This server provides read-only access to live Apple App Store data for competitor research, ASO, and product analysis — no Apple developer account or API keys required. Capabilities include:
Search apps (search_app_store): Find apps by keyword, returning up to 50 slim results (ID, name, developer, rating, price).
Get full app profile (get_app_store_app): Fetch a complete public profile by numeric ID or App Store URL, including description, release notes, ratings, version history, screenshots, subtitle, in-app purchase flag, and privacy labels.
Compare multiple apps (compare_app_store_apps): Batch-fetch full profiles for several apps in a single call for side-by-side competitor comparison; individual failures don't break the batch.
Get customer reviews (get_app_store_reviews): Retrieve up to ~500 recent public reviews per storefront, sortable by most recent or most helpful.
Digest & summarize reviews (digest_app_store_reviews): Compress up to 500 reviews into a structured English digest (themes, complaints, praise, sentiment) via MCP sampling — works across foreign-language storefronts.
Analyze screenshots (get_app_store_screenshots): Fetch actual screenshot images (up to 8, iPhone or iPad) for visual analysis of positioning, onboarding flows, and paywall design.
Browse top charts (get_app_store_charts): Access top-free, top-paid, or top-grossing charts, filterable by category and country.
Key characteristics:
All tools are read-only and support a country parameter (ISO 3166-1 alpha-2, default: us).
Responses are cached in-memory for ~15 minutes (meta.fresh flag indicates cache status).
Data is sourced from Apple's public APIs and best-effort web scraping; no download counts, revenue estimates, or keyword rankings are available.
A compare_competitors MCP prompt packages the standard competitive analysis workflow.
Provides tools for searching, fetching metadata, comparing apps, retrieving reviews, screenshots, and top charts from the Apple App Store for competitor research and ASO analysis.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@App Store MCP Server compare Duolingo and Babbel in the US App Store"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An open-source MCP server for live Apple App Store competitor research.
It lets AI agents search apps, fetch public App Store metadata, compare competitors side by side, and retrieve reviews and top charts as structured JSON — for market research, ASO research, and product analysis.
It works with public competitor data only. The default, recommended uvx
setup below needs no Apple developer account, no API keys, and no database
(a separate, optional hosted alternative does require an API key — see
Hosted deployment).
Compare Duolingo, Babbel, and Busuu on the US Apple App Store.
Requires uv. Add to your MCP client config:
{
"mcpServers": {
"appstore": {
"command": "uvx",
"args": ["appstore-mcp"]
}
}
}Claude Code: claude mcp add appstore -- uvx appstore-mcp, or install as a
plugin: /plugin marketplace add LaurMost/appstore-mcp then /plugin install appstore-mcp
Claude Desktop: add the snippet above to claude_desktop_config.json
Cursor: add the snippet above to ~/.cursor/mcp.json
If your MCP client can't find uvx, use the absolute path from which uvx as
the command.
Related MCP server: mcp-store-scraper
The uvx setup above is still the primary, recommended way to use this
server — it needs no API key. A hosted HTTP instance is also available at
https://appstore-mcp.fastmcp.app/mcp for MCP clients that need a
network-accessible endpoint instead of a local stdio process. It requires an
API key, sent as an Authorization: Bearer <key> header. See
docs/adr/0012-additive-hosted-http-mode.md
for why this is additive rather than a replacement, and the trade-offs
involved.
Tool | What it does |
| Search apps by keyword (slim results: id, name, developer, rating, price) |
| Full public profile for one app: description, release notes, ratings, versions, screenshots, subtitle, in-app-purchase flag, privacy labels |
| Batch-fetch several apps (IDs or URLs) side by side in one call |
| Recent public customer reviews (up to ~500 per storefront) |
| Compress up to 500 reviews into a structured digest (themes, complaints, praise, sentiment) via MCP sampling — raw reviews never enter your context, and foreign-language storefronts are digested in English |
| An app's screenshots as actual images, so a multimodal model can analyze visual positioning, onboarding, and paywall design |
| Top-free / top-paid / top-grossing charts, overall or per category, per country |
All tools are read-only and take a country storefront parameter (ISO
3166-1 alpha-2, default us). One MCP prompt, compare_competitors, packages
the headline comparison workflow.
