MCP MeasureMCP Measure

索引已觀測

fetcher

The web capability layer for AI agents: render, extract, DNS, SSL, WHOIS & more via x402.

我該用這個嗎

品質與安全性

A
說明品質
99%
結構描述完整度
92%
命名品質
88%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

根據工具定義與協定合規性的自動化分析。

上下文成本

~1,730Token（工具定義）
~431 B典型回應大小
中等的注意力影響（128k 上下文的 1.35%）

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": {
    "fetcher": {
      "url": "https://api.fetcher.cloud/mcp"
    }
  }
}

遠端端點

https://api.fetcher.cloud/mcpstreamable-http

它能做什麼

工具清單

工具（19）

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
⚪render_page(url, screenshot, full_page)

Render a JavaScript page in a real browser; returns rendered HTML, text, optional screenshot. (browser; $0.02/call in USDC via x402, 10 free/day).

輸入結構描述

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Target URL or hostname."
    },
    "screenshot": {
      "type": "boolean"
    },
    "full_page": {
      "type": "boolean"
    }
  },
  "required": [
    "url"
  ]
}
⚪screenshot_page(url, full_page)

Screenshot a page (real browser) as a base64 PNG/JPEG. (browser; $0.02/call in USDC via x402, 10 free/day).

輸入結構描述

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Target URL or hostname."
    },
    "full_page": {
      "type": "boolean"
    }
  },
  "required": [
    "url"
  ]
}
🟢extract_content(url, mode)

Extract a page's main content as clean Markdown + text with metadata. (content; $0.005/call in USDC via x402, 30 free/day).

輸入結構描述

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Target URL or hostname."
    },
    "mode": {
      "type": "string",
      "enum": [
        "markdown",
        "text",
        "full"
      ]
    }
  },
  "required": [
    "url"
  ]
}
⚪resolve_url(url)

Follow a URL's full redirect chain; return final URL, hops, and metadata. (web-intel; $0.003/call in USDC via x402, 50 free/day).

輸入結構描述

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Target URL or hostname."
    }
  },
  "required": [
    "url"
  ]
}
⚪unfurl_url(url)

Link preview card (title, description, image, favicon) for any URL. (content; $0.003/call in USDC via x402, 50 free/day).

輸入結構描述

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Target URL or hostname."
    }
  },
  "required": [
    "url"
  ]
}
🟢get_feed(url, limit)

Discover and parse a site's RSS/Atom feed into JSON items. (content; $0.003/call in USDC via x402, 40 free/day).

輸入結構描述

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Target URL or hostname."
    },
    "limit": {
      "type": "number"
    }
  },
  "required": [
    "url"
  ]
}
🟢get_oembed(url)

Rich embed (oEmbed) data for a media URL (YouTube, Vimeo, X, Spotify...). (content; $0.002/call in USDC via x402, 50 free/day).

輸入結構描述

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Target URL or hostname."
    }
  },
  "required": [
    "url"
  ]
}
🟢find_favicon(host)

Find a site's best icon/logo. (web-intel; $0.002/call in USDC via x402, 50 free/day).

輸入結構描述

{
  "type": "object",
  "properties": {
    "host": {
      "type": "string",
      "description": "Target URL or hostname."
    }
  },
  "required": [
    "host"
  ]
}
🟢check_robots(host, path, user_agent)

Parse robots.txt; answer whether a user-agent may crawl a path; list sitemaps. (web-intel; $0.002/call in USDC via x402, 50 free/day).

輸入結構描述

{
  "type": "object",
  "properties": {
    "host": {
      "type": "string",
      "description": "Target URL or hostname."
    },
    "path": {
      "type": "string"
    },
    "user_agent": {
      "type": "string"
    }
  },
  "required": [
    "host"
  ]
}
🟢inspect_headers(url)

HTTP response headers + security-header analysis for a URL. (web-intel; $0.002/call in USDC via x402, 50 free/day).

輸入結構描述

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Target URL or hostname."
    }
  },
  "required": [
    "url"
  ]
}
⚪dns_lookup(host)

Full DNS record dump (A/AAAA/MX/NS/TXT/SOA/CAA/CNAME) for a host. (domain-dns; $0.003/call in USDC via x402, 50 free/day).

