Rush SR Lap Analyzer

sr.rushv0.2.0更新於 Oct 1, 2026

Analyze AiM RaceStudio lap data: lap times, compare laps, time loss, compare two sessions.

已驗證Streamable HTTP可網頁執行Location & LifestyleData & Analytics

概覽

AI 產生的概覽

遠端 MCP 伺服器，用來分析 AiM RaceStudio 圈速資料，比較單圈與場次，提供圈速與時間損失。

功能
它提供唯讀工具進行賽車遙測分析：analyze_session 回傳圈速、最快圈、理論最快圈、穩定性，以及被排除的圈與原因；compare_laps 給出同一場次中兩圈的時差、煞車點與彎中最低速度；find_time_loss 顯示相對最快圈損失時間最多的區段；compare_sessions 比較兩個場次各自的最佳有效圈，包括時差、得失區段、煞車點、彎中最低速度與最高速度。資料以 AiM RaceStudio 匯出的 CSV 提供，可為文字或附件檔案。
適用情境
適合檢視 AiM RaceStudio 場次資料的車手、教練與車隊，用於快速逐圈比較、時間損失分析，或在同一條賽道上比較兩位車手、兩輛車，而不必開啟分析軟體。
執行需求
遠端 Streamable HTTP 端點 laps.mcp.rush.sr；不需登入，也不需要 API 金鑰。輸入需要 AiM RaceStudio 匯出的 CSV，單一檔案上限 8 MB。二進位 .xrk 記錄無法直接讀取；在 Claude 中由 Rush SR 外掛先進行轉換。
安裝前請注意
所有工具皆為唯讀，伺服器聲明資料僅在記憶體中分析、不做儲存，也不呼叫語言模型。上傳的場次檔案會經過 Amazon CloudFront 與 Cloudflare 等基礎設施供應商，檔案連結僅透過 HTTPS 下載一次。結果中包含一行指向廠商網站的固定署名。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Rush SR Lap Analyzer，將其新增到工作區。
  2. 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。

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "lap-analyzer": {
      "type": "http",
      "url": "https://laps.mcp.rush.sr/mcp"
    }
  }
}

README

Rush SR Lap Analyzer

A remote MCP server that analyzes AiM RaceStudio lap data. It works as a connector in Claude and as a plugin in ChatGPT. Built by Rush Auto Works.

https://laps.mcp.rush.sr/mcp        Streamable HTTP, no sign-in

Tools

ToolWhat it does
analyze_sessionLap times, best lap, theoretical best, consistency, and which laps were excluded and why.
compare_lapsTime delta, braking points and corner minimum speeds for two laps in one session.
find_time_lossThe sectors where a lap loses the most time against your best lap.
compare_sessionsTwo sessions on their best valid laps: delta, sectors gained and lost, braking points, corner minimum speeds, top speed. Use it for two drivers or two cars on the same track.

Every tool is read-only. Every result ends with one line, Built by Rush Auto Works, with a link to rushautoworks.com.

Giving it data

Send an AiM RaceStudio CSV export as csv_text, or attach the file where the client supports uploads. compare_sessions takes csv_text_a and csv_text_b (or file_a and file_b) and optional lap_a and lap_b. Files are limited to 8 MB, so a very long session may be rejected with a message naming the limit.

Excluded laps: the first lap (out-lap), the last segment (in-lap, because it ends with the data, not on a beacon crossing), and any lap more than 7% slower than the best.

AiM .xrk logs are binary and are not read directly. In Claude, install the Rush SR plugin, which converts an .xrk with libxrk and runs the same engine in the sandbox.

Try it

Two synthetic sessions, not from a real driver, are in examples/:

  • synthetic-session-a.csv: best lap 4 in 45.793 s, theoretical best 45.547 s, 4 valid laps.
  • synthetic-session-b.csv: the same track about 3% slower. compare_sessions on the pair gives a delta of -1.416 s.

What it does with your data

It analyzes the data in memory and stores nothing. It makes no calls to a language model and needs no sign-in. A file link is downloaded once, over HTTPS, with limits on size, redirects and time. Requests pass through Amazon CloudFront and Cloudflare as infrastructure providers. Workers Logs are switched off in wrangler.jsonc, and a test fails if that changes.

Privacy policy: https://rushautoworks.com/privacy-policy/

Support

[email protected], or an issue at https://github.com/Rush-Auto-Works/llm-plugins/issues.

Deploy

npx wrangler deploy

ChatGPT's plugin submission checks a token at /.well-known/openai-apps-challenge on the MCP host. The dashboard issues the token when a submission draft is started. Add it to vars in wrangler.jsonc and redeploy:

"vars": { "OPENAI_APPS_CHALLENGE": "<token from the ChatGPT plugins dashboard>" }

The route returns the token as plain text. Until the variable is set it returns 404, so nothing is served by default. Check it with curl https://laps.mcp.rush.sr/.well-known/openai-apps-challenge.

Run it locally

npm cinpm test         # boots wrangler dev and runs the E2E suitenpm run dev      # http://127.0.0.1:8787/mcp

MIT licensed.

來源：servers/laps/README.md，提交 4efb754

工具

0
工具後設資料尚未被收錄。

版本歷史

1
  1. v0.2.0最新Oct 1, 2026