scrapeunblocker-mcp-remote
Fetch any web page's HTML, AI-parsed JSON, or Google results via the ScrapeUnblocker anti-bot API
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"scrapeunblocker-mcp-remote": {
"url": "https://mcp.scrapeunblocker.com/mcp"
}
}
}遠端端點
https://mcp.scrapeunblocker.com/mcpstreamable-http它能做什麼
工具清單
工具（4）
🟢fetch_html(url, proxy_country, wait_method, wait_value, sleep_seconds, ...)
Fetch the fully rendered HTML of any web page through the ScrapeUnblocker API (https://docs.scrapeunblocker.com), bypassing anti-bot protection (Cloudflare, DataDome, PerimeterX, Akamai, Shape). Use when a normal fetch is blocked (403/429, captcha) or the page needs a real browser. Returns raw HTML. Pass `steps` to interact with the page (search, click, paginate) before capture - use the list_elements tool first to discover selectors.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "The absolute URL to fetch (http/https)."
},
"proxy_country": {
"type": "string",
"minLength": 2,
"maxLength": 2,
"description": "Optional ISO country code to route through, e.g. 'US'."
},
"wait_method": {
"type": "string",
"enum": [
"css",
"js"
],
"description": "Optional render-wait: 'css' selector or 'js' expression."
},
"wait_value": {
"type": "string",
"description": "The selector/expression paired with wait_method."
},
"sleep_seconds": {
"type": "number",
"exclusiveMinimum": 0,
"description": "Extra seconds to wait after load."
},
"steps": {
"type": "array",
"items": {
"type": "object",
"properties": {
"action": {
"type": "string",
"enum": [
"wait_for",
"wait_for_text",
"wait",
"click",
"type",
"select",
"press_key",
"scroll"
],
"description": "The action to perform."
},
"selector": {
"type": "string",
"description": "CSS selector the action targets (required for wait_for/click/type/select)."
},
"selector_type": {
"type": "string",
"enum": [
"css",
"xPath",
"className",
"tagName"
],
"description": "How to interpret `selector` (default 'css')."
},
"value": {
"type": [
"string",
"number"
],
"description": "Action payload: text to type/select, text for wait_for_text, a key name for press_key (e.g. 'Enter'), milliseconds for wait, or 'bottom'/pixels for scroll."
},
"clear": {
"type": "boolean",
"description": "For 'type': clear the field first."
},
"timeout_ms": {
"type": "integer",
"exclusiveMinimum": 0,
"description": "Per-step timeout override in ms."
}
},
"required": [
"action"
],
"additionalProperties": false
},
"description": "Ordered browser actions to run in a real browser after the page loads (wait_for, wait_for_text, wait, click, type [human-like], select, press_key, scroll), then return the resulting HTML. NON-IDEMPOTENT: it runs once and is not retried. A failed step returns a 422 naming the offending step plus the page HTML at that point. Discover selectors with list_elements first."
}
},
"required": [
"url"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢fetch_parsed(url, proxy_country)
Fetch a web page through the ScrapeUnblocker API (https://docs.scrapeunblocker.com) and return AI-parsed structured JSON instead of raw HTML (product details, article content, listings). If the page holds no structured data, the result says so (that call is not billed) - use fetch_html for the page itself.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "The absolute URL to fetch and parse."
},
"proxy_country": {
"type": "string",
"minLength": 2,
"maxLength": 2,
"description": "Optional ISO country code, e.g. 'US'."
}
},
"required": [
"url"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢google_search(keyword, proxy_country, pages_to_check)
Run a Google search through the ScrapeUnblocker API (https://docs.scrapeunblocker.com) and return organic results as JSON.
輸入結構描述
{
"type": "object",
"properties": {
"keyword": {
"type": "string",
"minLength": 1,
"description": "The search query."
},
"proxy_country": {
"type": "string",
"minLength": 2,
"maxLength": 2,
"description": "Optional ISO country code to search from, e.g. 'US'."
},
"pages_to_check": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 10,
"description": "How many result pages to collect (default 1)."
}
},
"required": [
"keyword"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢list_elements(url, proxy_country, wait_method, wait_value, sleep_seconds)
Fetch a page through the ScrapeUnblocker API (https://docs.scrapeunblocker.com) and return its interactive elements (buttons, inputs, selects, links, forms), each with a ready-to-use selector, as JSON {url, count, elements:[...]} instead of raw HTML. Use it to discover what to target, then drive the page with the `steps` param of fetch_html.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "The absolute URL to load and inspect (http/https)."
},
"proxy_country": {
"type": "string",
"minLength": 2,
"maxLength": 2,
"description": "Optional ISO country code to route through, e.g. 'US'."
},
"wait_method": {
"type": "string",
"enum": [
"css",
"js"
],
"description": "Optional render-wait: 'css' selector or 'js' expression."
},
"wait_value": {
"type": "string",
"description": "The selector/expression paired with wait_method."
},
"sleep_seconds": {
"type": "number",
"exclusiveMinimum": 0,
"description": "Extra seconds to wait after load before inspecting."
}
},
"required": [
"url"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}社群
證據