Skip to content
Data Breach Search Engine & Leak Checker logo

Data Breach Search Engine & Leak Checker MCP server

Which MCP servers are Data Breach Search Engine & Leak Checker's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-11-01

← Back to Data Breach Search Engine & Leak Checker

Whose server it is
  • Registry namecc.checkleaked/spotify-dataverified in the MCP registry

The registry name sits under checkleaked.cc. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-11-01
  • Stateanswerschecked 2026-11-01
  • Tools12
  • Server calls itselfspotify-data
  • Server version0.1.0
  • Protocol version2025-06-18

On 2026-11-01 the server answered initialize and tools/list without a sign-in. First answer in 299 ms.

Should an agent connect itSkip it
  • Its tools do none of the product's use cases we checked: check whether an email address appears in known breaches; see which passwords tied to an account have leaked; search leaked records by company domain.
  • Checked on 3 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 3, the first on 2026-11-01
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
  • What an agent can do with it0 of 3 use cases
  • Answeredmeasuring3 of the 7 daily checks it takes to print a share
  • Median first answer304 ms
  • Space in an agent's context≈ 2,060 tokensthe definitions of all its tools (13), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 13 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • cannot · check whether an email address appears in known breaches
  • cannot · see which passwords tied to an account have leaked
  • cannot · search leaked records by company domain

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers12 tools · read 2026-11-01
  • search

    Search the Spotify catalog by name to find ids for the other tools. `type` picks what to search: tracks, artists, albums or playlists. Returns up to `limit` hits (max 20) with id, name, key fields and open.spotify.com URL. For track…

  • get_tracks

    Track details for up to 50 tracks in one call: name, artists, album, release date, duration, explicit flag, popularity, ISRC and (by default) lifetime play count. include_insights adds genres, moods, activities, BPM, credits, lyrics flag…

  • get_track_play_count

    Lifetime Spotify play counts (streams) for up to 50 tracks in one call, with track name, artists and release date. The fastest way to compare streams. A play count of 0 means fewer than 1,000 plays.

  • get_track_insights

    Genres, moods and activities (with Spotify's 0-1 weights), tempo in BPM, credits (writers, producers), lyrics flag and vocal languages for up to 50 tracks.

  • get_artists_stats

    Monthly listeners, followers, world rank, popularity, genres and top 5 cities (with listener counts) for up to 50 artists in one call.

  • get_artist_overview

    One artist's profile: monthly listeners, followers, world rank, top cities, top tracks with play counts, latest release, discography counts, related artists, biography and social links.

  • get_artist_insights

    An artist's sound profile from their top tracks: genres, moods and activities with 0-1 weights, and tempo (average, min, max BPM). Up to 20 artists per call.

  • get_related_artists

    Artists Spotify lists as related to ("Fans also like") the given artist.

  • get_album

    An album with its track list and (by default) every track's lifetime play count, plus the album total, release date, label, UPC and popularity.

  • get_playlist

    A playlist's name, owner, followers and description, plus `limit` tracks (max 100) from `offset` with lifetime play counts. Use next_offset from the answer to page through long playlists (later pages skip the metadata and cost one request).

  • get_chart

    Spotify Charts by country: top_tracks (Top 200), viral_tracks (Viral 50, daily only), top_artists or top_albums. Each entry has rank, previous and peak rank, days (or weeks) on the chart, movement and, for top_tracks, the streams in that…

  • isrc_lookup

    Find the Spotify track(s) for an ISRC (International Standard Recording Code), e.g. USUG11904206. Returns ids, names, artists, album and release date.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "spotify-data": {
      "type": "http",
      "url": "https://spotify-proxy.checkleaked.cc/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http checkleaked https://spotify-proxy.checkleaked.cc/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://spotify-proxy.checkleaked.cc/mcp as a custom connector in the settings.

Also shipped through: oci

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.