AgentRead
Web pages to clean Markdown for AI agents. 5 free calls/day, then pay per call via x402 on Base.
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": {
"agentread": {
"url": "https://agentread.omar-cv.workers.dev/mcp"
}
}
}遠端端點
https://agentread.omar-cv.workers.dev/mcpstreamable-http它能做什麼
工具清單
工具（3）
🟢inspect_url(url)
Free, lightweight check of a public URL: reachability, HTTP status, final URL after redirects, content type, page title, and whether extraction is likely to work. Downloads at most a small prefix of the page.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"minLength": 1,
"maxLength": 2048,
"description": "Absolute public http:// or https:// URL. Default ports only; no credentials; no IP literals."
}
},
"required": [
"url"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}輸出結構描述
{
"type": "object",
"properties": {
"schemaVersion": {
"type": "string",
"const": "1.0"
},
"operation": {
"type": "string",
"const": "inspect_url"
},
"requestedUrl": {
"type": "string"
},
"normalizedUrl": {
"type": "string"
},
"hostname": {
"type": "string"
},
"reachable": {
"type": "boolean"
},
"statusCode": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
]
},
"finalUrl": {
"type": [
"string",
"null"
]
},
"redirects": {
"type": "integer"
},
"contentType": {
"type": [
"string",
"null"
]
},
"contentLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
]
},
"isHtml": {
"type": "boolean"
},
"title": {
"type": [
"string",
"null"
]
},
"mayRequireJavaScript": {
"type": "boolean"
},
"extractionSupported": {
"type": "boolean"
},
"limitation": {
"type": [
"string",
"null"
]
}
},
"required": [
"schemaVersion",
"operation",
"requestedUrl",
"normalizedUrl",
"hostname",
"reachable",
"statusCode",
"finalUrl",
"redirects",
"contentType",
"contentLength",
"isHtml",
"title",
"mayRequireJavaScript",
"extractionSupported",
"limitation"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢extract_url(url, maxCharacters, includeLinks)
Fetch a public web page and return its main content as clean Markdown with title, description, headings and extraction metadata. Removes navigation, ads, cookie banners and scripts. Does not execute JavaScript. Paid via x402 ($0.003 per successful call; the first 5 successful calls per day are free). Returns JSON (structuredContent + text) with schemaVersion, operation, requestedUrl, finalUrl, title, description, markdown, headings[{level,text}], truncated, extraction{method,statusCode,contentType,charset,redirects,bytesFetched,characters,totalCharacters,words,warnings,durationMs}.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"minLength": 1,
"maxLength": 2048,
"description": "Absolute public http:// or https:// URL. Default ports only; no credentials; no IP literals."
},
"maxCharacters": {
"type": "integer",
"minimum": 100,
"maximum": 100000,
"description": "Maximum Markdown characters to return (default 20000, max 100000)."
},
"includeLinks": {
"type": "boolean",
"description": "Keep hyperlinks and images in the Markdown (default true). When false, link text is kept as plain text."
}
},
"required": [
"url"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢extract_url_structured(url, maxCharacters, includeLinks)
Fetch a public web page and return structured data: page metadata (title, description, canonical URL, language, site name, byline), main content Markdown, ordered headings with levels, and links (text + URL). Deterministic HTML processing, no LLM. Paid via x402 ($0.005 per successful call; the first 5 successful calls per day are free). Returns JSON with schemaVersion, operation, requestedUrl, finalUrl, metadata{title,description,canonicalUrl,language,siteName,byline,publishedTime}, markdown, headings, headingsTruncated, links[{text,url}], linksTruncated, truncated, extraction{...}.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"minLength": 1,
"maxLength": 2048,
"description": "Absolute public http:// or https:// URL. Default ports only; no credentials; no IP literals."
},
"maxCharacters": {
"type": "integer",
"minimum": 100,
"maximum": 100000,
"description": "Maximum Markdown characters to return (default 20000, max 100000)."
},
"includeLinks": {
"type": "boolean",
"description": "Keep hyperlinks and images in the Markdown (default true). When false, link text is kept as plain text."
}
},
"required": [
"url"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}社群
證據