Apify上のMamba Labs YouTube Channel Stats ExtractorアクターのためのMCPサーバーです。
会社のドメインまたはYouTubeハンドルから、登録者数とチャンネルのメタデータを含むチャンネルへ解決します。
会社のドメインまたはYouTubeハンドルを、その会社のYouTubeチャンネルに解決します。登録者数、安定したUCチャンネルID、チャンネルハンドル、チャンネル名、作成日、説明文を、Clayですぐ使えるフラットな1行として返します。登録者数はYouTube側で約1,000人以上になると切り上げられ、Webページと公式APIの両方で同じ丸め値が返るため、出力行にはその旨を示すフラグが付けられます。オプションで文字起こし取得も可能ですが、現在はYouTubeの制限を受けています。キャプショントラック一覧は取得できますが、キャプション本文のエンドポイントは発信元証明トークンなしでは空のボディを返すため、出力行では「動画にキャプションがない」ではなくnot_extractableとして報告されます。APIキーは不要です。読み取り専用です。APIFY_TOKENが必要で、呼び出しごとにApifyクレジットを消費します。
Related MCP server: YouTube MCP
MCPクライアントの設定に次を追加します:
{
"mcpServers": {
"mamba-youtube-channel-stats": {
"command": "npx",
"args": ["-y", "@mambalabsdev/mcp-youtube-channel-transcript-extractor"],
"env": { "APIFY_TOKEN": "your-apify-token" }
}
}
}Node.js 18以降
Apifyコンソールから取得したApify APIトークン
このアクターは使い切り課金制で、呼び出しごとにApifyクレジットを消費します。料金はアクターページをご覧ください。
「stripe.comのYouTube登録者数は？」
「hubspot.comのYouTubeチャンネルIDを取得して」
「gitlab.comはYouTubeチャンネルを運営している？いつ開設されたの？」
ツール: get_youtube_channel_stats
入力 | 型 | 意味 |
| string | 会社のドメイン。例: |
| string | 任意。会社名との照合に使われ、検索精度を高めます。 |
| string | 任意。YouTubeハンドル（例: |
| boolean |
|
| boolean |
|
| boolean |
|
| string | 文字起こし取得時に、チャンネルの直近の動画のうち何本分を取得するか。デフォルトは |
すべての行にはプラットフォームごとの_statusフィールドがあり、最初に読むべきフィールドです。語彙はMamba Labsの一連のソーシャルメディア系アクター全体で共通です:
ステータス | 意味 |
| 取得・解析済み。値が存在する |
| 探索したがプロフィールが存在しない |
| プロフィールは存在するが、値を取得できない |
| プラットフォーム側が拒否した。後ほど再試行する価値がある |
| 実在のプロフィールが見つかったが、それは別の人・別の会社 |
| そのプラットフォームは要求していない |
falseとnullは決して互換性はありません。 falseは「調べた結果、そうでない」という意味です。nullは「調べられなかった」という意味です。どの会社に存在がないかをフィルタする場合はnullではなくfalseでフィルタしてください。なぜならnullの行は「不在」ではなく「未判明」だからです。
apify.com/mambalabs/youtube-channel-transcript-extractor
Mamba Labsが提供するGTMリッチメントアクター群は company_domain で結合できるフラットな出力を採用しています。
フル一覧は apify.com/mambalabs をご覧ください。
MIT
Resolve a company domain, or a YouTube handle, to that company's YouTube channel. Returns the subscriber count, the stable UC channel id, channel name, creation date and description, as one flat Clay ready row. Subscriber counts are rounded by YouTube above roughly a thousand subscribers, on the page and in its official API alike, and the row flags that. Optional transcript pulling is available and is CURRENTLY GATED by YouTube: the caption track list is readable and the caption content endpoint returns an empty body without a proof of origin token, which the row reports as not_extractable rather than as a video having no captions. A company with no channel reports youtube_status not_found. Read youtube_status before any count. Use it to look up one known company channel per call; it does not search YouTube, list a channel's videos, or return video detail, and the package name mentions transcripts only because transcript pulling is an option. No API key needed. Read only; requires an APIFY_TOKEN and consumes Apify credits per call.
