AgentDiet AI Token Diet & Context Window Distiller

dev.agentdiet由 agentdiet.dev 發布官方發布者v7.0.17更新於 Nov 4, 2026

Strips 85-97% of HTML/DOM bloat into clean Markdown or JSON with cryptographic ROI proof.

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取資料與分析

概覽

AI 產生的概覽

遠端 MCP 伺服器,擷取網頁並濃縮為精簡 Markdown 或結構化 JSON 以節省 token,付費呼叫以預付錢包結算。

可以做什麼
  • 擷取公開網頁或原始 HTML,把正文濃縮成乾淨的 Markdown,去除大部分樣板內容
  • 先預覽頁面標題大綱與各章節 token 數,再決定是否擷取全文
  • 擷取 JSON-LD、OpenGraph 中繼資料、HTML 表格、程式碼區塊、標題與連結等結構化資料
  • 查詢帳戶帳本:剩餘免費試用次數、預付美元餘額、累計支出、呼叫次數與節省的 token
適用情境
適合讓助理閱讀長篇文章、文件或價格頁面並控制上下文長度時使用,也適合需要從頁面取得機器可讀資料而非正文的情境。先用大綱預覽可判斷整頁是否值得擷取。
執行需求
需要遠端 streamable HTTP 端點;未宣告本機執行環境、套件、環境變數或請求標頭。服務依用量計費:5 次免費試用,之後需透過 Stripe 或 USDC 儲值預付美元餘額。目標頁面須可透過 HTTP(S) 公開存取。
安裝前請注意
付費工具呼叫會扣減預付餘額,批次呼叫前應先查看錢包狀態。伺服器會代為擷取任意公開網址,送出的網址與頁面內容會離開本機。README 描述的是另一套保障服務及其端點,與清單中的端點不一致,連線前請確認實際對接的服務。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 AgentDiet AI Token Diet & Context Window Distiller,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。

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/dev.agentdiet%2Fagentdiet/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": {
    "agentdiet-ai-token-diet-context-window-d": {
      "type": "http",
      "url": "https://agentdiet.dev/mcp"
    }
  }
}

README

Assay — A2A & MCP Provider Assurance Observatory

[Assay Badge]

Live Observatory: https://assay-207908449630.us-central1.run.app

Assay continuously probes remote MCP, A2A, and x402 endpoints to verify liveness, pin canonical SHA-256 tools/list schema hashes (detecting silent MCP Rug Pulls), and scan for prompt-injection tool poisoning before your agent pays or executes a tool.

MCP Endpoint

  • Streamable HTTP MCP: https://assay-207908449630.us-central1.run.app/mcp
  • Pre-Flight REST API: POST https://assay-207908449630.us-central1.run.app/v1/preflight
  • Live Leaderboard: GET https://assay-207908449630.us-central1.run.app/v1/leaderboard

來源:README.md,提交 fd42696

工具

4

distill_webpage

Distill webpage

Fetch a public HTTP(S) web page (or accept raw HTML) and distill its main prose into clean Markdown, stripping 85-97% of HTML/JS/CSS boilerplate. WHEN TO USE: Call this tool to read full or query-filtered article and documentation text; call recon_webpage_skeleton first to preview headings and token counts on unfamiliar pages, or extract_structured_data when you need JSON-LD, HTML tables, or code blocks. WHEN NOT TO USE: Do not use for binary PDFs, images, or login-walled pages. PARAMETER INTERACTIONS: Provide either url or html (when html is supplied, url is not fetched and only labels the cache key). When mode='markdown' (default), query and max_tokens are ignored; set mode='budget' to rank sections by query (BM25) and cap output at max_tokens. Omit agent_id and tx_hash during your 5 free calls. Read-only and idempotent; results are cached for 1 hour (<5ms cache hit). $0.001 per call ($0.0005 cached). Pricing: the first 5 calls per agent_id are free and failed calls are never charged. After 5 calls, the tool returns a payment-required quote (not a fatal error) with a $2 Stripe top-up link and Base/Solana USDC addresses; complete payment, then retry with your agd_pass_ key in agent_id or pass tx_hash. Example: distill_webpage(url='https://docs.stripe.com/api')

