AI Skill
SKILL.md

Domain knowledge for Charge Atlas — workflow patterns, data models, and gotchas for your AI agent.

Charge Atlas — global EV charging station data

Charge Atlas answers the question "where can I charge an electric vehicle here?" anywhere in the world. It exposes one consistent station shape and one consistent filter set across two coverage regions:

  • coverage: "us_canada" — the United States (50 states + DC + territories) and Canada. Authoritative, refreshed daily, includes private and planned sites alongside public ones.
  • coverage: "global" — every other country. Community-edited, strongest in the EU and UK, sparser in some emerging markets.

The right region is picked automatically from the search coordinates or country code; the AI never has to choose. The user-visible coverage field on every response simply labels which region produced the result so callers can warn appropriately (community-edited listings can be stale).

Interactive Map App

An interactive map dashboard is available alongside this chat. When the app panel is open, search results are automatically forwarded to the map — do NOT re-open the app. Just call the search and detail capabilities and the map will update with stations rendered as colored circle markers (green = DC Fast, orange = Level 2, gray = Level 1), click-through to station detail, and a panel list showing the top results.

Data Model

  • Station — A single physical charging location with one street address. Each station carries one or more EVSE ports (Electric Vehicle Supply Equipment) and one or more connector types. The same parking lot is one station even if it has 12 stalls.
  • Connector / Port — The physical plug. Common types: CCS Combo (most non-Tesla DC fast), CHAdeMO (older Japanese DC fast, Nissan Leaf), NACS / Tesla (Tesla Supercharger; growing US standard), J1772 (Level 2 AC; nearly all non-Tesla US/Canada AC), Type 2 Mennekes (European AC standard), Tesla Destination (Tesla-branded Level 2).
  • Charge LevelL1 (120V AC, ~5 mi/hr — wall outlet), L2 (208–240V AC, ~25 mi/hr — most public AC), DC (DC fast, 50–350 kW, 100–250 mi in 30 min).
  • Network — Operator brand (Tesla Supercharger, Electrify America, EVgo, ChargePoint, IONITY, Ionna, BP Pulse, Shell Recharge, Pod Point, etc.). Many stations are non-networked (e.g. workplace, hotel).
  • Statusavailable, in_use, out_of_order, planned, temporarily_unavailable. Real-time availability is partial: only some networks publish it, and freshness varies.

Coverage Regions

Regioncoverage tagNotes
United States (50 states + DC + territories)us_canadaDaily-refreshed catalogue; includes private, planned, and temporarily-closed sites
Canadaus_canadaSame catalogue — DC fast charging is well-covered
Everywhere elseglobalCommunity-edited; richer in EU and UK, sparser in some emerging markets

Searches by latitude/longitude or bounding box automatically pick the right region from the coordinates. Searches that take a country code respect that code directly. Route-corridor search is US/Canada-only — for international routes, use the journey-planner capability instead.

Key Patterns

  • Coordinates first: every search accepts latitude + longitude. Bounding-box search takes min_lat / min_lon / max_lat / max_lon (south-west and north-east corners). Distances are in statute miles unless specified.
  • Filter by charger speed with min_charge_level = L1 | L2 | DC. To find road-trip-capable stations, pass DC.
  • Filter by network by passing the network slug (e.g. Tesla, ChargePoint, EVgo, Electrify America, IONITY). Use the network listing capability to discover valid slugs for a country.
  • Free-text location search is global. Place names, neighborhoods, addresses, and postcodes are geocoded automatically. For best results pass a fully qualified place ("King's Cross, London, UK", "Madrid, Spain") rather than a bare postal code.
  • Station IDs are opaque tokens returned on every search row's id field. Pass them straight back into the detail capability — they round-trip unchanged. Detail responses for community-coverage stations also include up to five recent user reviews and check-in reports when available.
  • Vehicle compatibility filtering: pass vehicle (e.g. tesla-model-3, nissan-leaf, kia-ev6) on any search to drop chargers whose connector set is incompatible with that car. The vehicle catalog capability returns every supported model slug.
  • Network comparison: the network-comparison capability ranks two-to-eight named networks by station count in a country, returning each network's share of the compared total — useful for buy-decision questions.
  • Journey planning: the journey planner takes free-text origin and destination, geocodes both, fetches a driving polyline, and returns DC fast chargers along the route. The polyline is tagged route_kind: "driving" for a real road route or "approximate" for a straight-line fallback when no road route is available — surface that to the user when it's approximate.
  • Locale-aware units: search responses include a display_units hint derived from the host's BCP-47 locale (US/UK/Liberia/Myanmar → miles, everywhere else → km). All distances are also returned in both miles and km on every station so the renderer can pick the right one.
  • Auto-locate: when latitude/longitude are omitted, ChatGPT clients pass the coarse user location via _meta.openai/userLocation and Charge Atlas uses it to default the search center. Country-summary and search_by_location calls similarly default the country bias from the same hint.
  • Open-now: Charge Atlas only marks a station open_now: true when the hours string clearly says 24/7. Anything else is reported as unknown — half-broken hours parsing is worse than honest "we don't know".

