// MCP TOOL REFERENCE

ARCH TOOLS MCP TOOLS

64 tools from the Arch Tools Mcp MCP Server, categorised by risk level.

View the Arch Tools Mcp policy → Token cost: 5,389 tokens →

// ALL 64 ARCH TOOLS MCP TOOLS

READ 43 tools

Read ai-oracle AI reasoning engine with standard and deep analysis modes Read browser-task Headless browser automation (click/type/extract) via Playwright — SSRF hardened Read check-domain Check if a domain is available or registered via RDAP. No API key needed. Read crypto-fear-greed Crypto Fear & Greed Index with historical data Read crypto-market-cap Top N cryptocurrencies by market cap with price, volume, and 24h change Read crypto-news Latest crypto news headlines. Filter by token symbol Read crypto-ohlcv OHLCV candlestick data for any crypto over 1-90 days Read crypto-price Real-time price, 24h change, market cap, and volume for any cryptocurrency Read crypto-sentiment Community sentiment, social stats, and price momentum for any cryptocurrency Read diff-text Compare two text strings and return differences in unified, word, char, or JSON format Read domain-check Check domain availability via RDAP Read email-find Find email addresses for a person at a company domain Read email-verify Deep email validation: syntax, MX record check, disposable domain detection Read extract-entities Named entity recognition: people, organizations, locations, dates, money, and more Read extract-metadata Extract metadata from text or URLs (word count, OG tags, headers, etc.) Read extract-page Fetch a webpage and return clean text, metadata, and links Read extract-pdf Extract text and tables from a PDF (requires PDF_EXTRACTOR_URL) Read fact-check Verify the accuracy of a claim. Returns verdict (TRUE/FALSE/MIXED/UNVERIFIED/MISLEADING), confidence score,... Read html-to-markdown Convert HTML or any URL to clean Markdown Read ip-lookup Geolocate any IP address — country, city, timezone, ISP, VPN/proxy detection Read jsonpath-query Run JSONPath expressions against any JSON payload Read language-detect Detect the language of any text with confidence score and script identification Read news-search Search for recent news articles on any topic. Returns title, URL, description, source, and publication date... Read ocr-extract Extract text from images or screenshots using AI vision (base64 or URL input) Read phone-validate Parse and validate phone numbers in any format — E.164, carrier type, country Read pii-detect Detect and optionally redact PII: names, emails, SSNs, credit cards, API keys, and more Read qr-code Generate QR codes from text or URLs (PNG data URL or SVG) Read readability-score Compute Flesch-Kincaid readability, grade level, word count, and read time Read research-report Generate a structured AI research report on any topic. Searches multiple sources and synthesizes findings i... Read screenshot-capture Capture page metadata and screenshot URL for any public URL Read search-web Search the web and return structured results (Tavily/Serper or DuckDuckGo fallback) Read semantic-search AI-powered semantic search across web content Read sentiment-analysis Analyze text sentiment: positive/negative/neutral with score and emotion detection Read summarize Summarize text in multiple styles: paragraph, bullets, tldr, headline, executive Read text-to-speech Convert text to natural-sounding audio via ElevenLabs. Returns base64-encoded MP3. Read token-lookup Search for any token by name or ticker, returns CoinGecko IDs Read transcribe-audio Transcribe audio files to text via OpenAI Whisper. Supports 100+ languages. Read url-shorten Shorten any URL via TinyURL Read validate-data Validate JSON data against a JSON Schema Read web-scrape Scrape and extract content from websites with optional CSS selector Read web-search Real-time web search with AI-synthesized answer (requires TAVILY_API_KEY) Read whois-lookup Look up domain registration info: registrar, created/expires dates, nameservers, status Read workflow-agent Multi-step autonomous AI agent pipeline

WRITE 18 tools

Write ai-generate AI-powered text generation using Claude (requires ANTHROPIC_API_KEY) Write barcode-generate Generate Code128 barcodes as SVG Write convert-format Convert data between JSON, YAML, CSV, and XML formats Write currency-convert Convert between currencies using real-time exchange rates (170+ currencies) Write design-create Generate designs and images via DALL-E 3 Write email-send Send transactional emails via Resend Write generate-hash Generate cryptographic hashes (sha256, sha512, md5, sha1) Write generate-image Generate images from text prompts via DALL-E 3 (1024×1024, 1792×1024, 1024×1792). Write generate-uuid Generate UUIDs (v1/v4), secure random tokens, and API-key-format strings Write image-generate Generate SVG images from text prompts via Claude Write regex-generate Generate regular expressions from plain English with explanations and test results Write send-email Send transactional emails via Resend — plain text or HTML. Write session-create Create a persistent AI conversation session Write session-message Send a message in an existing AI session Write social-post Post content to social media platforms Write timezone-convert Convert a datetime between any two IANA timezones Write video-generate Generate short video clips from text prompts Write webhook-send POST a JSON payload to any webhook URL

DESTRUCTIVE 1 tools

Destructive image-remove-bg Remove background from any image

EXECUTE 2 tools

Execute rss-parse Fetch and parse RSS or Atom feeds into clean structured JSON Execute transform-text Transform text: uppercase, lowercase, trim, reverse, slug, title, camel, snake, base64

// FAQ

How many tools does the Arch Tools Mcp MCP server have? +

The Arch Tools Mcp MCP server exposes 64 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Arch Tools Mcp tools? +

Route the Arch Tools Mcp server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Arch Tools Mcp tools fall into? +

Arch Tools Mcp tools are categorised as Read (43), Write (18), Destructive (1), Execute (2). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.