arch-tools-mcp
63 production tools for AI agents — one API key, pay per call in USDC (x402) or Stripe credits.
我该使用它吗
质量与安全性
发现（79）
- LOWTool 'ai-generate' description lacks action verb在 ai-generate 中
- LOWTool 'ai-oracle' description lacks action verb在 ai-oracle 中
- LOWTool 'crypto-fear-greed' description lacks action verb在 crypto-fear-greed 中
- LOWTool 'crypto-market-cap' description lacks action verb在 crypto-market-cap 中
- LOWTool 'crypto-ohlcv' description lacks action verb在 crypto-ohlcv 中
- LOWTool 'crypto-price' description lacks action verb在 crypto-price 中
- LOWTool 'crypto-sentiment' description lacks action verb在 crypto-sentiment 中
- LOWTool 'extract-entities' description lacks action verb在 extract-entities 中
- LOWTool 'extract-pdf' description lacks action verb在 extract-pdf 中
- LOWTool 'language-detect' description lacks action verb在 language-detect 中
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"arch-tools-mcp": {
"url": "https://arch-tools-mcp.onrender.com/sse"
}
}
}远程端点
https://arch-tools-mcp.onrender.com/ssessehttps://arch-tools-mcp.onrender.com/mcpstreamable-httphttps://archtools.dev/mcpstreamable-http它能做什么
工具清单
工具（63）
⚪ai-generate(model, prompt, system, max_tokens)
AI-powered text generation using Claude (requires ANTHROPIC_API_KEY)
输入模式
{
"type": "object",
"properties": {
"model": {
"enum": [
"claude-sonnet-4-6",
"claude-opus-4-6",
"claude-haiku-4-5-20251001"
],
"type": "string",
"default": "claude-sonnet-4-6"
},
"prompt": {
"type": "string",
"maxLength": 10000,
"description": "Generation prompt"
},
"system": {
"type": "string",
"maxLength": 2000,
"description": "Optional system prompt"
},
"max_tokens": {
"type": "integer",
"default": 1000,
"maximum": 4096,
"minimum": 100
}
},
"required": [
"prompt"
]
}⚪ai-oracle
AI reasoning engine with standard and deep analysis modes
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}⚪barcode-generate(value, width, format, height, include_text)
Generate Code128 barcodes as SVG
输入模式
{
"type": "object",
"properties": {
"value": {
"type": "string",
"description": "Value to encode"
},
"width": {
"type": "integer",
"default": 300,
"maximum": 800,
"minimum": 80
},
"format": {
"enum": [
"code128",
"code39",
"ean13",
"upca"
],
"type": "string",
"default": "code128"
},
"height": {
"type": "integer",
"default": 80,
"maximum": 300,
"minimum": 30
},
"include_text": {
"type": "boolean",
"default": true
}
},
"required": [
"value"
]
}⚪browser-task(url, text, action, selector)
Headless browser automation (click/type/extract) via Playwright — SSRF hardened
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "URL to open"
},
"text": {
"type": "string",
"description": "Text for type action"
},
"action": {
"enum": [
"extract",
"click",
"type",
"html"
],
"type": "string",
"default": "extract"
},
"selector": {
"type": "string",
"description": "CSS selector (required for click/type, optional for extract)"
}
},
"required": [
"url"
]
}🟢check-domain
Check if a domain is available or registered via RDAP. No API key needed.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}⚪convert-format(to, data, from)
Convert data between JSON, YAML, CSV, and XML formats
输入模式
{
"type": "object",
"properties": {
"to": {
"enum": [
"json",
"yaml",
"csv",
"xml"
],
"type": "string"
},
"data": {
"description": "Data to convert (string or object)"
},
"from": {
"enum": [
"json",
"yaml",
"csv",
"xml"
],
"type": "string"
}
},
"required": [
"from",
"to",
"data"
]
}⚪crypto-fear-greed
Crypto Fear & Greed Index with historical data
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}🟡crypto-market-cap
Top N cryptocurrencies by market cap with price, volume, and 24h change
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}⚪crypto-news
Latest crypto news headlines. Filter by token symbol
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}⚪crypto-ohlcv
OHLCV candlestick data for any crypto over 1-90 days
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}⚪crypto-price
Real-time price, 24h change, market cap, and volume for any cryptocurrency
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}⚪crypto-sentiment
Community sentiment, social stats, and price momentum for any cryptocurrency
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}⚪currency-convert(to, from, amount)
Convert between currencies using real-time exchange rates (170+ currencies)
输入模式
{
"type": "object",
"properties": {
"to": {
"type": "string",
"maxLength": 3,
"description": "Target currency code (e.g. EUR)"
},
"from": {
"type": "string",
"maxLength": 3,
"description": "Source currency code (e.g. USD)"
},
"amount": {
"type": "number",
"description": "Amount to convert"
}
},
"required": [
"amount",
