Skip to main content
Glama

openchargemap-mcp-server: find stations

openchargemap_find_stations
Read-only

Find EV charging stations from the global Open Charge Map registry near a point or within a bounding box. Provide either a center (latitude + longitude + distance) or a boundingbox; optionally scope to a country with countrycode. This tool is coordinate-native and does not geocode place names — resolve a place like "Ballard, Seattle" to coordinates with openstreetmap_geocode first, then pass them here. Filter by connector type, minimum power (kW), operator/network, usage type (public/free/membership), charge level, operational status, and minimum charge points. Filter IDs are integers — resolve a connector or network name to its ID with openchargemap_lookup_reference (e.g. "CCS" -> 33). Each result includes title, address, distance from the search point, connections (type, power, count), operator, access rules, registry operational status, and the last-verified date. Results come back one page at a time: when a page reports truncated, repeat the same search with the reported nextOffset to read the next one.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
offsetNoMatching stations to skip before the returned page, for reading past a truncated result. Repeat the same search with the nextOffset value the previous call reported. One search reaches at most 500 stations, so 499 is the deepest offset that can return one — narrow the area or add filters to reach stations beyond that. Ordering is by distance and stable, but Open Charge Map is edited continuously, so a station added or removed between pages can shift what a later offset lands on.
levelidNoCharge level ID (1=Low <2kW, 2=Medium >2kW, 3=High >40kW/fast). Array OR-matched. Use 3 as a coarse "fast charging only" filter when a specific connector is not required.
distanceNoSearch radius from the center point, in the unit given by distanceUnit (default km). Max 500. Keep small (5-25) for dense urban areas; widen for rural coverage.
latitudeNoCenter latitude (WGS84 decimal degrees). Use with longitude + distance for a radius search. Resolve place names via openstreetmap_geocode first.
longitudeNoCenter longitude (WGS84 decimal degrees). Use with latitude + distance for a radius search.
maxresultsNoMaximum stations to return, ordered by distance from the search point. Max 200.
minpowerkwNoMinimum charging power in kW across any connection at the station. Use ~50 for DC fast charging, ~150 for high-power DC. Stations whose fastest connection is below this are excluded.
operatoridNoOperator/network ID, or array of IDs (OR-matched). Resolve a network name with openchargemap_lookup_reference (category "operators") — e.g. "Tesla", "ChargePoint".
boundingboxNoBounding-box search as an alternative to a center+radius. Mutually exclusive with latitude/longitude/distance — sending a boundingbox alongside a latitude or a longitude is rejected, not resolved in favour of one of them.
countrycodeNoRestrict to one country by ISO 3166-1 alpha-2 code (e.g. "US", "FR", "GB"). Omit for a global search. The server is global by default — there is no implicit country.
usagetypeidNoUsage/access type ID, or array (OR-matched). Resolve via openchargemap_lookup_reference (category "usagetypes") — e.g. Public=1, Public-Pay At Location=5, Public-Membership Required=4.
distanceUnitNoUnit for the distance parameter and the returned distance values.KM
statustypeidNoRegistry operational-status ID, or array (OR-matched). Resolve via openchargemap_lookup_reference (category "statustypes"). NOTE: registry status is operator-reported and can be stale — combine with dateLastVerified and openchargemap_get_station_comments to judge real-world reliability, do not treat it as ground truth.
minchargepointsNoMinimum number of charge points (stalls) at the station. Filters out single-point locations when you need a station likely to have an open stall.
connectiontypeidNoConnector type ID, or an array of IDs (OR-matched). Resolve names with openchargemap_lookup_reference — e.g. CCS (Type 2)=33, CHAdeMO=2, NACS/Tesla Supercharger=27, Type 2 socket=25, Type 1/J1772=1.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
capNoThe maxresults cap that was applied.
errorNoPresent when the call failed. Absent on success.
shownNoStations in the returned page.
noticeNoHow to reach the stations this page left out, or why it came back empty.
stationsNoMatching stations, ordered by distance from the search point.
truncatedNoTrue when matching stations were left out of the returned page.
nextOffsetNoThe offset to pass on an otherwise identical call to read the next page. Absent when nothing further was retrieved.
totalCountNoMatching stations this search retrieved, before the offset/maxresults page was taken. Open Charge Map publishes no match total and one search can only retrieve so deep, so this is exact only when the search reached the end of what Open Charge Map holds for the area — otherwise it is a floor that rises as deeper pages are read. The notice says which of the two applies.
attributionNoRequired attribution to Open Charge Map contributors under CC BY 4.0.
searchSummaryNoHuman-readable echo of the resolved search: location mode, scope, and active filters as the server applied them.

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true and openWorldHint=true, but the description adds substantial behavioral context: the registry is continuously edited so pagination offsets may shift, operational status is operator-reported and can be stale (recommending combination with dateLastVerified and comments), and boundingbox is mutually exclusive with latitude/longitude (rejected, not resolved). It also discloses the 500-station maximum. These details go well beyond the annotations and prepare the agent for real-world variability.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is longer than typical but every sentence earns its place: it front-loads the core action, then covers coordinate requirement, filter types, ID resolution, result fields, and pagination in a logical order. It avoids repetition and fluff, though it could be slightly trimmed without losing value. Still, it is well-structured and readable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 15-parameter tool with multiple search modes, filtering, and pagination, the description is exhaustive: it explains both search patterns, emphasizes the coordinate-native limitation, details the filter ID resolution, describes result contents, and covers pagination with offset behavior and staleness caveats. The presence of an output schema covers return structure, so nothing essential is missing for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter already has detailed semantics (e.g., distance max 500, levelid meaning, minpowerkw thresholds). The tool description only lists filter categories without adding new parameter-specific guidance beyond what the schema provides. It meets the baseline for a fully documented schema but does not elevate it; no extra insight like practical usage patterns beyond the schema's own examples.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb ('Find') and resource ('EV charging stations from the global Open Charge Map registry'), then immediately scopes the search modes (point/radius or bounding box) and optional country filter. It clearly distinguishes itself from sibling tools by being the station finder, while get_station fetches a single station, get_station_comments fetches comments, and lookup_reference resolves IDs. No ambiguity about what this tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use this tool and what to do beforehand: it does not geocode place names, so it instructs to resolve coordinates with openstreetmap_geocode first. It also directs users to resolve filter IDs via openchargemap_lookup_reference, and explains pagination (repeat with nextOffset for truncated results). This gives clear decision criteria and alternative usage, far beyond a generic 'use this for stations' statement.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.5/5.0
Disambiguation5/5

Each tool has a distinct role: discovery (find_stations), retrieval (get_station), community feedback (get_station_comments), and reference lookup (lookup_reference). No two tools overlap in purpose, and the descriptions reinforce their boundaries.

Naming Consistency5/5

All tool names share the 'openchargemap_' prefix followed by a clear verb_noun pattern (find_stations, get_station, get_station_comments, lookup_reference). The naming is uniform and predictive, making it easy for an agent to infer function.

Tool Count5/5

With 4 tools, the server is focused and well-scoped for a read-only EV charging station registry. Each tool serves an essential query need (search, detail, comments, reference data) without unnecessary clutter.

Completeness5/5

The tool set covers the full lifecycle of querying station data: resolving reference IDs via lookup_reference, searching with filters, retrieving detailed records, and accessing community feedback. This is complete for the stated purpose, with no obvious dead ends.