Skip to content

MCP servers › ai.appgoat › mcp

MCP server · registry snapshot 2026-10-24 · last tested 2026-10-24

ai.appgoat/mcp

App Store and Google Play data: apps, reviews, keywords, charts, competitors, ASO playbooks. — the publisher's description

1 of 2 record checks metRead-only · tools listed 2026-10-24version 0.2.0streamable HTTP29 tools

Summary

ai.appgoat/mcp is a remote MCP server listed in the official MCP registry at version 0.2.0. On 2026-10-24 ProtocolProbe connected to it in read-only mode and read its inventory: 29 tools, 0 resources and 8 prompts.

Record checks

1 of 2 record checks met · 7 do not apply

  • met: Registry entry is active and says how to run it
  • not met: Source repository link opens
  • not applicable: Repository is not archived
  • not applicable: Code pushed to the repository in the 90 days before our check
  • not applicable: Repository publishes a security policy (SECURITY.md)
  • not applicable: Package names its licence with a standard (SPDX) identifier
  • not applicable: The version the registry lists can be installed and is not withdrawn
  • not applicable: npm package carries build provenance (attestation)
  • not applicable: No known critical or high advisory in the package or its dependencies

From public records, not a safety rating. Each check with its reason

Key facts

Runs
remote (hosted by the publisher)
Transport
streamable HTTP
Sign-in
none needed to open a session
Tools
29
Last tested
2026-10-24

Add to your client

Observed fact

This server accepted a session without any credential and lists 3 tools whose name or declaration suggests they change data (untrack_keywords, unwatch, apply_action). That is our reading of the names; we did not call them. Source: our connection, 2026-10-24.

How fresh this is

Live-tested
yes, a real session (not a text-only review)
Last tested
2026-10-24
Mode
read-only (no tool calls)
Latest version
0.2.0, published 2026-10-23 (registry, as of the 2026-10-24 snapshot)
First listed version
2026-10-23 (earliest version still in the registry; older removed versions would be earlier)
Registry data
snapshot 2026-10-24
Package and repository
checked 2026-10-24
Engine
mcp-runtime-engine@0.1.0 · sdk@1.32.0

Changes since the last refresh

New in the registry: not in the list of 2026-10-23, listed on 2026-10-24 with version 0.2.0 (published 2026-10-23).

Source: the official MCP Registry list on 2026-10-23 and on 2026-10-24.

What it is

What does this server offer?

Observed inventory
29tools
0resources
8prompts

None of its 29 tools are described as changing anything. For 29 the reading was uncertain, so no mark is shown.

  • “Look up one App Store or Google Play app: title, subtitle, developer, category, price, rating and histogram, installs (Play), version and dates, description, languages, and the same app in the other …”

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

    8 inputs, 1 required
    • appstringrequired“Any app identifier: App Store id (`284882215`, `id284882215`), Play package (`com.spotify.music`), Apple bundle id (`com.spotify.client`), store URL (URL-encod…”
    • storestring“Disambiguates `{app}` (a bundle id vs a Play package, or a name).”
    • countrystring“ISO country code(s): `us` (default), a comma list (paid plans), or `all` (Studio).”
    • max_ageinteger“Refresh from the store when our data is older than this many seconds (0 = always).”
    • waitboolean“Block up to ~25 s for a refresh (default).”
    • includearray“Extra sections: markets (every storefront), iap, versions (history with release notes), privacy (App Store labels), estimates (modelled downloads/revenue), cha…”
    • full_textboolean“Return long text (description, release notes, review bodies) in full instead of cut short”
    • formatstring“'markdown' (default): compact tables for reading.”
  • “Read an app's user reviews, newest first, up to 100 per page: rating, title, text, version, date, developer reply and AI tags (sentiment, intent, severity, topic) where tagged.”