Responses are compact and normalized by default; get_app_store_app accepts
include_raw=true when you want Apple's unmodified lookup payload.
digest_app_store_reviews uses MCP sampling:
the tool asks your client's LLM to compress the reviews, so no API key is
needed. Not all MCP clients support sampling. If yours doesn't, either use
get_app_store_reviews for raw reviews, or enable the server-side fallback:
uvx "appstore-mcp[anthropic]" # + set ANTHROPIC_API_KEY
uvx "appstore-mcp[openai]" # + set OPENAI_API_KEYSet APPSTORE_MCP_SAMPLING_MODEL to override the fallback model. The digest
is LLM-generated data reduction, not ground truth — quotes may be translated
or paraphrased, and responses say so in meta.warnings.
Primary source: Apple's public iTunes Search/Lookup API.
subtitle, has_iap, and privacy come from the public App Store web
page; reviews and charts come from undocumented Apple feeds. These are
best-effort: when they break or return nothing, tools degrade gracefully
and say so in meta.warnings rather than failing or faking data.
Not available from public Apple data, so not provided: download counts, revenue estimates, keyword rankings, full review history, historical charts.
Apps are listed per-storefront: results, ratings, and reviews differ by
country, and an app can exist in one storefront but not another.
Results are cached in-memory for ~15 minutes; meta.fresh tells you whether
a response came from cache.
uv sync --dev
uv run pytest # offline fixture tests
uv run pytest -m live # live smoke tests against real Apple endpoints
uv run mypy
uv run ruff check . # lint
uv run ruff format . # format (Black-compatible style)fastmcp.json declares how to run the server from source (see
Project Configuration).
Use it to poke at the server directly, without a full MCP client:
fastmcp dev # launch the MCP Inspector against local source (stdio)
fastmcp run # run the server standalone (stdio)
fastmcp dev http.fastmcp.json # same, but over HTTP on localhost:8000Want a scriptable CLI instead of an MCP client? fastmcp generate-cli
connects to a running server and writes a standalone typed CLI (plus an
agent-ready SKILL.md) with one subcommand per tool - it queries over a
live connection, so a fastmcp.json/stdio target doesn't work here; start
the HTTP variant first, then point it at that:
fastmcp run http.fastmcp.json &
fastmcp generate-cli http://localhost:8000/mcp/ cli.pyThe real hosted deployment
(https://appstore-mcp.fastmcp.app/mcp, with an API key — see
Hosted deployment) works as a generate-cli/fastmcp list/fastmcp call target too, if you'd rather point at that than spin up
your own local HTTP server.
This is a local-iteration convenience only — the published package (uvx appstore-mcp) always runs over stdio via its own main() entrypoint,
regardless of what's declared here.
Some tests assert full response shapes via inline-snapshot. After an intentional change to a tool's output shape, regenerate them:
uv run pytest --inline-snapshot=fix,create # then review the diffOptionally, verify the whole stack through a real MCP client — Claude Code driving the local server over stdio against live Apple:
uv run python scripts/claude_code_integration_test.pyThis is a manual, on-demand check, not part of the default dev loop: it
requires a logged-in claude CLI and spends real
Anthropic API tokens per run.
This project is not affiliated with or endorsed by Apple. "App Store" is a trademark of Apple Inc.
MIT
Fetch full profiles for multiple apps (IDs or apps.apple.com URLs) in one batch for side-by-side competitor comparison. Returns the profiles plus per-app errors; apps that fail do not fail the whole call.