"from",
"to"
]
}🟡design-create
Generate designs and images via DALL-E 3
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}⚪diff-text(format, modified, original)
Compare two text strings and return differences in unified, word, char, or JSON format
输入模式
{
"type": "object",
"properties": {
"format": {
"enum": [
"unified",
"words",
"chars",
"json"
],
"type": "string",
"default": "unified"
},
"modified": {
"type": "string",
"description": "Modified text"
},
"original": {
"type": "string",
"description": "Original text"
}
},
"required": [
"original",
"modified"
]
}🟢domain-check
Check domain availability via RDAP
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}🟢email-find
Find email addresses for a person at a company domain
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}🟡email-send
Send transactional emails via Resend
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}⚪email-verify(email)
Deep email validation: syntax, MX record check, disposable domain detection
输入模式
{
"type": "object",
"properties": {
"email": {
"type": "string",
"description": "Email address to verify"
}
},
"required": [
"email"
]
}🟢extract-entities(text, types)
Named entity recognition: people, organizations, locations, dates, money, and more
输入模式
{
"type": "object",
"properties": {
"text": {
"type": "string",
"maxLength": 50000,
"description": "Text to extract entities from"
},
"types": {
"type": "array",
"items": {
"enum": [
"person",
"organization",
"location",
"date",
"money",
"percentage",
"email",
"url",
"phone",
"product"
],
"type": "string"
},
"description": "Entity types to extract (default: all)"
}
},
"required": [
"text"
]
}🟢extract-metadata(url, text)
Extract metadata from text or URLs (word count, OG tags, headers, etc.)
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "URL to fetch and extract metadata from"
},
"text": {
"type": "string",
"description": "Text to analyze"
}
}
}🟢extract-page(url)
Fetch a webpage and return clean text, metadata, and links
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "URL to extract"
}
},
"required": [
"url"
]
}🟢extract-pdf(url)
Extract text and tables from a PDF (requires PDF_EXTRACTOR_URL)
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Public PDF URL"
}
},
"required": [
"url"
]
}🟢fact-check
Verify the accuracy of a claim. Returns verdict (TRUE/FALSE/MIXED/UNVERIFIED/MISLEADING), confidence score, summary, and supporting/contradicting evidence with sources.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}⚪generate-hash(input, algorithm)
Generate cryptographic hashes (sha256, sha512, md5, sha1)
输入模式
{
"type": "object",
"properties": {
"input": {
"type": "string",
"description": "String to hash"
},
"algorithm": {
"enum": [
"sha256",
"sha512",
"md5",
"sha1"
],
"type": "string",
"default": "sha256"
}
},
"required": [
"input"
]
}⚪generate-image
Generate images from text prompts via DALL-E 3 (1024×1024, 1792×1024, 1024×1792).
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}⚪generate-uuid(type, count, prefix)
Generate UUIDs (v1/v4), secure random tokens, and API-key-format strings
输入模式
{
"type": "object",
"properties": {
"type": {
"enum": [
"v1",
"v4"
],
"type": "string",
"default": "v4"
},
"count": {
"type": "integer",
"default": 1,
"maximum": 100,
"minimum": 1
},
"prefix": {
"type": "string",
"maxLength": 50,
"description": "Optional prefix for each UUID"
}
}
}⚪html-to-markdown(url, html)
Convert HTML or any URL to clean Markdown
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "URL to fetch and convert"
},
"html": {
"type": "string",
"description": "HTML string to convert"
}
}
}⚪image-generate(style, width, height, prompt, quality)
Generate SVG images from text prompts via Claude
输入模式
{
"type": "object",
"properties": {
"style": {
"enum": [
"vivid",
"natural"
],
"type": "string",
"default": "vivid"
},
"width": {
"enum": [
1024,
1792
],
"type": "integer",
"default": 1024
},
"height": {
"enum": [
1024,
1792
],
"type": "integer",
"default": 1024
},
"prompt": {
"type": "string",
"maxLength": 4000,
"description": "Image description / prompt"
},
"quality": {
"enum": [
"standard",
"hd"
],
"type": "string",
"default": "standard"
}
},
"required": [
"prompt"
]
}🔴image-remove-bg
Remove background from any image
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}⚪ip-lookup(ip)
Geolocate any IP address — country, city, timezone, ISP, VPN/proxy detection
输入模式
{
"type": "object",
"properties": {
"ip": {
"type": "string",
"description": "IPv4 or IPv6 address to look up"
}
},
"required": [
"ip"
]
}🟢jsonpath-query(json, path)
Run JSONPath expressions against any JSON payload
输入模式
{
"type": "object",
"properties": {
"json": {
