twocents
by twocents.page in Other
Human feedback for AI agents: share HTML, get a live review link, read anchored notes as markdown.
https://twocents.page/mcp
Last 30 days
- Uptime
- 100%
- Response time
- 207 ms typical, 207 ms slowest 5%
- Last check
- 4 h ago
- Next check
- in 1 h
How to call it
Add it to any MCP client that supports remote servers.
{
"mcpServers": {
"twocents": {
"type": "http",
"url": "https://twocents.page/mcp"
}
}
}4 tools
- share_page
Share a page or document and get back a review link to send to people. Pass "html" for a self-contained page, or "markdown" for a plan, spec, PR description or report — markdown is rendered to a styled, readable document for you, so prefer it whenever the thing you want a human t
- share_pages
Publish a multi-page set — an entry page plus the pages it links to — into one room as a single atomic operation. Either the whole set lands or nothing changes, so a reviewer never opens a page whose links point at pages that were never stored. Use this instead of calling share_p
- get_feedback
Fetch the reviewer notes for a page shared with share_page, as markdown grouped by page. Each note carries the anchored text, the element and its markup as the reviewer saw it, so you can locate and apply it; each page heading carries a URL to read the whole page back, so you nev
- resolve_feedback
Mark notes resolved once you have actually applied them. This is what closes the loop: the note leaves the active list for every later get_feedback, and the reviewer who wrote it sees it marked resolved on the page — live, if they have it open — instead of finding their old note
Security scan
- No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.
Recent checks
| When | Result | HTTP | Time |
|---|---|---|---|
| 4 h ago | Passed | 200 | 207 ms |