SubcueAI

io.github.Subcuev1.0.0更新於 Oct 10, 2026

Public read-only MCP for SubcueAI: live pricing, latest desktop version, overview and FAQ.

已驗證Streamable HTTP可網頁執行Business & CommerceProductivity & Workflow

概覽

AI 產生的概覽

讓助理透過公開唯讀端點讀取 SubcueAI 的即時產品資料，包括訂閱價格、桌面應用程式最新版本、產品概觀與常見問題。

功能
這是 SubcueAI（適用於 macOS 與 Windows 的即時 AI 面試助理）的公開、免驗證、唯讀 MCP 伺服器。它提供 get_pricing 等工具，回傳目前訂閱方案與價格；以及 get_latest_version，可傳入選用的平台參數，回傳桌面應用程式最新版本、發行日期與下載網址。它也透過 subcue://overview 與 subcue://faq 資源提供產品功能與常見問題。回應為 Markdown，資料與官網同源。
適用情境
當助理需要取得 SubcueAI 的最新價格、版本或發行資訊，以及產品概觀與常見問題時適用，可避免爬取網頁。它是範圍很窄的產品資訊伺服器，並非通用工具。
執行需求
遠端 streamable HTTP 端點 金鑰或環境變數。僅支援 stdio 的用戶端需要此儲存庫提供的 Node 18+ 橋接程式或容器。必須送出可辨識的 User-Agent，預設函式庫的 User-Agent 會被拒絕並回傳 403。
安裝前請注意
此伺服器嚴格唯讀，未宣告任何憑證，不會代為寫入或送出資料。請求會送往第三方端點，且邊緣有速率限制，請避免高頻請求。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 SubcueAI，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": {
    "subcue-mcp": {
      "type": "http",
      "url": "https://subcue.ai/mcp"
    }
  }
}

README

SubcueAI Public MCP Server

mcp-name: io.github.Subcue/subcue-mcp

SubcueAI (the real-time AI interview assistant for macOS & Windows) ships a public, unauthenticated, read-only Model Context Protocol server. Any AI agent can query live product data — pricing, latest desktop version, product overview, FAQ — instead of scraping HTML.

  • Endpoint: POST https://subcue.ai/mcp
  • Transport: streamable-http (single JSON response), JSON-RPC 2.0, MCP protocol 2025-06-18
  • Auth: none. Writes: none — the server is strictly read-only.
  • Server card: https://subcue.ai/.well-known/mcp/server-card.json

This repository documents the server and provides ready-to-run client examples. The server itself runs on Cloudflare Workers as part of the SubcueAI website.

Quick start

sh
# List toolscurl -s https://subcue.ai/mcp -X POST -H 'Content-Type: application/json' \  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
# Live pricingcurl -s https://subcue.ai/mcp -X POST -H 'Content-Type: application/json' \  -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"get_pricing"}}'

Sample get_pricing output (live data, abridged):

markdown
# SubcueAI Pricing
## Starter — free- Standard AI model- Mock interview practice
## Pro — $20/mo; $16/mo when billed yearly ($192/yr)...

Tools

ToolArgumentsReturns
get_pricing—Current subscription plans and pricing (Markdown)
get_latest_versionplatform (optional, e.g. macos-arm64, windows-x64)Latest desktop app version, release date, download URL

Resources

URIContent
subcue://overviewWhat SubcueAI is, key features, links (Markdown)
subcue://faqFrequently asked questions (Markdown)

Use resources/list / resources/read per the MCP spec.

Connect from popular clients

Claude Code

sh
claude mcp add --transport http subcue https://subcue.ai/mcp

Cursor / any client using mcp.json

json
{  "mcpServers": {    "subcue": { "url": "https://subcue.ai/mcp" }  }}

claude.ai — Settings → Connectors → Add custom connector → https://subcue.ai/mcp.

Stdio-only clients — this repo ships a zero-dependency stdio ⇄ HTTP bridge (bridge/server.mjs, Node 18+):

sh
claude mcp add subcue -- node /path/to/subcue-mcp/bridge/server.mjs# or containerised:docker build -t subcue-mcp . && docker run -i subcue-mcp

Examples in this repo

Other machine-readable entry points

SubcueAI publishes a full agent-facing surface beyond MCP:

EndpointWhat it is
/llms.txtPlain-text site & product summary for language models
/.well-known/api-catalogRFC 9727 linkset of public JSON APIs
/.well-known/agent-skills/index.jsonAgent Skills discovery index
/.well-known/agent-skills/subcue-public-info/SKILL.mdAgent skill: how to fetch SubcueAI public data
Accept: text/markdownAny public marketing/legal page returns Markdown instead of HTML

Notes for agent developers

  • Responses are deterministic JSON-RPC; notifications (notifications/*) are accepted and return 202 with no body.
  • Data is live (pricing and versions come from the same source of truth as the website) — prefer these endpoints over scraping rendered HTML.
  • Rate limiting applies at the edge; be a good citizen.
  • Send a descriptive User-Agent — default library UAs (e.g. Python-urllib/3.x) are rejected by edge bot protection with a 403.

License

Documentation and examples: MIT © 2026 Subcue AI LLC.

來源：README.md，提交 ca4b06e

工具

0
工具後設資料尚未被收錄。

版本歷史

1
  1. v1.0.0最新Sep 16, 2026