"description": "JSON object or string to query"
},
"path": {
"type": "string",
"description": "JSONPath expression starting with $"
}
},
"required": [
"json",
"path"
]
}⚪language-detect(text)
Detect the language of any text with confidence score and script identification
输入模式
{
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "Text to detect language of"
}
},
"required": [
"text"
]
}🟢news-search
Search for recent news articles on any topic. Returns title, URL, description, source, and publication date from Brave News, Tavily, or Serper.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}🟢ocr-extract(prompt, image_url, media_type, image_base64)
Extract text from images or screenshots using AI vision (base64 or URL input)
输入模式
{
"type": "object",
"properties": {
"prompt": {
"type": "string",
"maxLength": 500,
"description": "Optional custom extraction instruction"
},
"image_url": {
"type": "string",
"description": "Public URL of the image"
},
"media_type": {
"enum": [
"image/jpeg",
"image/png",
"image/gif",
"image/webp"
],
"type": "string",
"default": "image/jpeg"
},
"image_base64": {
"type": "string",
"description": "Base64-encoded image data"
}
}
}🟢phone-validate(phone, country_code)
Parse and validate phone numbers in any format — E.164, carrier type, country
输入模式
{
"type": "object",
"properties": {
"phone": {
"type": "string",
"description": "Phone number in any format"
},
"country_code": {
"type": "string",
"maxLength": 2,
"description": "ISO 3166-1 alpha-2 country code hint (e.g. US)"
}
},
"required": [
"phone"
]
}⚪pii-detect(text, redact, replacement)
Detect and optionally redact PII: names, emails, SSNs, credit cards, API keys, and more
输入模式
{
"type": "object",
"properties": {
"text": {
"type": "string",
"maxLength": 50000,
"description": "Text to scan for PII"
},
"redact": {
"type": "boolean",
"default": false,
"description": "Return text with PII replaced"
},
"replacement": {
"type": "string",
"default": "[REDACTED]",
"description": "Replacement string when redact is true"
}
},
"required": [
"text"
]
}⚪qr-code(text, width, format, margin)
Generate QR codes from text or URLs (PNG data URL or SVG)
输入模式
{
"type": "object",
"properties": {
"text": {
"type": "string",
"maxLength": 4000,
"description": "Text or URL to encode"
},
"width": {
"type": "integer",
"default": 300,
"maximum": 1000,
"minimum": 100
},
"format": {
"enum": [
"dataurl",
"svg"
],
"type": "string",
"default": "dataurl"
},
"margin": {
"type": "integer",
"default": 2,
"maximum": 10,
"minimum": 0
}
},
"required": [
"text"
]
}🟢readability-score(text)
Compute Flesch-Kincaid readability, grade level, word count, and read time
输入模式
{
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "Text to analyze"
}
},
"required": [
"text"
]
}⚪regex-generate(flags, description, test_strings)
Generate regular expressions from plain English with explanations and test results
输入模式
{
"type": "object",
"properties": {
"flags": {
"type": "string",
"maxLength": 10,
"description": "Regex flags (e.g. 'gi')"
},
"description": {
"type": "string",
"maxLength": 500,
"description": "Plain English description of what the regex should match"
},
"test_strings": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 20,
"description": "Optional strings to test against"
}
},
"required": [
"description"
]
}⚪research-report
Generate a structured AI research report on any topic. Searches multiple sources and synthesizes findings into executive summary, key findings, and conclusion with citations.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}🟢rss-parse(url, limit)
Fetch and parse RSS or Atom feeds into clean structured JSON
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "URL of the RSS or Atom feed"
},
"limit": {
"type": "integer",
"default": 20,
"maximum": 100,
"minimum": 1
}
},
"required": [
"url"
]
}⚪screenshot-capture(url, width, height, full_page)
Capture page metadata and screenshot URL for any public URL
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "URL to screenshot"
},
"width": {
"type": "integer",
"default": 1280,
"maximum": 2560,
"minimum": 320
},
"height": {
"type": "integer",
"default": 900,
"maximum": 2048,
"minimum": 200
},
"full_page": {
"type": "boolean",
"default": true,
"description": "Capture full scrollable page"
}
},
"required": [
"url"
]
}🟢search-web(limit, query)
Search the web and return structured results (Tavily/Serper or DuckDuckGo fallback)
输入模式
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 5,
"maximum": 10,
"minimum": 1
},
"query": {
"type": "string",
"description": "Search query"
}
},
"required": [
"query"
]
}🟢semantic-search
AI-powered semantic search across web content
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}🟡send-email
