cost_tracker
Record and retrieve AI API call costs by team. Persists to Cloudflare KV — survives cold starts and scale-out.
teammodelaction必填metadatainputTokensoutputTokens
io.github.lazymac2x由 GitHub 帳號 lazymac2x 發布v1.0.0更新於 Oct 25, 2026
Cloudflare Workers MCP server: ai-cost-optimizer
一個遠端 MCP 伺服器,用來依團隊與模型追蹤、計算、設定預算並預測 AI API 支出。
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。
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.lazymac2x%2Fai-cost-optimizer/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。把它新增到你客戶端的 mcpServers 設定中。
{
"mcpServers": {
"ai-cost-optimizer": {
"type": "http",
"url": "https://api.lazy-mac.com/ai-cost-optimizer/mcp"
}
}
}Cloudflare Workers MCP server: ai-cost-optimizer. REST + MCP (JSON-RPC 2.0). Live: api.lazy-mac.com/ai-cost-optimizer
來源:README.md,提交 234f023
Record and retrieve AI API call costs by team. Persists to Cloudflare KV — survives cold starts and scale-out.
teammodelaction必填metadatainputTokensoutputTokensCalculate cost from token counts for any supported AI model. Stateless — no KV required.
model必填inputTokens必填outputTokens必填Set and check budget limits for teams. Raises a flag when a configurable spending threshold is reached.
teamaction必填thresholdbudgetLimitAnalyze costs broken down by model for a given team over a configurable time window.
daysteamForecast future AI spend based on historical usage patterns using daily-average linear projection.
teamforecastDayshistoricalDays已滿足適用檢查項的 90%
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。
請在儲存庫或註冊中心條目中宣告授權條款。