| Name | Required | Description | Default |
|---|---|---|---|
| apps | Yes | App IDs or apps.apple.com URLs to compare, e.g. ['570060128', 'https://apps.apple.com/us/app/babbel/id829587759']. | |
| country | No | ISO 3166-1 alpha-2 storefront all apps are compared on, e.g. 'us', 'de', 'jp'. One call always uses a single storefront. | us |
| Name | Required | Description |
|---|---|---|
| apps | Yes | |
| meta | Yes | |
| errors | No | |
| sources | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint, openWorldHint, idempotentHint. Description adds valuable disclosure of error handling: returns per-app errors and partial failures. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with purpose, no filler. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given low complexity, existence of output schema, and rich annotations, description covers necessary behavioral aspects (error handling) and use case. It is complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with parameter descriptions describing formats and defaults. Description does not add additional semantic value beyond schema for parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'Fetch', resource 'app profiles', and scope 'multiple apps in batch' for side-by-side comparison. Distinguishes from siblings like get_app_store_app (single) and search_app_store (search).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implies use case for competitor comparison. Mentioning that apps that fail do not fail whole call gives usage context. Lacks explicit when-not-to-use or alternatives, but context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch up to limit reviews and compress them into a structured
digest (themes, complaints, praise, sentiment) via MCP sampling, so
hundreds of reviews never enter your context. Works across storefront
languages - the digest is always English. Requires a client that
supports MCP sampling (or a server-side API-key fallback); use
get_app_store_reviews for the raw reviews instead.
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | 'most_recent' or 'most_helpful'. | most_recent |
| focus | No | Optional steer for the digest, e.g. 'pricing complaints' or 'onboarding friction'. | |
| limit | No | Max reviews to digest (10-500). | |
| country | No | ISO 3166-1 alpha-2 storefront code, e.g. 'us', 'de', 'jp'. Defaults to the country in the URL if one was passed, else 'us'. | |
| app_id_or_url | Yes | Numeric App Store app ID or a full apps.apple.com URL. |
| Name | Required | Description |
|---|---|---|
| meta | Yes | |
| app_id | Yes | |
| digest | Yes | LLM-compressed representation of a review set (data reduction, not ground truth - quotes may be translated/paraphrased). |
| sources | Yes | |
| reviews_considered | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds crucial behavioral context: it uses MCP sampling to compress reviews, the digest is always English regardless of storefront language, and it requires sampling support. No contradictions with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is only three sentences, front-loaded with the core action. Every sentence serves a purpose: function, differentiation, and requirement. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool complexity (5 parameters, output schema exists), the description fully covers what the tool does, its output format, language behavior, and usage constraints. It is complete for an agent to decide to invoke this tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description echoes the `limit` parameter and mentions the digest language, but does not add substantial new meaning beyond the schema. The `focus` parameter, for example, is only described in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool fetches reviews and compresses them into a structured digest (themes, complaints, praise, sentiment) via MCP sampling. It explicitly distinguishes from the sibling tool get_app_store_reviews by advising to use that for raw reviews. The verb 'digest' and resource 'App Store reviews' are specific and unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use (to avoid context overload), when not to use (when raw reviews are needed, use get_app_store_reviews), and requirements (client must support MCP sampling or have server-side fallback). This provides explicit guidance on tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch the full public App Store profile for one app by numeric ID or apps.apple.com URL. Page-sourced fields (subtitle, has_iap, privacy) are best-effort; set include_page_data=false to skip that second request. Set include_raw=true to also get Apple's unmodified lookup payload (large - only when normalized fields are not enough).
| Name | Required | Description | Default |
|---|---|---|---|
| country | No | ISO 3166-1 alpha-2 storefront code, e.g. 'us', 'de', 'jp'. Defaults to the country in the URL if one was passed, else 'us'. | |
| include_raw | No | Also return Apple's unmodified lookup payload under `raw` (large - only when normalized fields are not enough). | |
| app_id_or_url | Yes | Numeric App Store app ID (e.g. '570060128') or a full apps.apple.com URL. | |
| include_page_data | No | Also fetch subtitle, has_iap, and privacy labels from the public App Store page (best-effort, one extra request). |
| Name | Required | Description |
|---|---|---|
| app | Yes | |
| raw | No | |
| meta | Yes | |
| sources | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description adds valuable behavioral context: page-sourced fields are best-effort, include_page_data triggers an extra request, and include_raw returns a large payload to be used sparingly. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is four sentences, front-loaded with the main action, and every sentence adds value. No redundant or unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of a thorough input schema, output schema, and annotations covering read-only and idempotent behavior, the description covers the main purpose and optional behaviors well. It could mention when to prefer sibling tools, but overall it provides sufficient context for an agent to use the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and descriptions are already good, but the description adds extra nuance: app_id_or_url can be numeric or URL, country defaults to URL's country or 'us', include_raw is 'large - only when normalized fields are not enough', and include_page_data is 'best-effort, one extra request'. This enhances understanding beyond schema alone.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states 'Fetch the full public App Store profile for one app by numeric ID or apps.apple.com URL', using a specific verb and resource. It clearly differentiates from sibling tools like search_app_store, get_app_store_reviews, etc., by focusing on a single app's profile.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear guidance on when to use the tool (for one app by ID or URL) and explains optional parameters (include_page_data, include_raw) with their trade-offs. However, it does not explicitly contrast with sibling tools or state when not to use this tool, e.g., when to use search instead.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch ranked top-chart apps for a storefront. Best-effort: sourced from an undocumented Apple RSS feed.
