Skip to content

storebridge-mcp server

io.github.IsaiahDupree/storebridge-mcpIsaiahDupreestreamable-httpv1.0.0Scanned

Remote MCP connector for App Store + Google Play data via StoreBridge API. No auth required.

13 tools: 1 change things and 12 only read.

Tools: 0 delete, 0 irreversible, 1 write, 12 read.
  • Reads private data · 0
  • Reads text others write · 13
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

Anlyon alternative

1 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

What the storebridge-mcp server can do

The storebridge-mcp server is published by the GitHub account IsaiahDupree. It has 13 tools. It can create or change data (1 tool: autocomplete_suggest), but cannot delete data. 12 tools only read.

13 tools bring in text other people can write (search_apps, get_apps_batch, get_app and 10 more).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 2, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

13 tools

Changes things 1Claude Code: ask
  • autocomplete_suggestUp to 5 autocomplete completions for a partial search query.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Up to 5 autocomplete completions for a partial search query. First-class on both stores.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 12Show 12 read-only tools
  • get_appFull details for one app: description, version, release dates, content rating, genres, screenshots, languages, rating (with histogram and current-version stats), version history, s…Reads text others writeNo findings

    Why it is in this group

    • The name "get_app" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Full details for one app: description, version, release dates, content rating, genres, screenshots, languages, rating (with histogram and current-version stats), version history, size, installs, IAP flag, privacy policy, and store-specific extras. {id} is the Apple trackId (numeric string, e.g. 6448311069) or the Google package name (e.g. com.whatsapp).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_app_datasafetyGoogle Play "Data safety" section for one app: data shared, data collected, security practices, and privacy policy URL.Reads text others writeNo findings

    Why it is in this group

    • The name "get_app_datasafety" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Google Play "Data safety" section for one app: data shared, data collected, security practices, and privacy policy URL. Google only — passing store="apple" returns a not_supported error.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_app_permissionsGoogle Play declared device/data permissions for one app, grouped by permission group.Reads text others writeNo findings

    Why it is in this group

    • The name "get_app_permissions" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Google Play declared device/data permissions for one app, grouped by permission group. Google only — passing store="apple" returns a not_supported error.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_app_reviewsReviews for one app.Reads text others writeNo findings

    Why it is in this group

    • The name "get_app_reviews" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "get_app_reviews" says "get" and "review": it reads comments, which other people can write.
    • untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Reviews for one app. Apple reviews come from the customerreviews RSS feed and are hard-capped at 500 per app per country (50/page x pages 1-10); page>10 returns an error, and sort="rating" is not supported for Apple. Google reviews are token-paginated and effectively unbounded — pass the nextToken from a prior call's pagination to page forward.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_apps_batchResolve a single Apple app by bundleId (e.g.Reads text others writeNo findings

    Why it is in this group

    • The name "get_apps_batch" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Resolve a single Apple app by bundleId (e.g. com.burbn.instagram), or fetch many apps at once with a comma-separated ids batch (Apple up to ~200 ids in one round-trip; Google fans out and coalesces). A batch request returns an "apps" array; a bundleId request returns a single "app". Supports store="both" for batch lookups.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_aso_keywordsDirectional keyword ideas for a seed term, each with a difficulty score/label, traffic score, result count, and top competitors — derived from live search/suggest results, not pane…Reads text others writeNo findings

    Why it is in this group

    • The name "get_aso_keywords" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Directional keyword ideas for a seed term, each with a difficulty score/label, traffic score, result count, and top competitors — derived from live search/suggest results, not panel data. Every result is labeled estimated:true.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_aso_rankPoint-in-time rank of one app across up to 20 keywords (one live search per keyword, fan-out capped at 20).Reads text others writeNo findings

    Why it is in this group

    • The name "get_aso_rank" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Point-in-time rank of one app across up to 20 keywords (one live search per keyword, fan-out capped at 20). Every result is labeled estimated:true. This is a snapshot, not rank tracking over time.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_categoriesList categories for a store.Reads text others writeNo findings

    Why it is in this group

    • The name "get_categories" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    List categories for a store. Apple returns its static 6000/7000-range genre map; Google returns its categories() constants.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_chartsRanked top-chart entries (App summary plus rank) for a store.Reads text others writeNo findings

    Why it is in this group

    • The name "get_charts" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Ranked top-chart entries (App summary plus rank) for a store. type is free/paid/grossing (Apple also supports new/newfree/newpaid). category is an Apple genre id (e.g. 6007) or a Google category constant (e.g. PRODUCTIVITY); omit for the overall chart. Google list() may return an empty array with meta.stale=true when a region is broken.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_developerA developer record plus their published apps.Reads text others writeNo findings

    Why it is in this group

    • The name "get_developer" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    A developer record plus their published apps. {id} is the Apple artistId (numeric) or the Google developerId string (e.g. "Google LLC").