輸入結構描述

{
  "type": "object",
  "properties": {
    "host": {
      "type": "string",
      "description": "Target URL or hostname."
    }
  },
  "required": [
    "host"
  ]
}
⚪ssl_lookup(host)

TLS certificate details (issuer, expiry, SANs) via Certificate Transparency logs. (domain-dns; $0.004/call in USDC via x402, 40 free/day).

輸入結構描述

{
  "type": "object",
  "properties": {
    "host": {
      "type": "string",
      "description": "Target URL or hostname."
    }
  },
  "required": [
    "host"
  ]
}
⚪whois_lookup(domain)

Deep domain registration record via RDAP (registrar, dates, nameservers, DNSSEC). (domain-dns; $0.005/call in USDC via x402, 40 free/day).

輸入結構描述

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string"
    }
  },
  "required": [
    "domain"
  ]
}
🟢extract_pdf(url, max_pages)

Extract text + metadata from a PDF URL (text-based PDFs). (content; $0.01/call in USDC via x402, 20 free/day).

輸入結構描述

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Target URL or hostname."
    },
    "max_pages": {
      "type": "number"
    }
  },
  "required": [
    "url"
  ]
}
⚪generate_qr(data, ecc)

Generate a QR code (SVG) for text or a URL. (utility; $0.002/call in USDC via x402, 50 free/day).

輸入結構描述

{
  "type": "object",
  "properties": {
    "data": {
      "type": "string"
    },
    "ecc": {
      "type": "string",
      "enum": [
        "L",
        "M",
        "Q",
        "H"
      ]
    }
  },
  "required": [
    "data"
  ]
}
⚪diff_pages(url_a, url_b)

Compare two pages (or one page vs its latest Wayback snapshot); return what changed. (content; $0.008/call in USDC via x402, 25 free/day).

輸入結構描述

{
  "type": "object",
  "properties": {
    "url_a": {
      "type": "string",
      "description": "Target URL or hostname."
    },
    "url_b": {
      "type": "string"
    }
  },
  "required": [
    "url_a"
  ]
}
🟢guard_inspect(text, deep)

Screen untrusted content (web pages, emails, tool output) for prompt-injection/manipulation before your agent trusts it. Returns a risk score + reasons; a screening signal, not a guarantee. (security; $0.005/call in USDC via x402, 30 free/day).

輸入結構描述

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "Untrusted content to screen."
    },
    "deep": {
      "type": "boolean",
      "description": "Use the ML classifier too (default true)."
    }
  },
  "required": [
    "text"
  ]
}
⚪guard_tx(to, data, value, chain, from)

Pre-sign wallet firewall: decode a transaction and flag unlimited approvals, setApprovalForAll, scam addresses, and spend-cap breaches before signing. Returns a risk verdict + reasons. (security; $0.008/call in USDC via x402, 25 free/day).

輸入結構描述

{
  "type": "object",
  "properties": {
    "to": {
      "type": "string"
    },
    "data": {
      "type": "string",
      "description": "Calldata (0x...)."
    },
    "value": {
      "type": "string",
      "description": "Native value in wei."
    },
    "chain": {
      "type": "string"
    },
    "from": {
      "type": "string"
    }
  },
  "required": [
    "to"
  ]
}
🟡check_domain(name, tlds, enriched)

Check domain availability across TLDs via RDAP. Set enriched=true for DNS, age, and Wayback history. (domain-dns; $0.004/call in USDC via x402, 50 free/day).

輸入結構描述

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    },
    "tlds": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "enriched": {
      "type": "boolean"
    }
  },
  "required": [
    "name"
  ]
}

建議的提示詞

find_specific
Find [specific item] using fetcher
預期的工具： find_favicon
research_workflow
Search for [topic], then get detailed information about the top results using fetcher
預期的工具： find_faviconget_feed
fetch_info
Fetch [information type] using fetcher
預期的工具： get_feed
search_research
Search for information about [topic] using fetcher
預期的工具： find_favicon
retrieve_data
Get details about [item] from fetcher
預期的工具： get_feed

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本19 個工具
已驗證未記錄版本19 個工具