mcp-server
Web tools for AI agents: scrape pages to Markdown, audit SEO, detect tech stacks, check sitemaps
我該用這個嗎
品質與安全性
發現項目(2)
- LOW在 tooltrace_extract 中
- LOW在 tooltrace_links 中
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": {
"mcp-server": {
"command": "npx",
"args": [
"@tooltrace/mcp-server"
]
}
}
}可執行的套件
0.1.2stdio遠端端點
https://mcp.tooltrace.io/mcpstreamable-http它能做什麼
工具清單
工具(7)
🟢tooltrace_extract(url, render, wait_until, wait_for_selector, mode, ...)
Extract clean content from a webpage. Returns Markdown, plain text, metadata, links, JSON-LD schema, and content sections. Use this for scraping, RAG ingestion, or content analysis.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public webpage URL to extract"
},
"render": {
"default": "auto",
"description": "Rendering mode. 'never' = fast static fetch (1 credit). 'auto' = static first, browser if needed. 'always' = browser rendering (5 credits).",
"type": "string",
"enum": [
"never",
"auto",
"always"
]
},
"wait_until": {
"description": "Browser navigation milestone. Only used with browser rendering.",
"type": "string",
"enum": [
"domcontentloaded",
"load",
"networkidle"
]
},
"wait_for_selector": {
"description": "CSS selector to wait for on rendered pages.",
"type": "string",
"maxLength": 200
},
"mode": {
"default": "structured",
"description": "'structured' for parsed data, 'raw' for HTML, 'both' for everything.",
"type": "string",
"enum": [
"structured",
"raw",
"both"
]
},
"include": {
"default": [
"markdown",
"metadata",
"sections"
],
"description": "Which fields to include in the response.",
"type": "array",
"items": {
"type": "string",
"enum": [
"markdown",
"text",
"metadata",
"links",
"schema",
"sections"
]
}
}
},
"required": [
"url"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}輸出結構描述
{
"type": "object",
"properties": {
"fetch": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"mode": {
"type": "string"
},
"markdown": {
"type": "string"
},
"text": {
"type": "string"
},
"metadata": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"links": {
"type": "array",
"items": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"schema": {
"type": "array",
"items": {}
},
"sections": {
"type": "array",
"items": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"raw_html": {
"type": "string"
},
"word_count": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"content_hash": {
"type": "string"
}
},
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢tooltrace_metadata(url, render, wait_until, wait_for_selector)
Extract page metadata: title, description, canonical URL, author, publication date, favicon, Open Graph, and Twitter card fields. Lightweight alternative to full extraction.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public webpage URL"
},
"render": {
"default": "auto",
"description": "Rendering mode. 'never' = fast static fetch (1 credit). 'auto' = static first, browser if needed. 'always' = browser rendering (5 credits).",
"type": "string",
"enum": [
"never",
"auto",
"always"
]
},
"wait_until": {
"description": "Browser navigation milestone. Only used with browser rendering.",
"type": "string",
"enum": [
"domcontentloaded",
"load",
"networkidle"
]
},
"wait_for_selector": {
"description": "CSS selector to wait for on rendered pages.",
"type": "string",
"maxLength": 200
}
},
"required": [
"url"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}輸出結構描述
{
"type": "object",
"properties": {
"fetch": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"metadata": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢tooltrace_links(url, render, wait_until, wait_for_selector, mode)
Extract all links from a webpage with anchor text, internal/external classification, and normalized URLs.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public webpage URL"
},
"render": {
"default": "auto",
"description": "Rendering mode. 'never' = fast static fetch (1 credit). 'auto' = static first, browser if needed. 'always' = browser rendering (5 credits).",
"type": "string",
"enum": [
"never",
"auto",
"always"
]
},
"wait_until": {
"description": "Browser navigation milestone. Only used with browser rendering.",
"type": "string",
"enum": [
"domcontentloaded",
"load",
"networkidle"
]
},
"wait_for_selector": {
"description": "CSS selector to wait for on rendered pages.",
"type": "string",
"maxLength": 200
},
"mode": {
"default": "normalized",
"description": "'normalized' deduplicates and cleans URLs. 'raw' preserves originals.",
"type": "string",
"enum": [
"normalized",
"raw"
]
}
},
"required": [
"url"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}輸出結構描述
{
"type": "object",
"properties": {
"fetch": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"mode": {
"type": "string"
},
"count": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"links": {
"type": "array",
"items": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
}
},
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢tooltrace_schema(url, render, wait_until, wait_for_selector, mode)
Extract JSON-LD structured data from a webpage. Returns schema.org entities like Article, Product, Organization, FAQ, BreadcrumbList, etc.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public webpage URL"
