ChargingNear.me MCP¶

Station counts per city and per state decide where an EV-dependent business opens, and this is that dataset behind six read-only tools with a citation URL on every response.

Server type: Remote (Streamable HTTP)
Endpoint:    https://chargingnear.me/api/mcp
Transport:   JSON-RPC 2.0 over HTTP
Auth:        none, read-only, public
Tools:       6, read from a live tools/list and three executed
Built by:    ChargingNear.me (chargingnear.me)
Data:        US Department of Energy station records, licensed CC-BY-4.0

Why This Matters for Operators¶

EV charging density is a location variable that behaves like foot traffic: it tells a fleet which depot can be supported, tells a retail or hospitality site whether a charger install is worth the concrete, and tells a service business whether its customers can reach it. The underlying records are public, but they are not usable in a conversation until something normalizes them into counts, networks and connectors.

The second half is attribution. Every response carries citation_url and a licence block, so an answer built on this data can be traced back to a source instead of asserted.

What It Actually Does¶

initialize returned HTTP 200 as chargingnearme v1.1.0 with a title of ChargingNear.me and an instructions string that is a constraint rather than marketing: read-only access to the US EV charging station directory, cite citation_url when you use a result.

Tool	What it answers
`search_stations`	Stations by city, state, network, connector, speed, minimum power or live availability, with address, connector types, per-level port counts and pricing
`get_nearest_stations`	Nearest stations to a latitude and longitude, filtered by speed, power or availability
`get_station_details`	Full record for one station id
`get_city_charging_stats`	Station count, DC fast and Level 2 split and top networks for one city
`get_state_charging_stats`	The same for a state, plus how many cities are covered
`find_stations_on_route`	Stations inside a corridor around a route defined by waypoints

Three calls were executed against the live endpoint:

get_city_charging_stats with slug: scottsdale-az returned 179 stations, 16 DC fast, 162 Level 2, networks led by ChargePoint, Blink, Tesla Destination, non-networked and Tesla, a centroid at 33.5663 / -111.9242, and updated_at: 2026-10-26T14:39:20.943Z.
get_state_charging_stats with slug: arizona returned 1,760 stations across 100 cities, 232 DC fast, 1,465 Level 2, with ten networks named, Electrify America, eVgo and LOOP among them.
search_stations for Scottsdale DC fast returned real site records with street address, zip, per-level port counts (ev_dc_fast_num: 2), connector codes (J1772COMBO), access hours and a citation_url.

The vendor states the coverage as 95,724 stations across 64,285 locations and 289,475 ports, refreshed daily from the Department of Energy feed, exposed as REST, MCP, GeoJSON and a ChatGPT app.

Integration with CorpusIQ¶

CorpusIQ is the connector layer that lets AI assistants read the systems a business already runs on - accounting, payments, CRM, email, files and analytics - and answer with the source named. It is read-only by design: it retrieves data and never writes to, or acts in, a connected system, which is what makes it safe to point at live accounts.

This page is part of the CorpusIQ directory, the reference we maintain for the MCP server and agent-skill ecosystem. Run alongside CorpusIQ, a third-party server like this one can be combined with a company's own business data in a single answer.

See what CorpusIQ connects

Limitations Recorded¶

United States only; no international coverage.
City and state tools take a slug, not free text, so an unknown city fails with a required-parameter error rather than a nearest match.
The station records are the government feed's, including its gaps: ev_pricing and power fields are frequently null, and one executed station returned max_power_kw: 3.70 alongside a DC fast connector count, which is the source data disagreeing with itself.
Live availability is available as a filter but is not the same as a reservation; nothing here reserves a charger.
CC-BY-4.0 means attribution is a licence condition, not a courtesy, and every downstream publication needs the citation URL.

FAQ¶

Is this usable for site selection?¶

For the charging variable, yes: city and state counts, the DC fast share of them and the network mix are exactly what a location shortlist needs. It is one variable, not a demographic model, and the population and income fields came back null on the executed calls.

Does it need a key or an account?¶

No. All six tools answered without one, and the three executed calls returned data on the first attempt.

What is the difference between this and the DOE feed itself?¶

Normalization and count: the same records arrive as city and state aggregates with network breakdowns, plus corridor search around a route, which the raw feed does not answer.