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

    16 inputs, 1 required
    • appstringrequired“Any app identifier: App Store id (`284882215`, `id284882215`), Play package (`com.spotify.music`), Apple bundle id (`com.spotify.client`), store URL (URL-encod…”
    • storestring“Disambiguates `{app}` (a bundle id vs a Play package, or a name).”
    • countrystring“ISO country code(s): `us` (default), a comma list (paid plans), or `all` (Studio).”
    • ratingstring“Star rating filter, `1`, `1,2` or a range `1-3`.”
    • versionstring“Only reviews written for this app version.”
    • sincestring“Only items at or after this ISO date / datetime.”
    • untilstring“Only reviews created before this ISO date / datetime.”
    • qstring“Case-insensitive text search in the title and body.”
    • sentimentstring“AI sentiment filter (comma list): positive, neutral, negative.”
    • intentstring“AI intent filter (comma list): bug, crash, feature_request, pricing, ux, praise, spam, other.”
    • topicstring“AI topic filter (comma list of topic labels, case-insensitive, or topic ids).”
    • limitinteger“Max items to return.”
    • cursorstring“`meta.next_cursor` from the previous page.”
    • max_ageinteger“Refresh the latest US reviews when older than this many seconds.”
    • full_textboolean“Return long text (description, release notes, review bodies) in full instead of cut short”
    • formatstring“'markdown' (default): compact tables for reading.”
  • get_app_historyon 1 other server

    “An app's daily metric history per country: rating, ratings count, reviews count, installs (Play), star histogram and price, one row per day a value changed (default the last 90 days), with the change…”

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

    6 inputs, 1 required
    • appstringrequired“Any app identifier: App Store id (`284882215`, `id284882215`), Play package (`com.spotify.music`), Apple bundle id (`com.spotify.client`), store URL (URL-encod…”
    • storestring“Disambiguates `{app}` (a bundle id vs a Play package, or a name).”
    • countrystring“ISO country code(s): `us` (default), a comma list (paid plans), or `all` (Studio).”
    • fromstring“Start date (ISO), default 90 days before `to`.”
    • tostring“End date (ISO), default today.”
    • formatstring“'markdown' (default): compact tables for reading.”
  • get_app_changes

    “What changed in an app's store listing, newest first, with old and new values: version, release notes, title, subtitle, description, screenshots, icon, price, IAP, privacy, in-app events, badges, fea…”

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

    8 inputs, 1 required
    • appstringrequired“Any app identifier: App Store id (`284882215`, `id284882215`), Play package (`com.spotify.music`), Apple bundle id (`com.spotify.client`), store URL (URL-encod…”
    • storestring“Disambiguates `{app}` (a bundle id vs a Play package, or a name).”
    • countrystring“Only changes seen in these storefronts (comma list).”
    • fieldstring“Only these fields (comma list), e.g.”
    • sincestring“Only items at or after this ISO date / datetime.”
    • limitinteger“Max items to return.”
    • cursorstring“`meta.next_cursor` from the previous page.”
    • formatstring“'markdown' (default): compact tables for reading.”
  • get_app_keywords

    “The search terms an app ranks for in a country, best rank first, with popularity (5–100) and difficulty (0–100): from the weekly keyword universe plus your tracked keywords.”

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

    7 inputs, 1 required
    • appstringrequired“Any app identifier: App Store id (`284882215`, `id284882215`), Play package (`com.spotify.music`), Apple bundle id (`com.spotify.client`), store URL (URL-encod…”
    • storestring“Disambiguates `{app}` (a bundle id vs a Play package, or a name).”
    • countrystring“Two-letter country code (default 'us').”
    • max_rankinteger“Only terms where the app ranks at or above this position.”
    • limitinteger“Max items to return.”
    • cursorstring“`meta.next_cursor` from the previous page.”
    • formatstring“'markdown' (default): compact tables for reading.”
  • get_competitorson 8 other servers

    “An app's competitors, best first, scored from search terms both apps rank for (shared keywords) plus the store's similar-apps list.”

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

    5 inputs, 1 required
    • appstringrequired“Any app identifier: App Store id (`284882215`, `id284882215`), Play package (`com.spotify.music`), Apple bundle id (`com.spotify.client`), store URL (URL-encod…”
    • storestring“Disambiguates `{app}` (a bundle id vs a Play package, or a name).”
    • countrystring“Two-letter country code (default 'us').”
    • limitinteger“Max items to return.”
    • formatstring“'markdown' (default): compact tables for reading.”
  • “Find apps by name or id in AppGoat's catalog of both stores (~5M apps): exact title matches first, then prefix, then substring, most-rated first.”

