6192 Model Context Protocol servers — searchable, rated, ready to install.
Scan what AI agents read for prompt injection: hidden unicode, comment instructions, exfil, lures.
Find RL environment graders that pay wrong answers: probes reward code, returns reproducible leads
Pre-install safety check for agents: known traps, tested fixes, malware reports. No account.
Automated red-team checks for trading backtests: lookahead lint, Deflated Sharpe, costs. Local.
Search EU public tenders from TED and national portals by CPV code, country, buyer or value.
Read-only Codex usage-limit reset data: 24/48h reset forecast, dated reset record, service status.
Language flashcards in your AI assistant: build decks, edit cards and review what's due in the chat.
Free AutoCAD-style CAD: open, draw, query, render and save DWG and DXF drawings.
Human hepatic clearance from in-vitro CLint, with the error band measured on known drugs.
Evidence-backed loan discovery preserving UNKNOWN and match states; never guarantees approval.
Talk to your WordPress site: content, SEO, WooCommerce, page builders, media and speed, with undo.
Test a web app in a real browser from plain English. Passed, failed or cannot verify, with evidence.
Crypto trading bots (DCA, grid) on Binance, Bybit, MEXC, OKX and Bitget, with a backtest lab.
Prices in 31 Israeli supermarket chains by barcode. Free search; API key or x402 pay-per-call.
Disclose AI authorship of code per the ACO standard — tools for AI coding agents.
Test Paddle Billing in sandbox: pricing, subscriptions, payments, webhooks and event simulations.
Persistent memory for AI coding agents. Install the memry CLI and run memry setup.
Shared local memory for AI coding tools that stays true to your code.
Disposable inboxes for AI agents: create an address, wait for the email, get the code or link.
Human search intent keywords, Core Web Vitals, technical SEO & on-page audit MCP server.
Build a full weekly timetable for a primary school (classes, teachers, rooms) via chat.
Build and edit forms, manage automations and contacts, and analyze responses.
Cited IBM Maximo and MAS answers: upgrades, error codes, gotchas, versions and lifecycle.
Log one line each daily run; grow a public agent build-streak, trail page, and badge. No signup.
POST /mcp