Aggrometer

io.github.Aggrometer由 GitHub 帳號 Aggrometer 發布v1.0.1更新於 Oct 25, 2026

The gaming attention graph: Steam players, Twitch live viewers, aggro ratio, hype, history.

已驗證Streamable HTTP可網頁執行金融資料與分析媒體與設計

概覽

AI 產生的概覽

遠端 MCP 伺服器,以唯讀工具提供遊戲關注度資料:Steam 同時上線人數、Twitch 觀看人數、aggro 比率、期待值與單一遊戲歷史。

可以做什麼
先用摘要工具查看資料倉儲的涵蓋範圍與資料新鮮度,再依名稱搜尋已收錄遊戲,取得 Steam app id 與目前上線人數。依目前 Steam 同時上線人數或 Twitch 即時觀看人數列出前 100 名遊戲,可限定單一 Steam 類型。讀取 aggro 榜(同一小時內即時觀看人數除以同時上線人數)以及類型彙總(合併玩家數、觀看人數、類型 aggro 與未上市遊戲的期待值)。查看願望清單最高的未上市遊戲的期待指數,並取得單一遊戲的完整檔案:每小時玩家與觀看歷史、價格與折扣歷史、暢銷榜排名、片段傳播速度、評論數與維基百科瀏覽量。
適用情境
適合遊戲開發者、發行商、行銷團隊與分析師,讓助理尋找類型空白、比較觀看與遊玩的關注度、追蹤上市前的期待或折扣效果,或調取某款遊戲的關注度歷史。
執行需求
遠端 streamable HTTP 端點,無需本機安裝。需要 Aggrometer API 金鑰,以 bearer 權杖放在 Authorization 標頭中,金鑰需從服務商定價頁面取得(付費訂閱方案或預付查詢額度)。需要能連線至該端點的網路。
安裝前請注意
存取需付費:需要訂閱或預付額度,查詢可能消耗額度。API 金鑰是放在 Authorization 標頭中的機密,應避免寫入共用設定與日誌。八個工具皆為唯讀,但資料為衍生的彙總與估算,歷史累積時間較短,序列稀疏可能反映涵蓋有限,而非確實沒有資料。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Aggrometer,將其新增到工作區。
  2. 連接 Authorization token 憑證。它們會被私密儲存,絕不會在公開頁面上展示。
  3. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.Aggrometer%2Faggrometer/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "aggrometer": {
      "type": "http",
      "url": "https://aggrometer.com/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

Aggrometer — the gaming attention graph

Live cross-platform gaming market data for humans and AI agents. Aggrometer continuously measures ~2,000 games: Steam concurrent players (hourly) and Twitch live viewership (15-min, game-level aggregates), plus prices, discounts, top-seller ranks, clip velocity, review counts, and pre-release hype — joined per game.

Signature metric: aggro = live viewers ÷ concurrent players, same hour. Above 1.0, a game holds more audience than players — the signal that streamer marketing converts, that a spectacle moment is happening, or that attention is arriving ahead of sales.

🌐 aggrometer.com · API index · OpenAPI · llms.txt · Pricing

MCP server

Remote, streamable HTTP, stateless — 8 read-only tools:

get_summary · top_played · top_watched · aggro_board · genre_rollup · hype_board · game_detail · search_games

Endpoint: https://aggrometer.com/mcp Auth: Authorization: Bearer <your aggrometer API key> — get a key (Basic $3.99/mo · Pro $29/mo · prepaid agent credits $9.99/1,000 queries)

Claude Code

bash
claude mcp add --transport http aggrometer https://aggrometer.com/mcp --header "Authorization: Bearer YOUR_KEY"

Claude Desktop / other MCP clients (config JSON)

json
{  "mcpServers": {    "aggrometer": {      "url": "https://aggrometer.com/mcp",      "headers": { "Authorization": "Bearer YOUR_KEY" }    }  }}

Cursor

This repo ships a .mcp.json — set the AGGROMETER_API_KEY environment variable and Cursor picks it up.

REST API

Same key, plain JSON:

bash
curl -H "Authorization: Bearer YOUR_KEY" "https://aggrometer.com/v1/boards/aggro?genre=RPG"

Full endpoint index (self-describing, no auth): GET /v1 · OpenAPI spec

Also on Apify

Pay-per-query without an Aggrometer key: apify.com/aggrometer/aggrometer-gaming-attention-data — agent-callable via Apify's MCP, x402-payable.

Who uses this

  • Game developers & publishers — genre whitespace, launch scouting, competitor attention
  • Marketing teams — watched-vs-played balance, per game and genre
  • Analysts & press — attention momentum, hype pipelines, discount effects
  • AI agents — all of the above, autonomously

Data notes

Game-level derived aggregates and estimates only. History accrues continuously since 2026-08-26; sparse series indicate a young warehouse, not missing coverage. Live viewership data provided by Twitch; the anticipation score is Aggrometer's own composite index (Steam wishlist rank + pre-release Twitch attention).

Support

[email protected]

來源:README.md,提交 f7756f8

工具

8

get_summary

Warehouse status: how many games are tracked, hours of history recorded, snapshot counts, and data freshness timestamps. Call this first to understand data coverage.

無需輸入參數。

top_played

Top 100 games by current Steam concurrent players (updated hourly). Optionally scoped to one Steam genre.

輸入參數genre

top_watched

Top 100 games by current live Twitch viewership (15-min updates). Optionally scoped to one Steam genre.

輸入參數genre

aggro_board

Aggrometer's signature metric: aggro = live Twitch viewers / concurrent Steam players, same hour, per game (min 500 players). Above 1.0 means more people watch than play — spectacle games, watch-to-learn genres. A sudden aggro jump is an early attention signal.

輸入參數genre

genre_rollup

Every Steam genre aggregated: game count, combined players, combined live viewers, genre-level aggro ratio, and combined hype (anticipation) of the genre's unreleased games. The whitespace signal: high players + low hype = an underserved genre; low players + high hype = a wave arriving.

無需輸入參數。

hype_board

Aggrometer Anticipation Index: top-wishlisted unreleased Steam games scored with pre-release Twitch attention and Wikipedia attention surges (score = wishlist-rank points + log-scaled live viewers + log-scaled pageview surge vs 30-day average). A relative index - compare games against each other; week-over-week change is the launch-anticipation signal.

無需輸入參數。

game_detail

Full profile of one game by Steam app id: hourly player history, Twitch viewer history, daily viewer-hours, price/discount history, top-seller rank appearances, clips-per-day virality, review counts and review-activity buckets back to launch, Wikipedia pageview history (monthly since 2018 + daily), developer news velocity, achievement-completion depth, and metadata (genres, developer, publisher). Use search_games first if you only know the name.

輸入參數app_id必填

search_games

Find games in the tracked catalog by name (substring match). Returns app ids for use with game_detail, plus current player counts.

輸入參數query必填

版本歷史

1
  1. v1.0.1最新Sep 16, 2026

評分

已滿足適用檢查項的 100%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分