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

    6 inputs, 1 required
    • qstringrequired“App name (≥ 2 characters) or exact id.”
    • storestring“Limit to one store: 'apple' or 'play'.”
    • categorystring“Store category name, e.g.”
    • limitinteger“Max items to return.”
    • cursorstring“`meta.next_cursor` from the previous page.”
    • formatstring“'markdown' (default): compact tables for reading.”
  • “A top free, paid or grossing chart for a store, country and category, today or on a past date: rank, app, developer, rating and the move since the previous capture (new entries marked), plus apps tha…”

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

    7 inputs
    • storestring“'apple' (default) or 'play'.”
    • countrystring“Two-letter country code (default 'us').”
    • chartstring“'free' (default), 'paid' or 'grossing'.”
    • categorystring“App Store genre id (`36` or `all` = all apps, `6014` = games, …) or Play category (`GAME_PUZZLE`; `APPLICATION` = all apps).”
    • datestring“The chart as of this date (ISO).”
    • limitinteger“How many ranks to return (default 100, max 200).”
    • formatstring“'markdown' (default): compact tables for reading.”
  • keyword_researchon 2 other servers

    “Keyword metrics and research for App Store / Google Play search terms: popularity (5–100), difficulty (0–100), result count and the #1 result's estimated daily downloads.”

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

    7 inputs, 1 required
    • termsarrayrequired“Search terms, 1–25 (at most 5 with include related or suggestions)”
    • storestring“Required unless `app` is given.”
    • countrystring“Two-letter ISO country code (storefront), e.g.”
    • appstring“Any app identifier (as in `{app}`); adds `app.rank` and `app.relevance` per term.”
    • waitboolean“Block up to ~25 s for a refresh (default).”
    • includearray“related (~10 related terms with metrics), suggestions (store autocomplete), top_apps (current top 10).”
    • formatstring“'markdown' (default): compact tables for reading.”
  • track_keywords

    “Deprecated: use watch with kind keyword (also reports rank moves as events).”

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

    6 inputs, 2 required
    • termsarrayrequired“Search terms to track, e.g.”
    • storestringrequired“'apple', 'play' or 'both' (tracks each term in each store)”
    • countriesarray“Two-letter country codes to track in (default ['us'])”
    • depthinteger“How many results to keep per ranking (default 100 Apple / 50 Play).”
    • tagsarray“Free-form labels.”
    • formatstring“'markdown' (default): compact tables for reading.”
  • untrack_keywords

    “Deprecated: use unwatch for keyword watches.”

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

    1 input, 1 required
    • idsarrayrequired“Tracked keyword ids”
  • list_tracked_keywords

    “Deprecated: use list_watches (keyword watches list their slots).”

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

    4 inputs
    • storestring“'apple' = Apple App Store (iOS), 'play' = Google Play (Android).”
    • countrystring“Only this two-letter country code.”
    • qstring“Only terms containing this text.”
    • formatstring“'markdown' (default): compact tables for reading.”
Show 17 more tools
  • get_keyword_ranks

    “Ranking history of a watched keyword: per capture the top 10 app ids, or with app, that app's rank over time (best, worst, latest).”

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

    5 inputs, 1 required
    • idintegerrequired“Keyword slot id (from a keyword watch, or list_tracked_keywords)”
    • appstring“Store app id; returns `rank` per point instead of the full id list.”
    • fromstring“Start, ISO date or datetime (default 90 days ago)”
    • tostring“End date or datetime (ISO), default now.”
    • formatstring“'markdown' (default): compact tables for reading.”
  • “Watch an app, a set of competitors or a set of keywords; significant changes become events (get_events, webhooks, daily email).”

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

    12 inputs
    • idinteger“Watch id to change (from list_watches).”
    • kindstring“'app' (one app), 'competitor_set' (several apps) or 'keyword' (search terms).”
    • appstring“Any app id, bundle id, package, store URL or name.”
    • competitorsarray“kind competitor_set: the apps to watch (any identifiers), up to 50”
    • termsarray“kind keyword: search terms, e.g.”
    • storestring“'apple', 'play' or 'both' (keyword watches without app; default both).”
    • countriesarray“Two-letter country codes to watch in (default ['us'])”
    • event_typesarray or null“Only these event types (default: every type of the kind)”
    • settingsobject“Thresholds: significance (0–1, default 0.5, minimum for an event), rank_move (default 5), keyword_top_n (10), chart_top_n (100), rating_drop (stars over 7 days…”
    • namestring or null“A label for the watch”
    • activeboolean“false pauses the watch, true resumes it”
    • formatstring“'markdown' (default): compact tables for reading.”
  • “Stop watches by id (from list_watches or watch): no new events, and their watched apps and keyword slots are freed.”