| Name | Required | Description | Default |
|---|---|---|---|
| chart | No | Which chart to fetch: 'top-free', 'top-paid', or 'top-grossing'. | top-free |
| limit | No | Max entries to return (1-100). | |
| country | No | ISO 3166-1 alpha-2 storefront code, e.g. 'us', 'de', 'jp'. | us |
| category | No | Optional filter - a numeric App Store genre ID, or one of: books, business, developer-tools, education, entertainment, finance, food-drink, games, graphics-design, health-fitness, lifestyle, magazines-newspapers, medical, music, navigation, news, photo-video, productivity, reference, shopping, social-networking, sports, stickers, travel, utilities, weather. Omit for the overall chart. |
| Name | Required | Description |
|---|---|---|
| meta | Yes | |
| chart | Yes | |
| entries | Yes | |
| sources | Yes | |
| category | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (readOnlyHint, openWorldHint, idempotentHint), the description adds critical context: the tool relies on an undocumented feed and is best-effort. This discloses potential flakiness not captured by annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences: first states the action, second adds a crucial reliability caveat. No extraneous words, and the key information is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of an output schema (not shown but noted), the description covers what the tool does, its parameters, and a behavioral caveat. It is sufficient for an agent to understand and invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds little meaning beyond the input schema, which already has 100% coverage with clear descriptions for all 4 parameters. The tool's overall purpose is stated, but parameter details are not enhanced.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Fetch') and clear noun ('ranked top-chart apps') and identifies the scope ('for a storefront'), clearly distinguishing it from sibling tools that handle individual apps, reviews, or search.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description states the data is 'best-effort' and from an 'undocumented Apple RSS feed', which advises agents to expect possible unreliability. However, it does not explicitly say when to use this instead of alternatives like search_app_store.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch recent public customer reviews for an app. Best-effort: sourced from an undocumented Apple feed capped at ~500 reviews per storefront, with a small page-sourced fallback when the feed is empty. Reviews are per-country.
