{
  "id": "contextdev.web.scrape.markdown",
  "object": "tool",
  "name": "Scrape Markdown",
  "summary": "Scrape any URL into clean, LLM-ready Markdown.",
  "description": "Turn a single URL into clean Markdown optimized for prompts, RAG, search, and analysis. JavaScript rendering, anti-bot bypass, and premium residential proxies are handled server-side and included in the price; PDFs are fetched and parsed natively; YouTube video and channel URLs return the video or channel itself, transcript included when captions exist. Options control link and image preservation, base64 shortening, main-content-only extraction, iframe rendering, animation settling, cache reuse (maxAgeMs), an extra post-load wait (waitForMs), the proxy exit country, and whether to also return the source HTML. The response carries the Markdown plus page metadata (title, language, canonical URL, author, site name, Open Graph, Twitter card, JSON-LD).\n\nRaw contextdev#web/scrape/markdown endpoint: input is { body, queryParams, pathParams } as the provider documents them (https://docs.context.dev/api-reference/web-scraping/markdown).",
  "category": "lookup",
  "hosted_by": "Context.dev",
  "runtime": "partner",
  "side_effects": false,
  "status": "live",
  "credits": 0,
  "price": null,
  "providers": [
    {
      "id": "contextdev",
      "name": "Context.dev",
      "price": null,
      "own_key_only": true
    }
  ],
  "mcp_name": "contextdev_web_scrape_markdown",
  "input_schema": {
    "type": "object",
    "properties": {
      "queryParams": {
        "type": "object",
        "properties": {
          "url": {
            "type": "string",
            "pattern": "^https?:\\/\\/\\S+$",
            "description": "Full URL to fetch, including the http:// or https:// scheme."
          },
          "includeLinks": {
            "type": "boolean",
            "description": "Preserve hyperlinks in the Markdown output. Default true."
          },
          "includeImages": {
            "type": "boolean",
            "description": "Include image references in the Markdown output. Default false."
          },
          "shortenBase64Images": {
            "type": "boolean",
            "description": "Truncate inline base64 image payloads to keep the output small. Default true."
          },
          "useMainContentOnly": {
            "type": "boolean",
            "description": "Keep only the page's main content, dropping headers, footers, sidebars, and navigation when detectable. Default false."
          },
          "includeHTML": {
            "type": "boolean",
            "description": "Also return an html field with the page HTML the Markdown was converted from. Default false."
          },
          "includeFrames": {
            "type": "boolean",
            "description": "Render iframe contents into the output. Default false."
          },
          "maxAgeMs": {
            "type": "integer",
            "minimum": 0,
            "maximum": 2592000000,
            "description": "Reuse a cached result younger than this many milliseconds. Default 86400000 (1 day), max 2592000000 (30 days). Set 0 to always fetch fresh."
          },
          "waitForMs": {
            "type": "integer",
            "minimum": 0,
            "maximum": 30000,
            "description": "Extra browser wait in milliseconds after page load before the content is captured (0-30000). Useful for JavaScript-heavy pages."
          },
          "settleAnimations": {
            "type": "boolean",
            "description": "Wait briefly for CSS and transition animations to settle before converting the page. Default false."
          },
          "country": {
            "type": "string",
            "enum": [
              "ad",
              "ae",
              "af",
              "ag",
              "ai",
              "al",
              "am",
              "ao",
              "ar",
              "at",
              "au",
              "aw",
              "az",
              "ba",
              "bb",
              "bd",
              "be",
              "bf",
              "bg",
              "bh",
              "bi",
              "bj",
              "bm",
              "bn",
              "bo",
              "bq",
              "br",
              "bs",
              "bw",
              "by",
              "bz",
              "ca",
              "cd",
              "cf",
              "cg",
              "ch",
              "ci",
              "cl",
              "cm",
              "cn",
              "co",
              "cr",
              "cv",
              "cw",
              "cy",
              "cz",
              "de",
              "dj",
              "dk",
              "dm",
              "do",
              "dz",
              "ec",
              "ee",
              "eg",
              "es",
              "et",
              "fi",
              "fj",
              "fr",
              "ga",
              "gb",
              "gd",
              "ge",
              "gf",
              "gg",
              "gh",
              "gm",
              "gn",
              "gp",
              "gq",
              "gr",
              "gt",
              "gu",
              "gw",
              "gy",
              "hk",
              "hn",
              "hr",
              "ht",
              "hu",
              "id",
              "ie",
              "il",
              "im",
              "in",
              "iq",
              "ir",
              "is",
              "it",
              "je",
              "jm",
              "jo",
              "jp",
              "ke",
              "kg",
              "kh",
              "kn",
              "kr",
              "kw",
              "ky",
              "kz",
              "la",
              "lb",
              "lc",
              "lk",
              "lr",
              "ls",
              "lt",
              "lu",
              "lv",
              "ly",
              "ma",
              "mc",
              "md",
              "me",
              "mf",
              "mg",
              "mk",
              "ml",
              "mm",
              "mn",
              "mo",
              "mq",
              "mr",
              "mt",
              "mu",
              "mv",
              "mw",
              "mx",
              "my",
              "mz",
              "na",
              "nc",
              "ne",
              "ng",
              "ni",
              "nl",
              "no",
              "np",
              "nz",
              "om",
              "pa",
              "pe",
              "pf",
              "pg",
              "ph",
              "pk",
              "pl",
              "pr",
              "ps",
              "pt",
              "py",
              "qa",
              "re",
              "ro",
              "rs",
              "ru",
              "rw",
              "sa",
              "sc",
              "sd",
              "se",
              "sg",
              "si",
              "sk",
              "sl",
              "sm",
              "sn",
              "so",
              "sr",
              "ss",
              "st",
              "sv",
              "sx",
              "sy",
              "sz",
              "tc",
              "td",
              "tg",
              "th",
              "tj",
              "tl",
              "tm",
              "tn",
              "tr",
              "tt",
              "tw",
              "tz",
              "ua",
              "ug",
              "us",
              "uy",
              "uz",
              "vc",
              "ve",
              "vg",
              "vi",
              "vn",
              "ye",
              "yt",
              "za",
              "zm",
              "zw"
            ],
            "description": "Two-letter ISO 3166-1 alpha-2 country code, lowercase (e.g. 'us', 'gb', 'de'). Must be one of Context.dev's supported countries."
          },
          "zdr": {
            "type": "string",
            "enum": [
              "enabled",
              "disabled"
            ],
            "description": "Set 'enabled' to bypass Context.dev's shared caches and omit request and response content from its retained usage logs. Requires zero data retention on the Context.dev organization, otherwise the call fails with ZDR_NOT_ENABLED."
          }
        },
        "required": [
          "url"
        ],
        "additionalProperties": false
      }
    },
    "required": [
      "queryParams"
    ],
    "additionalProperties": false
  },
  "kind": "endpoint"
}