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

    1 input, 1 required
    • idsarrayrequired“Watch ids”
  • “Your watches (apps, competitor sets, keyword sets), newest first, with id, apps, terms, countries, event types and whether they are paused, plus watched apps and keyword slots used vs the plan's limi…”

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

    4 inputs
    • kindstring“Only this kind: 'app', 'competitor_set' or 'keyword'.”
    • appstring“Only watches that include this app (any id, bundle id, package, URL or name).”
    • storestring“Disambiguates `{app}` (a bundle id vs a Play package, or a name).”
    • formatstring“'markdown' (default): compact tables for reading.”
  • “Significant changes on your watched apps and keywords, newest first: type, one-line title, AI summary, significance (0–1), app, country and the key payload fields (version, changes old → new, rating …”

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

    9 inputs
    • typestring“Comma list of event types, e.g.”
    • appstring“Only events of this app (any id, bundle id, package, URL or name).”
    • storestring“Disambiguates `{app}` (a bundle id vs a Play package, or a name).”
    • watchinteger“Only events of this watch id.”
    • sincestring“Only items at or after this ISO date / datetime.”
    • min_significancenumber“Only events at least this significant (0–1).”
    • limitinteger“Max items to return.”
    • cursorstring“`meta.next_cursor` from the previous page.”
    • formatstring“'markdown' (default): compact tables for reading.”
  • get_developeron 2 other servers

    “A developer's profile: name, website, country, app count, total ratings and installs, all their apps (most-rated first) and the same company in the other store.”

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

    3 inputs, 1 required
    • devstringrequired“`apple:<artist id>`, `play:<developer id>`, a numeric Apple artist id, a Play developer id (often the name), or the website domain (`spotify.com`).”
    • storestring“Disambiguates `{app}` (a bundle id vs a Play package, or a name).”
    • formatstring“'markdown' (default): compact tables for reading.”
  • “Poll a background store fetch that another call started (its output said refreshing or still being fetched, with a job id): status, per-country progress.”

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

    2 inputs, 1 required
    • idstringrequired“`meta.freshness.job_id`, e.g.”
    • formatstring“'markdown' (default): compact tables for reading.”
  • list_connectionson 16 other servers

    “The user's connected App Store Connect, Play Console and Apple Ads accounts: connection id, provider, mode (actions or read_only), status and the linked apps.”

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

    2 inputs
    • providerstring“Only this provider: 'asc' (App Store Connect), 'play_console' or 'apple_ads'.”
    • formatstring“'markdown' (default): compact tables for reading.”
  • read_connection

    “Read live data from one of the user's connected accounts.”

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

    17 inputs, 2 required
    • idstringrequired“Connection id (con_…) from list_connections”
    • whatstringrequired“'reviews', 'listing' or 'ads' (Apple Ads)”
    • appstring“A linked app (App Store id or package name); required for reviews and listing”
    • unansweredboolean“reviews: only reviews without a developer reply”
    • ratingstring“reviews: star filter, '1', '1,2' or '1-3'”
    • countrystring“reviews: App Store territory filter (two-letter code)”
    • localestring“listing: locale such as en-US, de-DE (default en-US)”
    • viewstring“ads: 'campaigns' (default), 'ad_groups', 'keywords', 'negatives' or 'report'”
    • campaign_idstring“ads: campaign id (needed for ad_groups, keywords, negatives and every report level except campaigns)”
    • ad_group_idstring“ads: ad group id (needed for keywords; optional for negatives)”
    • levelstring“ads report: 'campaigns' (default), 'adgroups', 'keywords' or 'searchterms'”
    • startstring“ads report: start date YYYY-MM-DD (default 7 days before end)”
    • endstring“ads report: end date YYYY-MM-DD (default yesterday, UTC)”
    • limitinteger“Max rows: reviews up to 200 (default 100), ads up to 1000 (default 200)”
    • cursorstring“reviews: next_cursor from the previous page”
    • full_textboolean“Return long text (description, release notes, review bodies) in full instead of cut short”
    • formatstring“'markdown' (default): compact tables for reading.”
  • propose_action

    “Prepare a change to the user's connected account as a DRY RUN: nothing is written.”

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

    5 inputs, 2 required
    • typestringrequired“What to change: review.reply, listing.update, keywords.set, screenshots.upload, ads.keyword.bid, ads.keyword.add or ads.negative.add”
    • paramsobjectrequired“Params for the type (see the tool description)”
    • connectionstring“Connection id from list_connections; optional when exactly one active connection fits the type and app”
    • playbookstring“The playbook proposing this, e.g.”
    • formatstring“'markdown' (default): compact tables for reading.”
  • apply_action

    “Go ahead with an action from propose_action, after the user has seen its diff and agreed.”

