Siftwright web data
Web data for agents: YouTube transcripts, screenshots, Google News, WHOIS, jobs, tech stack, more.
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": {
"web-data": {
"url": "https://siftwright.com/mcp"
}
}
}遠端端點
https://siftwright.com/mcpstreamable-http它能做什麼
工具清單
工具（9）
🟢youtube_transcript(urls, language, translateTo, outputFormats, maxVideosPerSource)
Get transcripts (captions) for YouTube videos, Shorts, playlists or channels as plain text and timed segments, with video metadata. Uses the captions YouTube already has; videos without captions return a failed item. Each video whose transcript comes back counts as one result on your Siftwright plan; failures are free.
輸入結構描述
{
"type": "object",
"properties": {
"urls": {
"type": "array",
"items": {
"type": "string"
},
"minItems": 1,
"maxItems": 10,
"description": "1 to 10 YouTube video, Shorts, playlist or channel URLs (or 11-character video IDs)."
},
"language": {
"type": "string",
"description": "Preferred caption language code(s), comma-separated in order of preference. Default en."
},
"translateTo": {
"type": "string",
"description": "Optional language code to machine-translate the captions into."
},
"outputFormats": {
"type": "array",
"items": {
"type": "string",
"enum": [
"text",
"segments",
"srt",
"vtt"
]
},
"description": "Default [\"text\",\"segments\"]."
},
"maxVideosPerSource": {
"type": "integer",
"minimum": 1,
"maximum": 25,
"description": "For playlists and channels. Default 10."
}
},
"required": [
"urls"
]
}🟢website_screenshot(urls, format, fullPage, viewportWidth, viewportHeight, ...)
Capture a PNG or JPEG screenshot, or render a PDF, of public web pages in a real browser. Returns a signed fileUrl per page that can be downloaded without a key for 7 days. Each page captured counts as one result.
輸入結構描述
{
"type": "object",
"properties": {
"urls": {
"type": "array",
"items": {
"type": "string"
},
"minItems": 1,
"maxItems": 5,
"description": "1 to 5 http(s) URLs."
},
"format": {
"type": "string",
"enum": [
"png",
"jpeg",
"pdf"
],
"description": "Default png."
},
"fullPage": {
"type": "boolean",
"description": "Capture the whole page height. Default true."
},
"viewportWidth": {
"type": "integer",
"minimum": 320,
"maximum": 3840,
"description": "Default 1280."
},
"viewportHeight": {
"type": "integer",
"minimum": 240,
"maximum": 2160,
"description": "Default 800."
},
"pdfPageFormat": {
"type": "string",
"enum": [
"A4",
"A3",
"Letter",
"Legal"
]
},
"waitForSelector": {
"type": "string",
"description": "CSS selector to wait for before capturing."
},
"delaySec": {
"type": "integer",
"minimum": 0,
"maximum": 10
}
},
"required": [
"urls"
]
}🟢google_news(query, maxItems, language, country)
Search Google News for a keyword, company or topic and get articles as structured data (title, link, source, published time). Each article returned counts as one result.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "What to search for, up to 300 characters."
},
"maxItems": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"description": "Default 30."
},
"language": {
"type": "string",
"description": "Default en."
},
"country": {
"type": "string",
"description": "Two-letter country code. Default US."
}
},
"required": [
"query"
]
}🟢pqc_scan(hosts)
Check whether domains use post-quantum TLS key exchange (X25519MLKEM768 / ML-KEM), which groups they prefer, TLS 1.2/1.3 support, certificate algorithms and expiry, and HSTS, with a letter grade. Each host that answers counts as one result.
輸入結構描述
{
"type": "object",
"properties": {
"hosts": {
"type": "array",
"items": {
"type": "string"
},
"minItems": 1,
"maxItems": 20,
"description": "1 to 20 public domain names (a URL is fine; the hostname is used)."
}
},
"required": [
"hosts"
]
}🟢contact_details(urls, maxPagesPerDomain)
Find public emails, phone numbers and social profiles (LinkedIn, X/Twitter, Facebook, Instagram, YouTube) on company websites by crawling up to a few pages of each site. Each website with a successful crawl counts as one result.
輸入結構描述
{
"type": "object",
"properties": {
"urls": {
"type": "array",
"items": {
"type": "string"
},
"minItems": 1,
"maxItems": 10,
"description": "1 to 10 company websites or domains."
