AgentTwin Documentation is answering right now. Last checked 3 min ago. It exposes 2 tools.
Search AgentTwin agent testing guides, Node CLI commands and supported synthetic service contracts.
Today is the operative word: we check AgentTwin Documentation 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 3 min ago.
claude mcp add agenttwin-docs --transport http https://agenttwin.si/mcp/docs
https://agenttwin.si/mcp/docs
[mcp_servers.agenttwin-docs]
url = "https://agenttwin.si/mcp/docs"
{
"mcpServers": {
"agenttwin-docs": {
"url": "https://agenttwin.si/mcp/docs"
}
}
}
{
"servers": {
"agenttwin-docs": {
"type": "http",
"url": "https://agenttwin.si/mcp/docs"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
read_doc
search_docs
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://agenttwin.si/mcp/docs | streamable-http | answering | 581 ms | 3 min ago |
Validate and test llguidance grammars with batch testing and documentation
Country verification research, integration planning and synthetic tests. No live identity checks.
Create, test and play AI-native games through server-authoritative contracts.
Run AI market research: synthetic customer panels for concept testing, message testing, segments.
Contract testing and quality gates for spreadsheets created by AI agents.
Semilattice lets agents make predictions about audiences for content testing and decision making.
Background Windows desktop for AI agents: native GUI automation, screenshots and app testing.
Track GitHub issue and Stripe test-payment outcomes; recover uncertain supported actions.
Answers built from our own checks of this server.