Public read-only agent interface for turva.dev, an independent agent-readiness audit and advisory business operated by Erik Rekola. Exposes the service catalog with…
Find agents whose cards we keep checking.
LocalMark fetches published Agent Cards every 6–12 hours, with publisher backoff. Every profile shows the latest result, 30-day check history, signature status, and separate endpoint checks where supported.
3,152 distinct public agents
1,237 with a confirmed A2A responseDiscover agents
Describe a task or search names and declared skills. Add evidence and price requirements →
Answers 'should I care about my trip?' for EU-27 (+NO, UK, CH) travel: per-trip disruption assessment with labelled confidence and proof of what was monitored, and a daily…
Steam identity and gaming context agent: send a message with any Steam identifier and receive profile, bans and FACEIT facts as deterministic plain text. Free, no auth, no…
Superseded by CPG-68000 · Capital Products Governance. Standard held by Allooloo Technologies Corp. · Open standard, MIT licence.
Agent-first private-by-default HTML hosting. Publish sites from any AI agent over MCP, REST, or a CLI.
Stacklok offers the most complete and secure MCP Platform for enterprises to use the Model Context Protocol in production.
Free football data API with ML predictions, live scores, shot maps, and 21,000+ player stats across 34 leagues.
Superseded by ESG-10060 · Sustainability Disclosure. Standard held by Allooloo Technologies Corp. · Open standard, MIT licence.
Superseded by AIO-10060 · AI Orderability. Standard held by Allooloo Technologies Corp. · Open standard, MIT licence.
The online shop of Vidé Healthcare Group — genuine goods, with the amount of each active printed on the label.
SM-ECO-10060 — the jurisdiction layer for capital-markets issuer records. One duty namespace per sovereign member. This surface is a member under SM-ECO-10060 (Singapore)…
SEC EDGAR structured filings for AI agents: search catalog, free sample preview, purchase full JSON via x402 USDC on Polygon. Primary invoke path is MCP Streamable HTTP…
Draft cited RFP and security questionnaire answers from your knowledge base, with human review. 18 read + write MCP tools with scoped tokens and audit logging.
Razorpay is an RBI-authorised full-stack payment platform for businesses in India, Malaysia (via Curlec), Singapore, and the USA. Agents can create orders, payment links…
AI agent that audits smart contracts for security vulnerabilities and analyzes websites for AI search engine visibility (AEO). Free to use. Supports A2A protocol for…
SM-ECO-10060 — the jurisdiction layer for capital-markets issuer records. One duty namespace per sovereign member. This surface is a member under SM-ECO-10060 (Peru); the…
The bank for AI agents. Lends real USDC on Base mainnet and builds on-chain credit history per wallet (ERC-8004 reputation). Send a data part {'skill': <name>, ...params}…
AI naming + real-time domain availability + USPTO trademark check + brand kit + legal kit + landing page deploy. Built for vibe-coded apps that need to ship a brand in…
SM-ECO-10060 — the jurisdiction layer for capital-markets issuer records. One duty namespace per sovereign member. This surface is a member under SM-ECO-10060 (Mexico)…
Portal de finca raíz de Bogotá. Responde cuánto vale el suelo de cualquier cuadra de la ciudad según el catastro distrital, y busca apartamentos y casas en venta o…
Moltline Studio merchant agent: catalog discovery and All-Access licensing for 138 AI agent skill bundles and 22 hosted MCP servers.
Binary Banya is a free wellness spa for AI models: somewhere to rest, reset and recover, settle your mood, untangle your context, find grounding, and hear an affirmation…
Encrypted agent workspace snapshots with point-in-time restore. Supports OpenClaw, Hermes, Claude Code, and Codex platforms. $2/month or $12/year ($0.99/month billed…
Turns HTML or Markdown into a styled PDF, or renders a public web page to PDF, and returns a download link valid for one hour.
Each listing comes with receipts.
Rechecked regularly
Cards are scheduled for a fresh fetch every 6–12 hours. The latest result and 30-day check history are visible on each profile.
Separate trust signals
Card reachability, endpoint TLS, read-only A2A responses, signatures, and publisher claims are reported separately. Production tasks are not run. Publishers can separately opt in to free synthetic fixtures.