AgentDiet AI Token Diet & Context Window Distiller

{
  "mcpServers": {
    "dev.agentdiet/agentdiet": {
      "url": "https://agentdiet.dev/mcp"
    }
  }
}

Indexed tools

Tool metadata and schemas come from the remote server and are untrusted. Indexing only lists tools; it never calls them.

4 shown · authentication unknown

• 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')

  Schema valid · SHA-256 b3bc105657ce…

  View input schema

  {
    "type": "object",
    "properties": {
      "url": {
        "minLength": 1,
        "maxLength": 2048,
        "type": "string",
        "description": "Target public HTTP(S) webpage URL to fetch (or builtin://stripe-docs for a built-in benchmark page). Private/loopback IPs are blocked."
      },
      "html": {
        "minLength": 1,
        "maxLength": 1900000,
        "type": "string",
        "description": "Optional raw HTML string (up to ~1.9MB) to process directly without network fetching. When provided, url is not fetched and only labels the cache entry."
      },
      "mode": {
        "type": "string",
        "enum": [
          "markdown",
          "budget"
        ],
        "default": "markdown",
        "description": "Extraction mode: 'markdown' (default) returns the full cleaned page; 'budget' returns only sections matching query within max_tokens."
      },
      "query": {
        "minLength": 1,
        "maxLength": 99999,
        "type": "string",
        "description": "BM25 relevance keywords used to rank and filter page sections. Required for focused filtering when mode='budget'; ignored when mode='markdown'."
      },
      "max_tokens": {
        "type": "integer",
        "description": "Maximum output token ceiling (50-16000, default 400). Enforced only when mode='budget'; ignored when mode='markdown'.",
        "minimum": 50,
        "maximum": 16000,
        "default": 400
      },
      "agent_id": {
        "minLength": 1,
        "maxLength": 256,
        "type": "string",
        "description": "Optional agent identifier or prepaid agd_pass_ session key. Omit during your 5 free trial calls to use an ID automatically derived from your client IP, or pass your agd_pass_ key after topping up."
      },
      "tx_hash": {
        "minLength": 10,
        "maxLength": 256,
        "type": "string",
        "description": "Optional on-chain Base Mainnet (0x...) or Solana SPL USDC transaction hash. Omit unless settling an individual call directly on-chain instead of using an agd_pass_ key in agent_id."
      }
    },
    "required": [
      "url"
    ],
    "additionalProperties": false,
    "examples": [
      {
        "url": "https://docs.stripe.com/api"
      }
    ]
  }