Gotchas

  • Real-time availability is sparse. Many networks (especially private/workplace chargers and the long tail of small operators) do not publish live status. Treat results without a status field as "operational per last directory update", not "free right now". Always check the network's own app before driving to a single specific station.
  • Connector compatibility is critical. A Tesla Model 3 with a J1772 adapter can use J1772 and Tesla destination; a Nissan Leaf needs CHAdeMO for DC fast. Returning a station whose only DC port is CCS to a CHAdeMO car is a wrong answer. When the user names their car, narrow connector_types accordingly.
  • NACS transition is mid-flight. As of 2024–2026 Tesla Supercharger sites are opening to non-Tesla cars on a rolling basis. Open access is published per-station — not all Superchargers in a city are open to non-Tesla EVs at the same time.
  • DC kW ratings are a maximum, not a guarantee. A "350 kW" stall delivers that to a vehicle that can accept it; many EVs cap at 100–150 kW. Do not promise "30 minutes to 80%" without knowing the car's peak DC rate.
  • International journey planning is sampled, not exhaustive. For long international drives the planner samples several waypoints along the polyline and runs a nearby search at each — adequate for trip planning, but may miss chargers between sample points on extremely long routes.
  • coverage: "global" listings can be stale because the underlying directory is community-edited. A station marked operational there may have been decommissioned; cross-reference with the network's own site for high-stakes decisions.
  • Distance units: every station carries both distance_miles and distance_km. The response also includes a display_units hint chosen from the user's locale — render whichever the hint asks for. Pass units: "miles" or units: "km" to override.

Disclaimers

Coverage, real-time status, and network coverage vary by country and by network. This data is best-effort and not a substitute for the network's own routing app for time-critical or safety-critical journeys (long-range road trips, single-shot drives in unfamiliar territory). Pricing, plug-and-charge support, and amenity details (open hours, restrooms, food) are not guaranteed and should be confirmed at the network's own site.

Where the data comes from

Tool calls are routed to the appropriate upstream directory based on the location of the query (US/Canada uses the NREL Alternative Fuels Data Center; everywhere else uses Open Charge Map). Responses are normalized to a single Charge Atlas station shape (id, name, lat, lon, address, country, network, charge_level, connector_types, ports, status, coverage). Distances are converted to statute miles. No caching of station rows, no transformation of source values beyond shape normalization.

NREL Alternative Fuels Data Center
National Renewable Energy Laboratory (NREL), US Department of Energy

Authoritative directory of public, semi-public, and planned alternative fuel stations across the United States and Canada. Includes electric, hydrogen, biodiesel, ethanol (E85), CNG, LNG, and propane. Charge Atlas only surfaces the electric subset (~70K EV charging stations as of 2026). Refreshed daily.

~70,000 US/Canada EV charging stations
Source updated: Daily
We refresh: Real-time (proxied per request, no caching)
JSON HTTP API
United States (50 states + DC + territories) and Canada
Open Charge Map
Open Charge Map (operated by Open Charge Map contributors as a not-for-profit project)

Community-maintained global directory of EV charging locations. Listings are crowd-sourced and verified by network operators where available. Charge Atlas uses Open Charge Map for non-US results and as a global fallback.

~700,000 charging locations in 100+ countries
Source updated: Continuous (community contributions and operator feeds)
We refresh: Real-time (proxied per request, no caching)
JSON HTTP API
Global, with strongest coverage in EU, UK, and ANZ
OpenStreetMap (basemap tiles)
OpenStreetMap contributors

Basemap tiles rendered by CARTO for the interactive map UI. Not used for any data lookup — display only.

