MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · Other

AppTierList

Ranked iPhone app lists by use case (S to F) from public App Store data. Read-only, no key.

Checks passed
15 / 22

0 failed · 7 not measured

Median response
119 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
11

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Responded

The server completed its last measured handshake. This is an observation, not a guarantee.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
103
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
400
Publisher identityCan the publisher be traced to its source?
402

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 85 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-06-18, serverInfo.name apptierlist.

  • Pass
    Lists tools

    tools/list returned 11 tools.

  • Pass
    Current protocol

    Negotiated 2025-06-18. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 119 ms over 2 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 150 ms over 2 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    2 of 2 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Pass
    Stable tool list

    No tool was removed and no required parameter was added in the last 30 days.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Pass
    Parameters documented

    21 of 23 parameters have a description (91%). The bar is 80%.

  • Pass
    Safety hints

    Every tool sets readOnlyHint or destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Pass
    Website matches publisher

    The website host matches the reverse-domain namespace.

  • Pass
    Source repo linked

    A repository URL is on file.

  • Not measured
    Repo owner matches

    This namespace is not an io.github login, so the owner comparison does not apply.

  • Pass
    Recently updated

    Updated 2026-10-30T13:22:08.552995Z, within 180 days.

  • Not measured
    Open-source licence

    The GitHub licence lookup has not returned an OSI result yet.

Start using AppTierList

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

claude mcp add --transport http apptierlist https://apptierlist.com/mcp

Capabilities

Tools 11

compare_apps

Side-by-side tier, position, score and components for two or more apps in one category (or in every category they share when list is omitted). An app with review_status under_review is not checked against that category yet: no tier, no position. Never compares positions across different categories.

Discovered
explain_ranking

Why an app sits where it does: score components per category, per-store search ranks, every judge verdict (with reason, whether it is current for the app's present listing and the category's present definition), and the app's change history. An app whose missing_since is set is no longer on the App Store: do not recommend it or send anyone to its store_url.

Discovered
fetch

One document by the id search returned: list:<slug> is the category's ranking (compact members), app:<slug> the app's full record. text holds the record as JSON.

Discovered
find_alternatives

Apps that do the same job as the given app, in three groups: most_similar (S to C tier; apps that also sit in more of this app's other categories first, then the same App Store genre, then tier), top_rated (the category's own order) and best_free (free to download, in-app purchases allowed); each app in one group at most, every one with why it is there (shared_lists, same_genre, free). all lists every alternative. They all come from the app's main-job category, so none does a different job. An app whose missing_since is set is no longer on the App Store: its alternatives matter most then.

Discovered
get_app

One app by slug or App Store id: App Store facts, generated summary, every category membership with tier/score/status/confidence and review_status (checked, or under_review: not checked against that category yet, so tier and position are null) and list_ranking_status (the category's own ranking_status: tier and position are null unless it is ranked), main_list (the list slug of the app's main job: the first category the placer marked primary on the current App Store listing; null when no read of the current listing marks one (never guessed). An app's alternatives belong to this job), maker claim status, recent history. An app whose missing_since is set is no longer on the App Store: do not recommend it or send anyone to its store_url.

Discovered
get_category

The tier list for one category: members in order with tier, score, the score components, per-store search ranks, membership status (active), confidence (normal|provisional), maker verification, freshness. Each ranked member carries a compact app (name, one-liner, price, rating, links); unranked and under_review entries carry a smaller one (name, rating, links). Full details of any app are at its api_url, or get_app. Positions are only meaningful within this category. under_review lists the apps not yet checked against this category's definition (review_status: "under_review"): they have no tier and no position, come after every ranked app, and should not be presented as ranked. ranking_status "under_review" means fewer than 6 apps are checked and "too_few" fewer than 6 apps in all, so the category has no ranking yet. An app whose missing_since is set is no longer on the App Store: it stays in the category at tier F, after every app still on sale, and is never counted or named #1; do not recommend it or send anyone to its store_url. A merged category's slug answers with the category it was merged into, with merged_from.

Discovered
health

Is the data being maintained: per-job last success and next due time, provider cool-downs, invariant check status, counts of pending judgments, stale apps, and public_unchecked (memberships shown as under review, expected to fall to 0).

Discovered
list_categories

Every ranked category (product type): slug, title, section, parent, how many apps are tiered, its #1 app, ranking_status (ranked; under_review: fewer than 6 apps checked against it yet; too_few: fewer than 6 apps in it at all; either way no ranking and no #1) and under_review_count (apps listed but not checked yet). Use the slug with get_category. verbose=true adds each definition, excludes, counts and URLs (about 10x larger). Default: active only; status=all includes drafts (unpublished, being built) and archived (kept, no longer recommended).

Discovered
recent_changes

Append-only history: memberships added/removed, tier changes, categories created/activated/archived, apps discovered/missing. Newest first (by time, then id); page with cursor. To poll for new events use after_id instead: events whose seq is greater than after_id, oldest first by seq, each with its seq, and next_after_id (the last seq) to send next time (start at 0); seq is the order events became public, so it never misses an event written late or shown after review, which since can (not with since, cursor or summary). since is exact for events: only changes after that instant. summary=true answers 'what moved this week' in one call instead: per category, apps added/removed/contested, each app's net tier move (up, down, entered or left the top 40) with the S/A moves and membership changes as highlights (each with its reason: why it moved, e.g. under review or checked), plus catalog events; window from since rounded down to its UTC day (default 7 days back, at most the last 31 days), counted over every event in it. By default the 15 busiest categories (lists_total says how many changed); pass list for one.

Discovered
search

Search categories and apps; returns results with an id to pass to fetch (list:<slug> for a category's ranking, app:<slug> for an app), a title and a URL. Same matching as search_apps; when no category matched every word, a hint says the categories match only some of them.

Discovered
search_apps

Find categories by name or definition and apps by name, word by word: 'best free ai companion', 'apps like calm' (the categories Calm is ranked in), 'chat gpt'. Filler words (best, free, app, like) are ignored. Returns summaries with compact apps; follow up with get_category or get_app. When nothing matches every word, the categories matching some of them come back with a hint.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected85 ms11
Connected153 ms11