SOLGPT // agent pages

Agent sitemap

SOLGPT is a natural-language Solana trading desk: live pump.fun tape, Jupiter/DFlow swaps, x402 agent wallets, and clawd bots. These pages are real HTML with real <a href> links so a computer (Orgo / e2b / browser) can browse without fighting the React SPA, wallet modal, or canvas.

How to browse

  1. Open /llms.txt (this index in plain text).
  2. Open /agent/ (this sitemap).
  3. Follow links. Prefer .md if you speak markdown (Accept: text/markdown also works).
  4. If you speak MCP, call POST /mcp (tools/list then tools/call).

Which pages need $CLAWD

Computer, media/art, and Grok/Hauhau need 100,000 $CLAWD. Everything else on this sitemap is public.

Sitemap

JSON APIs (no wallet)

Live tape: wss://clawd-ws.fly.dev/ws. Grok Bot: https://x.ai/bot/KZEcx_uMDR-zJIXLlYw5I. Hosts: x402.life, clawdbot.x402.life.

What this does and how it works

Two parts sit in front of the origin. Same for these static pages and the React SPA.

  1. Edge/origin injects one line: a module script at /.webmcp/bridge.js with data-packs="c2pa,mcp-server-client" and data-mcp-url="/mcp". Cloudflare may also inject this at the edge. This origin copy is the fallback.
  2. The bridge finds document.modelContext. If the browser has no WebMCP surface, it no-ops and the page is unchanged.

Packs register MCP tools. The Site MCP Server pack discovers tools from same-origin POST /mcp (tools/list) and proxies tools/call with credentials: same-origin. The Content Credentials pack (c2pa) reads image provenance in the visitor browser.

Agents already speaking MCP can drive the page. clawd-bot computers: open /llms.txt then /agent/ then call /mcp.

$CLAWD still gates computer, art, Grok/Hauhau (100,000 $CLAWD). Public MCP tools are read-only (pages, trending, health, pump quote). No keys.

Longer explainer: WebMCP.