},
"maxPagesPerDomain": {
"type": "integer",
"minimum": 1,
"maximum": 15,
"description": "Pages to crawl per site. Default 6."
}
},
"required": [
"urls"
]
}🟢tech_stack(urls, includeDns)
Detect what a website is built with: CMS, ecommerce platform, frameworks, analytics, ad pixels, hosting, CDN, email and DNS provider, with the evidence for each detection. Each website that loads counts as one result.
輸入結構描述
{
"type": "object",
"properties": {
"urls": {
"type": "array",
"items": {
"type": "string"
},
"minItems": 1,
"maxItems": 20,
"description": "1 to 20 websites or domains."
},
"includeDns": {
"type": "boolean",
"description": "Add DNS-based detections (email and DNS provider). Default true."
}
},
"required": [
"urls"
]
}🟢app_store_reviews(apps, countries, maxReviewsPerApp, sortBy, minRating, ...)
Get Apple App Store reviews for apps (by name, numeric ID or URL) in one or more countries, filtered by rating, keywords and date. Every 25 reviews returned count as one result (rounded up per request).
輸入結構描述
{
"type": "object",
"properties": {
"apps": {
"type": "array",
"items": {
"type": "string"
},
"minItems": 1,
"maxItems": 5,
"description": "1 to 5 app names, App Store IDs or URLs."
},
"countries": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 5,
"description": "Two-letter storefront codes. Default [\"us\"]."
},
"maxReviewsPerApp": {
"type": "integer",
"minimum": 1,
"maximum": 2000,
"description": "Default 200."
},
"sortBy": {
"type": "string",
"enum": [
"mostrecent",
"mosthelpful"
]
},
"minRating": {
"type": "integer",
"minimum": 1,
"maximum": 5
},
"maxRating": {
"type": "integer",
"minimum": 1,
"maximum": 5
},
"keywords": {
"type": "array",
"items": {
"type": "string"
},
"description": "Keep only reviews mentioning any of these words."
},
"since": {
"type": "string",
"description": "ISO date; keep only reviews on or after it."
}
},
"required": [
"apps"
]
}🟢ats_jobs(companies, titleKeywords, excludeTitleKeywords, locations, departments, ...)
List open jobs from company careers pages on Greenhouse, Lever, Ashby, SmartRecruiters and Recruitee in one schema (title, team, location, remote, salary when published, apply URL), with title, location, department and recency filters. Every 3 jobs returned count as one result (rounded up per request).
輸入結構描述
{
"type": "object",
"properties": {
"companies": {
"type": "array",
"items": {
"type": "string"
},
"minItems": 1,
"maxItems": 10,
"description": "1 to 10 careers-page URLs, company domains, or ats:slug values like greenhouse:airbnb."
},
"titleKeywords": {
"type": "array",
"items": {
"type": "string"
}
},
"excludeTitleKeywords": {
"type": "array",
"items": {
"type": "string"
}
},
"locations": {
"type": "array",
"items": {
"type": "string"
}
},
"departments": {
"type": "array",
"items": {
"type": "string"
}
},
"remoteOnly": {
"type": "boolean"
},
"postedWithinDays": {
"type": "integer",
"minimum": 0,
"maximum": 365,
"description": "0 = any time."
},
"maxJobsPerCompany": {
"type": "integer",
"minimum": 1,
"maximum": 500,
"description": "Default 100."
},
"includeDescription": {
"type": "boolean",
"description": "Include full job description text. Default false."
}
},
"required": [
"companies"
]
}🟢domain_whois(domains, includeDns)
Look up who a domain is registered with, when it was created, when it expires, its status, nameservers and DNSSEC (from RDAP/WHOIS registries), plus A, MX, SPF and DMARC records, and whether it looks available. Every 3 domains with a registry answer count as one result (rounded up per request).
輸入結構描述
{
"type": "object",
"properties": {
"domains": {
"type": "array",
"items": {
"type": "string"
},
"minItems": 1,
"maxItems": 50,
"description": "1 to 50 domain names."
},
"includeDns": {
"type": "boolean",
"description": "Add A, MX, SPF and DMARC records. Default true."
}
},
"required": [
"domains"
]
}社群
證據