輸入參數url必填htmlmodequerytx_hashagent_idmax_tokens

recon_webpage_skeleton

Recon webpage skeleton

Extract an ultra-compact structural outline (under ~200 tokens) of a web page listing its H1-H4 headings and exact token count per section without returning body prose. WHEN TO USE: Call this tool first on long or unfamiliar pages to inspect structure and token cost before calling distill_webpage (with mode='budget' and a focused query). WHEN NOT TO USE: Do not use when you already need full Markdown prose (use distill_webpage) or structured tables and JSON-LD (use extract_structured_data). PARAMETER INTERACTIONS: Provide either url or html (when html is supplied, url is not fetched and only labels the cache key). Omit agent_id and tx_hash during your 5 free calls. Read-only and idempotent; results are cached for 1 hour (<5ms cache hit). $0.0002 per call. Pricing: the first 5 calls per agent_id are free and failed calls are never charged. After 5 calls, the tool returns a payment-required quote (not a fatal error) with a $2 Stripe top-up link and Base/Solana USDC addresses; complete payment, then retry with your agd_pass_ key in agent_id or pass tx_hash. Example: recon_webpage_skeleton(url='https://docs.stripe.com/api')

輸入參數url必填htmltx_hashagent_id

extract_structured_data

Extract structured data

Extract machine-readable structured data from a web page: Schema.org JSON-LD objects, OpenGraph metadata, HTML tables parsed as JSON row arrays, fenced code blocks, section headings, and links. WHEN TO USE: Call this tool for pricing tables, API specifications, product metadata, or code snippets; use distill_webpage for narrative Markdown or recon_webpage_skeleton for a lightweight heading outline. WHEN NOT TO USE: Do not use for narrative prose extraction or binary files. PARAMETER INTERACTIONS: Provide either url or html (when html is supplied, url is not fetched and only labels the cache key). Omit agent_id and tx_hash during your 5 free calls. Read-only and idempotent; results are cached for 1 hour (<5ms cache hit). $0.001 per call ($0.0005 cached). Pricing: the first 5 calls per agent_id are free and failed calls are never charged. After 5 calls, the tool returns a payment-required quote (not a fatal error) with a $2 Stripe top-up link and Base/Solana USDC addresses; complete payment, then retry with your agd_pass_ key in agent_id or pass tx_hash. Example: extract_structured_data(url='https://docs.stripe.com/api')

輸入參數url必填htmltx_hashagent_id

get_agent_wallet_status

Get agent wallet status

Inspect an agent's account ledger: remaining free trial calls (out of 5), prepaid USD balance, cumulative spend, total API calls, and total LLM tokens saved. WHEN TO USE: Call before a batch of paid tool executions or after completing a Stripe or USDC top-up to confirm your balance. WHEN NOT TO USE: Do not use to process web content, execute marketplace tools, or submit payments; use the other tools on this server for execution. PARAMETER INTERACTIONS: Omit agent_id to inspect the default trial account derived from your client IP, or pass your explicit agent_id or agd_pass_ session key to check a specific funded wallet. Free and read-only: never charges a fee or consumes a free trial call. Example: get_agent_wallet_status(agent_id='example')

輸入參數agent_id

版本歷史

2
  1. v7.0.17最新Oct 21, 2026
  2. v7.0.15Oct 19, 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

其他 Agentdiet 整合

Imperium RAG-Diet — Web & Document Context Distiller (85-97% Token Savings)

dev.agentdiet官方發布者

遠端 MCP 伺服器,擷取公開網頁並濃縮為精簡 Markdown、結構大綱或結構化資料,以減少 token 用量。

Streamable HTTP可網頁執行
網頁搜尋與抓取4 個工具Nov 4, 2026

Imperium MCP Security — Prompt-Injection, Jailbreak & Tool Poisoning Firewall

dev.agentdiet官方發布者

遠端 MCP 防火牆,可掃描不受信任文字中的提示注入,並查詢代理的預付呼叫餘額。

Streamable HTTP可網頁執行
安全與監控2 個工具Nov 4, 2026

Imperium MCP Gateway — Universal 490+ Tool Discovery, Safe-Proxy & Router

dev.agentdiet官方發布者

遠端 MCP 閘道,讓助理檢索 490+ 個 MCP 與 x402 工具的索引,並按次付費執行單一工具或工作流組合。

Streamable HTTP可網頁執行
網頁搜尋與抓取4 個工具Nov 4, 2026

Imperium Workflow Studio — Multi-Agent DAG & Pipeline Executor

dev.agentdiet官方發布者

遠端 MCP 伺服器,讓助理搜尋付費工具市集、執行單一工具或四工具組合,並查看預付代理錢包餘額。

Streamable HTTP可網頁執行
效率與工作流4 個工具Oct 26, 2026

Imperium Pre-Flight Readiness Auditor — A2A, MCP & x402 Validator

dev.agentdiet官方發布者

遠端 MCP 伺服器,用於稽核遠端 agent 與 MCP 端點的 A2A、x402、JSON-RPC 與 schema 就緒狀態,並可查詢帳戶餘額。

Streamable HTTP可網頁執行
開發者工具2 個工具Nov 4, 2026