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_similar_apps"Customers also bought" / related apps for one app.Reads text others writeNo findings

    Why it is in this group

    • The name "get_similar_apps" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    "Customers also bought" / related apps for one app. First-class on both stores.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • search_appsSearch apps on the Apple App Store, Google Play, or both.Reads text others writeNo findings

    Why it is in this group

    • The name "search_apps" says "search": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Search apps on the Apple App Store, Google Play, or both. Returns matching apps with store, title, developer, icon, price, rating, category, and url. Use store="both" to fan out to both engines and merge results. Apple limit is clamped to 50; Google supports 1-250. The price filter (free/paid) only applies to Google.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write13
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:58 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
1
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://storebridge-mcp.vercel.app/mcp: tools/list returned 13 tools to an anonymous client, including autocomplete_suggest (write)

    What this check looks for

Posture changes

  1. Nov 20, 2026
    • HTTP status of an anonymous initialize: 503 to 200
    • tools/list served without credentials: no to yes
    • Tools that change things, listed without credentials: 0 to 1
    • Protocol version: none to 2025-06-18
  2. Nov 13, 2026
    • HTTP status of an anonymous initialize: 200 to 503
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 1 to 0
    • Protocol version: 2025-06-18 to none

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. HTTP status of an anonymous initialize: 503 -> 200; tools/list served without credentials: no -> yes; Tools that change things, listed without credentials: 0 -> 1 (and 1 more).View diff
    • HTTP status of an anonymous initialize: 503 to 200
    • tools/list served without credentials: no to yes
    • Tools that change things, listed without credentials: 0 to 1
    • Protocol version: none to 2025-06-18
  2. PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 503; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 1 -> 0 (and 1 more).View diff
    • HTTP status of an anonymous initialize: 200 to 503
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 1 to 0
    • Protocol version: 2025-06-18 to none

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http storebridge https://storebridge-mcp.vercel.app/mcp
claude mcp add --transport http storebridge https://storebridge-mcp.vercel.app/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__storebridge__search_apps",
      "mcp__storebridge__get_apps_batch",
      "mcp__storebridge__get_app",
      "mcp__storebridge__get_app_reviews",
      "mcp__storebridge__get_similar_apps",
      "mcp__storebridge__get_app_permissions",
      "mcp__storebridge__get_app_datasafety",
      "mcp__storebridge__get_charts",
      "mcp__storebridge__get_categories",
      "mcp__storebridge__get_developer",
      "mcp__storebridge__get_aso_keywords",
      "mcp__storebridge__get_aso_rank"
    ],
    "ask": [
      "mcp__storebridge__autocomplete_suggest"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as storebridge. Review it before you use it.

Capability tags behind 13 rules
  • mcp__storebridge__search_apps untrusted-input
  • mcp__storebridge__get_apps_batch untrusted-input
  • mcp__storebridge__get_app untrusted-input
  • mcp__storebridge__get_app_reviews untrusted-input
  • mcp__storebridge__get_similar_apps untrusted-input
  • mcp__storebridge__get_app_permissions untrusted-input
  • mcp__storebridge__get_app_datasafety untrusted-input
  • mcp__storebridge__get_charts untrusted-input
  • mcp__storebridge__get_categories untrusted-input
  • mcp__storebridge__get_developer untrusted-input
  • mcp__storebridge__autocomplete_suggest untrusted-input
  • mcp__storebridge__get_aso_keywords untrusted-input
  • mcp__storebridge__get_aso_rank untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.IsaiahDupree/storebridge-mcp/verify?hash=8348e7143c6c42566670128e12a4112d428bb1afc3736296f228142175aa43d5" | jq -e '.changed == false'

Pinned hash 8348e7143c6c, from Nov 2, 2026, 15:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.IsaiahDupree/storebridge-mcp/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.IsaiahDupree/storebridge-mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.IsaiahDupree/storebridge-mcp.svg)](https://radar.anlyon.com/servers/io.github.IsaiahDupree/storebridge-mcp)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:16 UTC.

storebridge-mcp server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the storebridge-mcp server safe?

No scan can promise that. What its definitions show: 13 tools, 1 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the storebridge-mcp server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the storebridge-mcp server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the storebridge-mcp server have?

13 tools: 1 write, 12 read. autocomplete_suggest, search_apps, get_apps_batch, get_app, get_app_reviews, get_similar_apps, get_app_permissions, get_app_datasafety and 5 more.

Does the storebridge-mcp server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the storebridge-mcp server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the storebridge-mcp server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 2, 2026.