Trust infrastructure for AI agents (RFC .well-known autodiscovery)
Show HN: Trust infrastructure for AI agents (RFC .well-known autodiscovery)
Trust infrastructure for AI agents (RFC .well-known autodiscovery) is a company in show hn launch.
Profile
AI agents browse your site but can't verify what they're clicking on. No trust chains, no structured intent, just pixel-guessing.Built MCP (Model Context Protocol) to fix this:- RFC 8615 .well-known/mcp.llmfeed.json autodiscovery - Structured JSON feeds declaring site capabilities & intent - Ed25519 cryptographic signatures for trust verification - Cross-LLM compatibility (Claude, GPT, Gemini tested)Example feed: { "capabilities": [{"intent": "search", "endpoint": "/api/search"}], "trust": {"signed_blocks": ["capabilities"], "algorithm": "Ed25519"} }Agent workflow: visit yoursite.com → GET /.well-known/mcp.llmfeed.json → discover capabilities → verify signatures → act with context.30-second
Its activity falls under show hn launch; the profile below is assembled from public directory data.
It is recorded at the Show HN launch stage.
| Sector | Show HN launch |
|---|---|
| Stage | Show HN launch |
Website: wellknownmcp.org/hn
Browse related
Create a free account