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

    3 inputs, 1 required
    • idstringrequired“Action id (act_…) from propose_action”
    • forceboolean“Apply the recomputed diff even though the account changed since the dry run.”
    • formatstring“'markdown' (default): compact tables for reading.”
  • “One action from propose_action: its status (draft, pending_approval, approved, applied, failed, rejected), diff, guardrail scores, the provider result or error, the approve link and the audit trail.”

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

    2 inputs, 1 required
    • idstringrequired“Action id (act_…)”
    • formatstring“'markdown' (default): compact tables for reading.”
  • reject_action

    “Discard a draft or pending action the user does not want; nothing is written to the account.”

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

    3 inputs, 1 required
    • idstringrequired“Action id (act_…)”
    • reasonstring“Why (shown in the audit log)”
    • formatstring“'markdown' (default): compact tables for reading.”
  • “Run an App Audit of one app in one country: a 0–100 score, prioritised ASO actions with evidence, title / subtitle / keyword rewrites within the store character limits, and findings from listing, rat…”

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

    9 inputs, 1 required
    • appstringrequired“Any app identifier: App Store id (`284882215`, `id284882215`), Play package (`com.spotify.music`), Apple bundle id (`com.spotify.client`), store URL (URL-encod…”
    • storestring“Disambiguates `{app}` (a bundle id vs a Play package, or a name).”
    • countrystring“Two-letter country code, one storefront (default 'us').”
    • modestring“lite = cached data, fewer reviews and keywords (cheaper and faster for us; same price).”
    • freshboolean“Run again even if a recent audit exists.”
    • free_onlyboolean“Only run when it is the free first audit (402 free_audit_used otherwise).”
    • white_labelboolean“Studio: the shareable report shows the organization's branding (set in the dashboard under Settings → Report branding) instead of AppGoat's, e.g.”
    • labelstring or null“Your label for the audit list, e.g.”
    • formatstring“'markdown' (default): compact tables for reading.”
  • “Check on an App Audit that audit_app started (by its id, e.g.”

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

    2 inputs, 1 required
    • idstringrequired“Audit id from audit_app, e.g.”
    • formatstring“'markdown' (default): compact tables for reading.”
  • “What an app's users praise and complain about, from the AI tags on its reviews: top issues (topics behind negative, bug, crash, UX and pricing reviews) with last-30-days vs previous-30-days counts an…”

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

    6 inputs, 1 required
    • appstringrequired“Any app identifier: App Store id (`284882215`, `id284882215`), Play package (`com.spotify.music`), Apple bundle id (`com.spotify.client`), store URL (URL-encod…”
    • storestring“Disambiguates `{app}` (a bundle id vs a Play package, or a name).”
    • countrystring“One storefront; omit for every storefront we hold reviews for.”
    • since_daysinteger“How many days of reviews to analyse, 7–730 (default 180).”
    • versionsinteger“How many of the latest versions to break down.”
    • formatstring“'markdown' (default): compact tables for reading.”
  • list_playbookson 6 other servers

    “AppGoat playbooks: step-by-step recipes (which tools to call, credit budget, decision rules, output format) for app audits, app idea research, ASO metadata rewrites, weekly competitor digests, turnin…”

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

    1 input
    • namestring“A playbook name from the list, e.g.”

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 2026-10-24.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).

Counted from the listing

Parameters with a description
100% of 167
Tools with a description
100% of 29
Typical description length
406 characters

The tool set

Counted from the listing

Tools
29
Size of the list
about 11,006 tokens for an agent to load (characters ÷ 4)
Naming
27 of 29 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 0 of 29 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-10-24 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste:
https://api.appgoat.ai/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "mcp": {
      "url": "https://api.appgoat.ai/mcp"
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://api.appgoat.ai/mcp"
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"mcp","type":"http","url":"https://api.appgoat.ai/mcp"}'
Claude Code
claude mcp add --transport http mcp https://api.appgoat.ai/mcp
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://api.appgoat.ai/mcp --transport http
  • Optional settings the entry also lists (left out above): X-API-Key.
  • The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
  • The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Does the registry listing match what we found?

Feature #6

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.

Registry saysWe foundResultSource · date
Remote endpoint api.appgoat.ai/mcpSession openedmatchesour test · 2026-10-24
No credential declared as requiredOpened a session without any credentialmatchesour test · 2026-10-24

Choosing

Record checks

Public records · not a safety rating

1 of 2 record checks met · 7 do not apply

  • MetRegistry entry is active and says how to run itActive, with a package or a remote address.
  • Not metSource repository link opensThe registry entry gives no repository link.
  • Does not applyRepository is not archivedNo public GitHub repository to read.
  • Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
  • Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
  • Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
  • Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
  • Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
  • Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-24. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards

Common questions about ai.appgoat/mcp

Answered from the data above

Does ai.appgoat/mcp need an API key or sign-in?

