Peek — URL metadata & Markdown is listed as active in the registry but did not answer our last check. It exposes 2 tools.
Link-preview metadata and clean page-to-Markdown for any public URL. No install.
Over the last week it answered 0.0% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 2 min ago.
claude mcp add peek --transport http https://smeltworks.com/peek/mcp
{
"mcpServers": {
"peek": {
"url": "https://smeltworks.com/peek/mcp"
}
}
}
[mcp_servers.peek]
url = "https://smeltworks.com/peek/mcp"
{
"mcpServers": {
"peek": {
"url": "https://smeltworks.com/peek/mcp"
}
}
}
{
"mcpServers": {
"peek": {
"url": "https://smeltworks.com/peek/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
peek_markdown
peek_preview
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://smeltworks.com/peek/mcp | streamable-http | answering | 483 ms | 2 min ago |
Turns any web page into clean Markdown, page metadata and classified links for LLMs.
URL-to-Markdown API for AI pipelines — clean markdown with metadata and caching.
Paid fallback for public webpages: clean text, Markdown, links, metadata, and JavaScript rendering.
Web scraping MCP — extract clean markdown, links, and metadata from any URL.
URL to clean article markdown/text + metadata and links. Deterministic. $0.001/call via x402.
Read any web page as clean Markdown for AI agents: fetch, search, metadata, links. SSRF-safe.
Any web page as clean Markdown for agents. Hosted, no install. Free tier; Pro adds JS rendering.
Fetch any URL as clean Markdown or metadata, and buy digital goods via x402 — for AI agents.
Answers built from our own checks of this server.