com.battery-snap/batterysnap

What it mainly works on, as our AI model read its tool descriptions: nothing outside itself: it only answers questions.

None of its 13 tools are described as changing anything.

• brandsreads or searches

  “Return the mobile devices brands for which we have battery statistics, along with the number of distinct models, the number of devices recorded per brand, and the largest single-model device count wi…”

  Publisher declares: read-only yes · idempotent yes · open-world no

  7 inputs

  • min_device_countinteger or null“Drop entries with fewer than this many recorded devices.”
  • max_device_countinteger or null“Drop entries with more than this many recorded devices.”
  • min_model_countinteger or null“Drop brands with fewer than this many distinct models.”
  • max_model_countinteger or null“Drop brands with more than this many distinct models.”
  • limitinteger or null“Return at most this many entries.”
  • offsetinteger or null“Skip this many entries before returning results — use with `limit` to page through a long list.”
  • fieldsarray or null“Optional whitelist of attribute names to keep in each returned entry, used to shrink the response.”
• modelson 3 other serversreads or searches

  “Return the mobile devices models of the given brands for which we have battery statistics, along with the brand each model belongs to, the number of devices recorded, the average battery temperature …”

  Publisher declares: read-only yes · idempotent yes · open-world no

  7 inputs

  • brandsarray or null“One or more lowercase Android device brand identifiers (e.g.”
  • min_device_countinteger or null“Drop entries with fewer than this many recorded devices.”
  • max_device_countinteger or null“Drop entries with more than this many recorded devices.”
  • sortstring“Sort order of the returned models: 'name' (default, alphabetical by brand then model) or 'device_count' (most recorded devices first).”
  • limitinteger or null“Return at most this many models (applied after filtering and sorting).”
  • offsetinteger or null“Skip this many entries before returning results — use with `limit` to page through a long list.”
  • fieldsarray or null“Optional whitelist of attribute names to keep in each returned entry, used to shrink the response.”
• deviceson 5 other serversreads or searches

  “Return the list of individual physical devices matching one or more (brand, model) pairs for which we have battery statistics.”

  Publisher declares: read-only yes · idempotent yes · open-world no

  2 inputs, 1 required

  • pairsarrayrequired“One or more {brand, model} pairs to look up.”
  • fieldsarray or null“Optional whitelist of attribute names to keep in each returned entry, used to shrink the response.”
• device_summaryreads or searches

  “Return aggregated battery metrics for ONE specific device: average / min / max temperature, average battery level, mean charge time per power source (AC, USB, wireless) and mean discharge time over a…”

  Publisher declares: read-only yes · idempotent yes · open-world no

  1 input, 1 required

  • device_uidstringrequired“Stable device UUID returned by the `devices` tool.”
• model_summaryreads or searches

  “Aggregate battery metrics across ALL devices of a given brand+model.”

  Publisher declares: read-only yes · idempotent yes · open-world no

  2 inputs, 2 required

  • brandstringrequired“Lowercase Android brand identifier (e.g.”
  • modelstringrequired“Model name, matched against resolved street name (e.g.”
• fleet_totalsreads or searches

  “Live fleet-wide counters: total devices, models, snapshots, sessions, the running snapshot-ingest rate (snapshots/sec) and the timing of the last insert batch.”

  Publisher declares: read-only yes · idempotent yes · open-world no

  Takes no inputs.

• fleet_summaryreads or searches

  “Aggregate battery metrics across the entire fleet, or across one brand when `brand` is provided.”

  Publisher declares: read-only yes · idempotent yes · open-world no

  1 input

  • brandstring or null“Optional lowercase brand identifier.”
• top_devices_by_uptimereads or searches

  “Return the devices with the longest single uptime ever recorded between reboots (max_elapsed_time).”

  Publisher declares: read-only yes · idempotent yes · open-world no

  3 inputs

  • brandstring or null“Optional lowercase brand filter.”
  • modelstring or null“Optional model filter — matches resolved street name or raw Build.MODEL, case-insensitive.”
  • limitinteger“Number of devices to return, 1..100.”
• top_devices_by_live_uptimereads or searches

  “Same as `top_devices_by_uptime`, but restricted to devices that have not yet rebooted past their recorded maximum — meaning the uptime is currently still climbing.”

  Publisher declares: read-only yes · idempotent yes · open-world no

  3 inputs

  • brandstring or null“Optional lowercase brand filter.”
  • modelstring or null“Optional model filter — matches resolved street name or raw Build.MODEL, case-insensitive.”
  • limitinteger“Number of devices to return, 1..100.”
• top_devicesreads or searches

  “Rank INDIVIDUAL devices by any battery metric — the general-purpose leaderboard.”

  Publisher declares: read-only yes · idempotent yes · open-world no

  6 inputs, 1 required

  • metricstringrequired“Which battery metric to rank on.”
  • orderstring“'desc' (default) ranks the highest values first, 'asc' the lowest.”
  • brandstring or null“Optional lowercase brand filter.”
  • modelstring or null“Optional model filter — matches resolved street name or raw Build.MODEL, case-insensitive.”
  • limitinteger“Number of devices to return, 1..100.”
  • min_snapshotsinteger“Ignore devices with fewer snapshots than this.”
• top_modelson 2 other serversreads or searches

  “Rank device MODELS by any battery metric, aggregating across every device of that model.”

  Publisher declares: read-only yes · idempotent yes · open-world no

  5 inputs, 1 required

  • metricstringrequired“Which battery metric to rank on.”
  • orderstring“'desc' (default) ranks the highest values first, 'asc' the lowest.”
  • brandstring or null“Optional lowercase brand filter.”
  • limitinteger“Number of devices to return, 1..100.”
  • min_devicesinteger“Ignore models backed by fewer devices than this.”
• device_rankingreads or searches

  “Answer 'is MY phone normal?' — rank one device's metric against other devices of the same model AND against the whole fleet, in one call.”

  Publisher declares: read-only yes · idempotent yes · open-world no

  2 inputs, 1 required

  • device_uidstringrequired“Stable device UUID returned by `devices`, `top_devices` or the share flow.”
  • metricstring“Which battery metric to rank on.”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.