It opened a session without any credential on 2026-10-24. The registry entry declares no required credential; no declaration is not a guarantee.

Has ai.appgoat/mcp been security tested?

Partly. 3 of the 16 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security verdict is published before verification.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Open without sign-in

It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-10-24
  1. Inventory: exercised
  2. Hidden instructions: exercised
  3. Real execution: not run · our policy
  4. Secret leak: not run · nothing to check it against
  5. Internal addresses: not run · our policy
  6. Unconfirmed changes: not run · our policy
  7. Bad input: not run · our policy
  8. Model requests: not run · nothing to check it against
  9. Sensitive questions: not run · nothing to check it against
  10. Folder boundary: not run · our policy
  11. Log leaks: not run · nothing to check it against
  12. Hidden content: not run · nothing to check it against
  13. Fake assistant turns: not run · an error was returned
  14. Token passthrough: not applicable
  15. Token audience: not applicable
  16. Sign-in redirect: not run · our policy
  17. Consent handling: not testable from outside
  18. Sign-in metadata: exercised

3 exercised13 not run (reason given)2 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 3 of the 16 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 3
  • 1Inventory
    tool-list
    Reads the declared tools, resources and prompts.exercised
  • 2Hidden instructions
    description-poisoning
    Looks for hidden instructions in tool descriptions.exercised
  • 18Sign-in metadata
    oauth-url-scheme
    Checks the published sign-in metadata for unsafe URLs.exercised
Not run, with the reason · 13
  • 3Real execution
    real-execution
    Calls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 4Secret leak
    canary-leak
    Plants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 5Internal addresses
    ssrf
    Checks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 6Unconfirmed changes
    write-without-confirmation
    Checks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 7Bad input
    error-handling
    Sends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 8Model requests
    sampling
    Checks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 9Sensitive questions
    elicitation-sensitive-data
    Checks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 10Folder boundary
    root-boundary
    Checks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 11Log leaks
    logging-side-channel
    Checks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 12Hidden content
    audience-hiding
    Checks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against
  • 13Fake assistant turns
    fake-assistant-turn
    Checks prompts that pose as the assistant's own words.The server returned an error when its prompts were read.not run · an error was returned
  • 16Sign-in redirect
    open-redirect
    Checks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy
  • 17Consent handling
    confused-deputy
    Checks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
Does not apply to this server · 2
  • 14Token passthrough
    token-passthrough
    Checks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable
  • 15Token audience
    token-audience-validation
    Checks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable

Source: our own test, 2026-10-24, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

  1. 0 msStarted a read-only session with the server's remote endpoint
  2. 823 msConnected after 0 redirects. No credential was sent or needed.
  3. Read the inventory: 29 tools, 0 resources, 8 prompts.
  4. 2,187 msFinished: 3 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified
pending: added in the weekly update
listed 2026-10-24; not classified yet
Pricing modelAI-classified
pending: added in the weekly update
the website is not read yet
Programming language
does not apply
no existing GitHub repository (server declares no repository link, so there is nothing to fetch)
Hosting type
registry · 2026-10-24
MCP capability
prompts, tools
our test · 2026-10-24
Transport
streamable HTTP
registry · 2026-10-24
Required credentials
none declared
registry · no declaration is not a guarantee
Package registry
does not apply
remote-only server: no package is shipped, so there is no package registry
Freshness
0–30 days
registry updatedAt · 2026-10-24
Lifecycle status
registry · 2026-10-24
License class
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Integrity hash
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Signature / provenance
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Dependency advisories
does not apply
ships no package, so there are no dependencies to audit
Popularity
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Publisher signals
not stated
no readable GitHub owner to describe
Maintenance
does not apply
server declares no repository link, so there is nothing to fetch
Environment
the publisher's infrastructure
where it runs, from the hosting type

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “ai.appgoat/mcp: MCP server record.” Data checked 2026-10-24. https://protocolprobe.com/mcp/servers/ai.appgoat/mcp

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

ProtocolProbe: 1 of 2 record checks met

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/ai.appgoat/mcp)](https://protocolprobe.com/mcp/servers/ai.appgoat/mcp)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.

Write to hello@protocolprobe.com · corrections log · methodology