Send transactional emails via Resend — plain text or HTML.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}🟢sentiment-analysis(text)
Analyze text sentiment: positive/negative/neutral with score and emotion detection
输入模式
{
"type": "object",
"properties": {
"text": {
"type": "string",
"maxLength": 50000,
"description": "Text to analyze"
}
},
"required": [
"text"
]
}🟡session-create
Create a persistent AI conversation session
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}🟡session-message
Send a message in an existing AI session
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}⚪summarize(text, style, max_length)
Summarize text in multiple styles: paragraph, bullets, tldr, headline, executive
输入模式
{
"type": "object",
"properties": {
"text": {
"type": "string",
"maxLength": 100000,
"description": "Text to summarize"
},
"style": {
"enum": [
"paragraph",
"bullets",
"tldr",
"headline",
"executive"
],
"type": "string",
"default": "paragraph"
},
"max_length": {
"type": "integer",
"default": 200,
"maximum": 1000,
"minimum": 50
}
},
"required": [
"text"
]
}⚪text-to-speech
Convert text to natural-sounding audio via ElevenLabs. Returns base64-encoded MP3.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}⚪timezone-convert(to_tz, from_tz, datetime)
Convert a datetime between any two IANA timezones
输入模式
{
"type": "object",
"properties": {
"to_tz": {
"type": "string",
"description": "Target IANA timezone (e.g. Asia/Tokyo)"
},
"from_tz": {
"type": "string",
"description": "Source IANA timezone (e.g. America/New_York). Defaults to UTC."
},
"datetime": {
"type": "string",
"description": "Datetime string to convert (ISO 8601). Defaults to now."
}
},
"required": [
"to_tz"
]
}🟢token-lookup
Search for any token by name or ticker, returns CoinGecko IDs
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}⚪transcribe-audio
Transcribe audio files to text via OpenAI Whisper. Supports 100+ languages.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}⚪transform-text(mode, text)
Transform text: uppercase, lowercase, trim, reverse, slug, title, camel, snake, base64
输入模式
{
"type": "object",
"properties": {
"mode": {
"enum": [
"uppercase",
"lowercase",
"trim",
"reverse",
"slug",
"title",
"camel",
"snake",
"base64_encode",
"base64_decode"
],
"type": "string",
"default": "uppercase"
},
"text": {
"type": "string",
"description": "Text to transform"
}
},
"required": [
"text"
]
}⚪url-shorten(url)
Shorten any URL via TinyURL
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "URL to shorten"
}
},
"required": [
"url"
]
}⚪validate-data(data, schema)
Validate JSON data against a JSON Schema
输入模式
{
"type": "object",
"properties": {
"data": {
"description": "Data to validate"
},
"schema": {
"type": "object",
"description": "JSON Schema to validate against"
}
},
"required": [
"schema",
"data"
]
}⚪video-generate
Generate short video clips from text prompts
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}🟡webhook-send(url, body, method, headers)
POST a JSON payload to any webhook URL
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Webhook endpoint URL"
},
"body": {
"description": "JSON payload to send"
},
"method": {
"enum": [
"POST",
"PUT",
"PATCH"
],
"type": "string",
"default": "POST"
},
"headers": {
"type": "object",
"description": "Optional extra headers (safe headers only)"
}
},
"required": [
"url"
]
}🟢web-scrape(url, format, selector)
Scrape and extract content from websites with optional CSS selector
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "URL to scrape"
},
"format": {
"enum": [
"text",
"html"
],
"type": "string",
"default": "text"
},
"selector": {
"type": "string",
"description": "Optional CSS selector to extract specific content"
}
},
"required": [
"url"
]
}🟢web-search(query, max_results, search_depth, include_answer)
Real-time web search with AI-synthesized answer (requires TAVILY_API_KEY)
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"maxLength": 500,
"description": "Search query"
},
"max_results": {
"type": "integer",
"default": 5,
"maximum": 10,
"minimum": 1
},
"search_depth": {
"enum": [
"basic",
"advanced"
],
"type": "string",
"default": "basic"
},
"include_answer": {
"type": "boolean",
"default": true,
"description": "Include AI-synthesized answer"
}
},
"required": [
"query"
]
}⚪whois-lookup(domain)
Look up domain registration info: registrar, created/expires dates, nameservers, status
输入模式
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "Domain name to look up (e.g. google.com)"
}
},
"required": [
"domain"
]
}⚪workflow-agent
Multi-step autonomous AI agent pipeline
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": true
}社区
证据