},
"render": {
"default": "auto",
"description": "Rendering mode. 'never' = fast static fetch (1 credit). 'auto' = static first, browser if needed. 'always' = browser rendering (5 credits).",
"type": "string",
"enum": [
"never",
"auto",
"always"
]
},
"wait_until": {
"description": "Browser navigation milestone. Only used with browser rendering.",
"type": "string",
"enum": [
"domcontentloaded",
"load",
"networkidle"
]
},
"wait_for_selector": {
"description": "CSS selector to wait for on rendered pages.",
"type": "string",
"maxLength": 200
},
"mode": {
"default": "normalized",
"description": "'normalized' deduplicates entities. 'raw' preserves original JSON-LD blocks.",
"type": "string",
"enum": [
"normalized",
"raw"
]
}
},
"required": [
"url"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}輸出結構描述
{
"type": "object",
"properties": {
"fetch": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"mode": {
"type": "string"
},
"count": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"schema": {
"type": "array",
"items": {}
}
},
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢tooltrace_seo_audit(url, render, wait_until, wait_for_selector)
Run an SEO audit on a webpage. Returns a score (0-100), weighted checks for metadata, headings, images, canonical signals, robots directives, social tags, schema, and content length, with evidence and recommendations.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public webpage URL to audit"
},
"render": {
"default": "auto",
"description": "Rendering mode. 'never' = fast static fetch (1 credit). 'auto' = static first, browser if needed. 'always' = browser rendering (5 credits).",
"type": "string",
"enum": [
"never",
"auto",
"always"
]
},
"wait_until": {
"description": "Browser navigation milestone. Only used with browser rendering.",
"type": "string",
"enum": [
"domcontentloaded",
"load",
"networkidle"
]
},
"wait_for_selector": {
"description": "CSS selector to wait for on rendered pages.",
"type": "string",
"maxLength": 200
}
},
"required": [
"url"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}輸出結構描述
{
"type": "object",
"properties": {
"fetch": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"score": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"checks": {
"type": "array",
"items": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"metadata": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢tooltrace_tech_stack(url, render, wait_until, wait_for_selector)
Detect the technology stack of a website: CMS, frameworks, JavaScript libraries, analytics, CDN, hosting, fonts, security tools, and more. Returns categorized detections with confidence levels.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public webpage URL to analyze"
},
"render": {
"default": "auto",
"description": "Rendering mode. 'never' = fast static fetch (1 credit). 'auto' = static first, browser if needed. 'always' = browser rendering (5 credits).",
"type": "string",
"enum": [
"never",
"auto",
"always"
]
},
"wait_until": {
"description": "Browser navigation milestone. Only used with browser rendering.",
"type": "string",
"enum": [
"domcontentloaded",
"load",
"networkidle"
]
},
"wait_for_selector": {
"description": "CSS selector to wait for on rendered pages.",
"type": "string",
"maxLength": 200
}
},
"required": [
"url"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}輸出結構描述
{
"type": "object",
"properties": {
"fetch": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"url": {
"type": "string"
},
"domain": {
"type": "string"
},
"technologies_detected": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"categories": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢tooltrace_sitemap(url, render)
Inspect a website's sitemap. Discovers sitemap URLs, parses sitemap XML, and returns listed page URLs with last-modified dates and change frequencies.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Website URL or direct sitemap URL"
},
"render": {
"default": "auto",
"description": "Rendering mode. 'never' = fast static fetch (1 credit). 'auto' = static first, browser if needed. 'always' = browser rendering (5 credits).",
"type": "string",
"enum": [
"never",
"auto",
"always"
]
}
},
"required": [
"url"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}輸出結構描述
{
"type": "object",
"properties": {
"requested_url": {
"type": "string"
},
"discovery_method": {
"type": "string"
},
"documents": {
"type": "array",
"items": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"discovered_urls": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"inspected_urls": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"inspection_complete": {
"type": "boolean"
},
"limit_reason": {
"type": "string"
},
"summary": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"findings": {
"type": "array",
"items": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"urls_included": {
"type": "boolean"
},
"urls": {
"type": "array",
"items": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
}
},
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}社群
證據