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | 'most_recent' or 'most_helpful'. | most_recent |
| limit | No | Max reviews to return (1-500; Apple caps the underlying feed at ~500 per storefront regardless of this value). | |
| country | No | ISO 3166-1 alpha-2 storefront code, e.g. 'us', 'de', 'jp'. Defaults to the country in the URL if one was passed, else 'us'. | |
| app_id_or_url | Yes | Numeric App Store app ID or a full apps.apple.com URL. |
| Name | Required | Description |
|---|---|---|
| meta | Yes | |
| app_id | Yes | |
| reviews | Yes | |
| sources | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds significant behavioral context beyond annotations: best-effort sourcing, undocumented Apple feed, ~500 review cap per storefront, page-sourced fallback, and per-country data. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences, front-loads the main action, and conveys essential limitations without unnecessary detail. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of an output schema, the description does not need to explain return values. It covers behavior, limitations, and per-country scope, making it complete for a moderately complex tool with 4 parameters.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
All parameters are documented in the schema with clear descriptions. The tool description adds context about the feed cap and fallback, which indirectly relates to limit and country, but does not significantly enhance meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool fetches recent public customer reviews for an app, specifies it is per-country and best-effort, and distinguishes it from sibling tools like compare_app_store_apps and digest_app_store_reviews by focusing on raw review retrieval.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use (fetch reviews) and notes limitations (best-effort, capped feed, fallback), but does not explicitly compare with siblings or provide when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch an app's App Store screenshots as actual images, so you can
analyze visual positioning, onboarding style, and paywall design
directly. Returns up to limit screenshots as image content blocks.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max screenshots to return (1-8); each is a full image in context, so keep this small. | |
| device | No | Which screenshot set to fetch: 'iphone' or 'ipad'. | iphone |
| country | No | ISO 3166-1 alpha-2 storefront code, e.g. 'us', 'de', 'jp'. Defaults to the country in the URL if one was passed, else 'us'. | |
| app_id_or_url | Yes | Numeric App Store app ID or a full apps.apple.com URL. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only, idempotent, and open-world hints. The description adds that it returns up to 'limit' screenshots as image content blocks and mentions each is a full image in context, advising to keep the limit small. This complements the annotations without contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise—two sentences that front-load the main purpose and include key details about return type and usage advice. No superfluous words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema, the description clarifies that the tool returns image content blocks, but does not specify the format (e.g., base64, URL). It is mostly complete but could be slightly more explicit about the return structure.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents parameters well. The description adds value by explaining the return behavior related to the 'limit' parameter and the purpose of screenshots, enhancing meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool fetches an app's App Store screenshots as actual images, and specifies the use case of analyzing visual positioning and design. It is distinct from sibling tools which handle reviews, charts, and text data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for visual analysis but does not explicitly contrast with sibling tools or provide guidance on when to avoid using this tool. The decision to use it is left to the agent without further context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search Apple App Store apps by keyword. Returns slim results (id, name, developer, rating, price) - use get_app_store_app for the full profile of a specific app.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results to return (1-50). | |
| query | Yes | Keyword(s) to search for, e.g. 'language learning'. | |
| country | No | ISO 3166-1 alpha-2 storefront code, e.g. 'us', 'de', 'jp'. | us |
| Name | Required | Description |
|---|---|---|
| meta | Yes | |
| query | Yes | |
| results | Yes | |
| sources | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, so the safety profile is covered. Description adds that results are 'slim' and lists included fields (id, name, developer, rating, price), which is useful beyond annotations. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no fluff. Front-loaded with purpose and action. Every sentence serves a purpose: first defines what it does and what it returns, second directs to alternative for more detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 3 parameters, all documented in schema, and output schema exists (as per context signals), the description provides enough context: purpose, return shape, and when to use alternative. A minor gap is that it doesn't mention the country or limit filtering, but those are in schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 100% description coverage, so baseline is 3. Description mentions 'by keyword' which aligns with the query parameter but does not add meaning for limit or country beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it searches Apple App Store by keyword and returns slim results. It distinguishes from sibling get_app_store_app by noting the latter provides full profiles. Specific verb 'Search' + resource 'Apple App Store apps'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly instructs to use get_app_store_app for full profile when needed, guiding when to use this slim version vs the alternative. Could note other siblings like get_app_store_charts for different use cases, but current guidance is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0compare_app_store_appsdigest_app_store_reviewsget_app_store_appget_app_store_chartsget_app_store_reviewsget_app_store_screenshotssearch_app_storeEach tool targets a distinct aspect of App Store data: batch profiles, individual profiles, search, charts, raw reviews, review digests, and screenshots. No overlap in purpose.
All tools follow a consistent verb_noun pattern in snake_case, with 'app_store' as the common noun. Verbs like get, search, compare, digest are clear and predictable.
Seven tools cover the essential App Store operations without being too few or excessive. The scope is well-scoped for a focused server.
Core CRUD-like operations are present (get, search, compare), along with reviews and screenshots. Minor gap: no developer info or historical ranking data, but the main use cases are well covered.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Find, compare, and audit software for AI agents. Scored registry of tools and MCP servers.
Hosted MCP server for live public-data APIs and Skills for AI agents.
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/LaurMost/appstore-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
