must be valid Overpass QL syntax. The system automatically handles JSON formatting for output. Remember to include out geom; if you need geometric data points.
What specific details does the `search_atms` tool return about a location? +
It provides more than just locations. The results include the operator or bank name, full addresses, 24/7 availability status, and network information for each ATM found.
If my search using `search_by_tag` comes up empty, what might be wrong? +
The issue is likely with the tag key or value provided. Double-check that your OpenStreetMap tags are accurate and try broadening your bounding box coordinates.
Are there any limitations on how many times I can run `search_amenities`? +
Since Overpass is a free public service, the server manages usage limits for stability. For very high-volume tasks, consider batching your requests or using the custom_query tool for optimized bulk fetching.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
NOAA Forecast — US Weather Predictions
Official NWS weather forecasts for any US location: 7-day daily forecasts, 156-hour hourly forecasts, raw grid data, and meteorologist forecast discussions from 122 Weather Forecast Offices.
IBGE Agregados (SIDRA)
Access official Brazilian statistical data from IBGE SIDRA — query surveys, metadata, variables, and geographic levels directly.
Fairing
Analyze customer insights via Fairing — manage post-purchase surveys, track responses, and query zero-party data through your AI agent.
You might also like
ArcXP
Automate newsroom publishing via ArcXP — manage, search, and update articles, photos, and videos directly from any AI agent.
Eventbrite Alternative
Manage your Eventbrite events — audit organizations, attendees, and orders via AI.
Salary.com API
Access salary benchmarks — audit compensation and jobs via AI.