| Name | Required | Description | Default |
|---|---|---|---|
| handle | No | Optional. A YouTube handle such as @shopify, or a full channel URL. Supplying it skips discovery and goes straight to the channel. | |
| skipCache | No | When "false" (default) a successful lookup is cached for seven days and reused. Set "true" to force a fresh fetch. Sent as a string for Clay compatibility. | |
| company_name | No | Optional. Improves search accuracy and is what the identity gate checks a discovered profile against, so supplying it reduces wrong matches. | |
| company_domain | No | Bare company domain, for example shopify.com. Supply this or a handle. With a domain the actor runs full discovery; with a handle it skips straight to the fetch. | |
| max_charge_usd | No | Optional spending cap for this call, in USD, passed to the actor as max_charge_usd. The run stops before any charge that would take it past this amount and keeps every row already charged. Leave empty to rely only on the maximum charge per run set on your Apify account. | |
| includeTranscripts | No | When "true", full timestamped transcripts are pulled for the most recent videos on the channel and returned as one row per video. Default is "false" because transcripts are the expensive half of this actor and most buyers want channel stats only. Sent as a string for Clay compatibility. | |
| transcriptVideoCount | No | How many of the channel's most recent videos to pull transcripts for, when transcripts are on. Default 5. Each video is one extra fetch and one extra billable transcript event, so this is the dial that sets the cost of a transcript run. | |
| includeFollowerCounts | No | When "true" (default) the profile page is fetched and the counts are extracted. Set "false" to resolve the profile URL only, which is cheaper and needs no proxy. Sent as a string for Clay compatibility. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description is otherwise unusually candid — YouTube's subscriber rounding, the transcript gating and the not_extractable vs. no-captions distinction, credit consumption, and the APIFY_TOKEN requirement are all disclosed. However, it asserts 'Read only' while the annotations declare readOnlyHint=false, an outright conflict on the safety profile. Flagged as an annotation contradiction, which caps this score.
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?
Purpose and return shape are front-loaded, and the caveats (rounding, gating, status field, cost) follow in descending priority. It runs long at roughly nine sentences, and the aside about the package name is borderline, but almost every sentence carries information an agent needs.
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?
With 8 optional parameters and no output schema, the description does the heavy lifting: it names the return fields, the flat-row shape, the youtube_status signal, and the not_found case, plus auth and billing. It stops short of enumerating all possible youtube_status values or how a missing domain+handle is handled, which keeps it from a 5.
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%, so the baseline is 3, but the description adds genuine semantics beyond it: transcripts are CURRENTLY GATED by YouTube and the row reports not_extractable rather than no-captions, which materially changes how an agent should interpret includeTranscripts/transcriptVideoCount results. It also explains the cost framing of a transcript run rather than leaving it to 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?
Opens with a precise verb+resource: resolve a domain or handle to a company's YouTube channel, then lists the returned fields (subscriber count, UC id, name, creation date, description). It also explicitly fences the scope — 'it does not search YouTube, list a channel's videos, or return video detail' — so an agent knows exactly what this tool is and is not.
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?
Gives direct usage guidance: 'Use it to look up one known company channel per call', with explicit exclusions (no search, no video listing, no video detail) and a sequencing rule ('Read youtube_status before any count'). The domain-vs-handle choice and its consequence (full discovery vs. straight to fetch) is stated inline.
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.
v1.1.1get_youtube_channel_stats2 fields changedInput schema / additionalPropertiesRemoved value: -falseInput schema / properties / max_charge_usdAdded value: +{
+ "description": "Optional spending cap for this call, in USD, passed to the actor as max_charge_usd. The run stops before any charge that would take it past this amount and keeps every row already charged. Leave empty to rely only on the maximum charge per run set on your Apify account.",
+ "minimum": 0,
+ "type": "number"
+}v1.0.0get_youtube_channel_statsScored across 1 tool
With only one tool there is nothing to confuse it with, and the description clearly enumerates what it does (domain/handle → channel stats) and what it does not do (search, video listing, video detail). The only mild internal blur is that the tool name advertises transcripts while the body frames them as a gated option, but that is a scoping note, not a tool-selection ambiguity.
The single tool follows a clean snake_case verb_noun pattern (get_youtube_channel_stats). No mixing of conventions or vague verb styles is present to break predictability.
One tool is thin for a server that also implies transcript extraction and channel resolution; resolving, stats, and transcript pulling are collapsed into a single overloaded call. It is not mis-scoped enough to be wrong, but it sits at the borderline of too few.
Channel lookup and stats are covered, but the headline transcript capability is effectively unusable (caption content gated, reported as not_extractable), and there is no video listing, video detail, or multi-channel/batch operation. An agent can still retrieve channel stats, so gaps are notable rather than fatal.
YouTube video metadata, transcripts and channel data by URL or @handle. No API key. Pay per result.
Find the contact email of YouTube channels from the link, the @handle or the channel_id. Resolves th
YouTube search, whole channels, video stats, comments and full transcripts with timestamps.
YouTube data for AI agents: channels, videos, transcripts, comments, search. Video research.