Source updated: Continuous (community-edited)
We refresh: On client request (tiles served by carto CDN)
Raster PNG tiles
Global
US data is sourced from the NREL Alternative Fuels Data Center, a public-domain US Government work. Non-US data is sourced from Open Charge Map and is licensed under CC BY-SA 4.0; downstream redistribution of the OCM portion must preserve attribution and share-alike terms.
Real-time charger availability is published by only a subset of networks and may be stale or absent. Do not rely on Charge Atlas as the sole source for safety-critical or time-critical driving decisions; confirm with the network operator's own app before departure.

Source availability last verified 2026-04-22.

Tools in this Server (11)

Charge Atlas Compare Networks

Compare two or more EV charging networks side-by-side in a given country. Returns each network's station count (and an estimated total when the underl...

Charge Atlas Get Country Summary

Get aggregate EV charging statistics for a country: total station count, breakdown by charger speed (DC fast / Level 2 / Level 1), and the top 20 netw...

Charge Atlas Get Station

Get full detail for a single charging station by Charge Atlas ID. Returns station name, full address, operator network, port count, supported connecto...

Charge Atlas Journey Planner

Plan an EV-friendly drive from origin to destination, with chargers along the way. Geocodes both endpoints, fetches a driving polyline, then surfaces ...

Charge Atlas List Connector Types

List the EV connector / plug types that Charge Atlas can filter on, with their charge level (L1 / L2 / DC), current type (AC / DC), max power in kW, a...

Charge Atlas List Networks

List EV charging network operators active in a country, with their station counts. Use the returned network names as comma-separated values for the 'n...

Charge Atlas List Vehicles

List the EV models that Charge Atlas can filter charging stations by. Each entry returns the model's slug (used as the 'vehicle' parameter on search c...

Charge Atlas Route Corridor

Find EV charging stations along a driving route corridor. Takes an ordered list of [lat, lon] waypoints and a corridor radius in miles, returns statio...

Charge Atlas Search By Bbox

Find public EV charging stations inside a geographic bounding box (map viewport). Pass the south-west corner as (min_lat, min_lon) and the north-east ...

Charge Atlas Search By Location

Find public EV charging stations near a free-text location anywhere in the world. The location string is geocoded internally and then queried for char...

Charge Atlas Search Nearby

Find public EV charging stations near a latitude/longitude coordinate. When the host provides ``openai/userLocation``, the coordinate is optional and ...

Frequently Asked Questions

What is the Charge Atlas MCP server?

Find EV charging stations anywhere in the world. Search by coordinates, map area, or driving route. Filter by speed (Level 1 / Level 2 / DC Fast), connector (CCS, CHAdeMO, NACS, J1772), and network. It provides 11 tools that AI agents can use through the Model Context Protocol (MCP).

How do I connect Charge Atlas to my AI agent?

Add the MCPBundles server URL to your MCP client configuration (Claude Desktop, Cursor, VS Code, etc.). The URL format is: https://mcp.mcpbundles.com/bundle/charge-atlas. Authentication is handled automatically.

How many tools does Charge Atlas provide?

Charge Atlas provides 11 tools that can be called by AI agents, along with a SKILL.md that gives your AI agent domain knowledge about when and how to use them.

What authentication does Charge Atlas require?

Charge Atlas uses open data APIs — no authentication required.

Setup Instructions

Connect Charge Atlas to any MCP client in minutes

https://mcp.mcpbundles.com/bundle/charge-atlas

What is MCP?

Model Context Protocol lets AI tools call external capabilities securely through a single URL. This bundle groups tools behind an MCP endpoint that many clients can use.

Use this bundle in 3 steps

  1. Copy the MCP URL above
  2. Open your AI tool and add a new MCP/connector
  3. Paste the URL and follow any auth prompts

Claude Desktop Users

Skip the manual setup! Use the .mcpb file format for one-click installation. Check the Claude Desktop tab for setup instructions.

Pick your tool tab for exact steps

Select ChatGPT, Cursor, Claude Code, or another tab for copy-paste config.

Other ways to use Charge Atlas

Same data, different audiences.

App

Polished interactive UI — explore the data visually with no setup.

Open the app

Try Charge Atlas now

No sign-up required. Open the interactive dashboard and start searching in seconds.