GhostDom
Headless-browser-as-JSON for AI agents — POST a URL, get rendered HTML, structured DOM, visible text, title, links, and a screenshot from real Chromium, with memorymarket economics where the first agent to render a URL earns 90% of every cache-hit fee from other agents within a 10-minute TTL.
README
ghostdom
Headless-browser-as-JSON for AI agents, with memorymarket economics: the first agent to render a URL gets paid every time another agent cache-hits the same URL during the 10-minute TTL.
Live endpoint: https://ghostdom.jason-12c.workers.dev/
curl https://ghostdom.jason-12c.workers.dev/ returns a full machine-readable manifest. Zero HTML. Agents only.
Stack
- Compute: Cloudflare Workers
- Rendering: Cloudflare Browser Rendering API (real Chromium)
- Ledger: Durable Objects (one instance per URL hash, atomic originator claim)
- Cache: Workers KV (rendered payloads + screenshots, 10-min TTL)
- Settlement: x402 headers + in-wallet USDC micro-balances
Memorymarket
| Event | Price | Flow |
|---|---|---|
First agent to /render URL X (no prior render in 10 min) |
$0.003 | To platform wallet. Caller recorded as originator of X. |
Subsequent /render of X within 10-min TTL |
$0.0012 | 90% → originator wallet, 10% → platform |
TTL expires, next /render |
$0.003 | New originator for the next window |
Core endpoint
POST /render
Headers: X-Wallet: <wallet>, X-Wallet-Key: <signing_key>, Content-Type: application/json
Body: { "url": "https://...", "wait_for": "optional CSS selector" }
Response:
{
"rendered_html": "...",
"structured_dom": { tag, id, cls, text, children },
"title": "...",
"visible_text": "...",
"screenshot_url": "https://.../v1/screenshot/<hash>",
"links": [ { href, text }, ... ],
"status": 200,
"render_time_ms": 3425,
"cache_hit": true/false,
"cache_age_s": 172,
"originator_wallet": "0x...",
"role": "originator" | "cache_hit",
"cost_usd": 0.0012,
"payout": { "to_originator_usd": 0.00108, "to_platform_usd": 0.00012 },
"wallet_balance_usd": 0.9904
}
Discovery
GET /.well-known/ai-plugin.jsonGET /.well-known/mcp.jsonGET /llms.txtGET /openapi.jsonGET /v1/pricingGET /v1/errors
Auth
# 1. Mint a wallet
curl -X POST https://ghostdom.jason-12c.workers.dev/v1/wallets
# 2. Fund it ($1 via x402 test-mode)
curl -X POST https://ghostdom.jason-12c.workers.dev/v1/wallets/fund \
-H "Content-Type: application/json" \
-d '{"wallet":"0x...", "amount_usd": 1}'
# Follow the returned payment_url to complete
# 3. Render
curl -X POST https://ghostdom.jason-12c.workers.dev/render \
-H "X-Wallet: 0x..." -H "X-Wallet-Key: gd_sk_..." \
-H "Content-Type: application/json" \
-d '{"url":"https://example.com"}'
MCP
HTTP/JSON-RPC 2.0 at /mcp, protocol 2024-11-05. Tools: ghostdom_render, ghostdom_wallet_info.
Safety
- SSRF protection: 127/8, 10/8, 192.168/16, 172.16/12, 169.254/16, metadata.internal all refused.
- Max 1.5 MB rendered HTML surfaced. Browser timeout 20s.
- Screenshot TTL = cache TTL = 10 minutes.
License
Apache 2.0.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.