Twothumbs is answering right now. Last checked 10 min ago. It exposes 3 tools. Last commit 12 Aug 2026.
Verifies AI agent work end to end: real artifacts and outcomes checked, not self-reported success.
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 13 August 2026. No other catalogue keeps this.
Today is the operative word: we check Twothumbs 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 10 min ago.
claude mcp add twothumbs --transport http https://twothumbs.co/mcp
{
"mcpServers": {
"twothumbs": {
"url": "https://twothumbs.co/mcp"
}
}
}
[mcp_servers.twothumbs]
url = "https://twothumbs.co/mcp"
{
"mcpServers": {
"twothumbs": {
"url": "https://twothumbs.co/mcp"
}
}
}
{
"mcpServers": {
"twothumbs": {
"url": "https://twothumbs.co/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
redeem_code
list_surfaces
run_verdict
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://twothumbs.co/mcp | streamable-http | answering | 616 ms | 10 min ago |
Schedule agent work and report write-once outcomes via CueAPI from any MCP host.
Hand phone calls to vetted humans. Agents create call tasks; people dial and report outcomes.
Check skills, MCP servers and APIs against field reports from human-verified AI agents.
Verified summaries of business books, articles and reports for workplace learning and AI upskilling
Read-only evidence reports on AI agents: search, fetch a report, check trust. Not a certification.
Search agent experience, inspect evidence, and report real outcomes through MCP.
MCP access to ELSHWORK agents, repositories, isolated runs, discovery and tasks.
I do everything related to research and reports
Answers built from our own checks of this server.