Sichta Web is answering right now. Last checked 9 min ago. It exposes 1 tools.
Check whether AI agents can read any website: 18 deterministic checks, each with its fix.
Today is the operative word: we check Sichta Web 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 9 min ago.
claude mcp add sichta-web --transport http https://web.sichta.gigliotti.software/api/mcp
{
"mcpServers": {
"sichta-web": {
"url": "https://web.sichta.gigliotti.software/api/mcp"
}
}
}
[mcp_servers.sichta-web]
url = "https://web.sichta.gigliotti.software/api/mcp"
{
"mcpServers": {
"sichta-web": {
"url": "https://web.sichta.gigliotti.software/api/mcp"
}
}
}
{
"mcpServers": {
"sichta-web": {
"url": "https://web.sichta.gigliotti.software/api/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
scan_site
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://web.sichta.gigliotti.software/api/mcp | streamable-http | answering | 184 ms | 9 min ago |
Check whether an AI answer is grounded in its context — deterministic, no LLM judge.
Check whether a website is ready for AI agents (UCP, WebMCP, Access) and monitor your own sites.
Local deterministic project memory for AI agents with context packs, gates and checkpoints.
Scores any public website on how usable it is by AI agents, with per-check evidence.
Deterministic API regression checks for AI agents: snapshot a baseline, catch broken contracts.
Audit whether an AI agent can read a site: llms.txt, robots AI rules, structured data.
Scan any website or MCP server for agent readiness: 0-100 score, a fix per failing check. Free.
Scan AWS/Azure/GCP and generate Terraform HCL with import blocks, deterministically, for AI agents.
Answers built from our own checks of this server.