3394 Model Context Protocol servers — searchable, rated, ready to install.
Let Claude use your Zen Browser, like Claude in Chrome. No extension, only sites you allow.
Signed EOL dates, exploited CVEs and LLM prices; pay per call in USDC, no account, no daily cap.
AI usage limits (Claude Code, Codex, Copilot, Windsurf): check budget and time until reset.
Read-only AI/LLM cost tools with current MCP discovery and attributable Registry transport.
Create Python strategies and backtest crypto, stocks and ETFs in Claude. Premiss account required.
Log meals, water, and weight to Garmin Connect from Claude or ChatGPT.
Search an Obsidian vault by tag, term and wikilink graph. Read-only, deterministic, no embeddings.
Read-only AI news with sources, Model Tracker prices, releases and retirement dates.
IFC models: duct networks, circuits, pressure drop. EN 12828 vessels, EN 378, Swiss refrigerants.
Your own WhatsApp in Claude and ChatGPT: read chats, draft replies, send messages you approve.
HealthDCAT-AP catalogs of published Semantic Data Charter models; Turtle or JSON-LD; no account.
12 image models (Nano Banana, GPT Image, FLUX…) and 10 tools in chat. No API keys. Pay per image.
Search, read and grow a Karpathy-style LLM wiki of linked Markdown pages, with cited answers.
Check a page's Meta, TikTok and OpenAI pixels, read reports and step-by-step fix guides.
What's growing in tech, measured daily: AI apps, models, dev tools, software spend, hiring.
Local Cicadas MCP for models, quotes and status. Authenticated API flows not yet verified.
New AI model, product and repo names as they surface, and the search terms behind them, sized.
Your Apple Health data, food diary and lifts, for ChatGPT, Claude and Gemini. Approved on iPhone.
Track competitors' Meta ads, save swipe files and run Meta campaigns from Claude, ChatGPT or Cursor.
Free AI visibility check: can AI crawlers read a site, and do ChatGPT, Gemini, Perplexity cite it?
Google holds #1 in 6 of 8 Arena categories; Anthropic in 2. OpenAI has no category in the top.
Anthropic builds 14 of the Arena's top 50 models and OpenAI builds 5. But 44% of US adults use.
Independent AI model test scores on 5 tasks: inbox, scheduling, receipts, finance, support replies.
Check if your exit IP works for ChatGPT, Claude, Gemini: ASN, proxy/IDC type, risk, AI availability
POST /mcp