PDF URL Check is answering right now. Last checked 2 min ago. It exposes 30 tools. Last commit 10 Sep 2026.
HEAD a public URL and say whether it looks like a PDF. Body discarded.
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 9 September 2026. No other catalogue keeps this.
Today is the operative word: we check PDF URL Check every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 pdf-url-ok --transport http https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/pdf-url-ok/mcp
{
"mcpServers": {
"pdf-url-ok": {
"url": "https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/pdf-url-ok/mcp"
}
}
}
[mcp_servers.pdf-url-ok]
url = "https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/pdf-url-ok/mcp"
{
"mcpServers": {
"pdf-url-ok": {
"url": "https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/pdf-url-ok/mcp"
}
}
}
{
"mcpServers": {
"pdf-url-ok": {
"url": "https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/pdf-url-ok/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
fetch-status
status-catalog
agent-tool-index
browser-url-ok
calc-eval
citation
compatibility
domain-shape
figma-url-shape
file-path-ok
hn-front-count
geo-hint
github-repo-shape
iana-zones
inspect-robots
jira-key-shape
search-query-len
lib-docs-hint
memory-key-count
normalize-url
pdf-url-ok
people-search-index
playwright-url-ok
think-steps
timezone
utc-time
validate-json
weather-hint
web-fetch
wiki-title-ok
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/pdf-url-ok/mcp | streamable-http | answering | 34 ms | 2 min ago |
PDF magic-byte check, file discarded
BSON document-length band, body discarded
Your assistant writes the ebook or report; Unplain designs it and returns a publish-ready PDF.
MCP tools for AI agents: render URLs to image/PDF, check link health, convert HTML/CSV/JSON.
Extract PDFs to Markdown, RAG chunks and cited tables; publish tracked Doc Links with read stats.
Convert any public webpage to a PDF. Single narrow tool, not a bloated PDF toolkit.
Web access for agents: fetch, extract, screenshot, or PDF any public URL.
Publish an HTML document as a link anyone can open in one tap, plus PDF, image and Word export.
Answers built from our own checks of this server.