Acutis Gate is answering right now. Last checked 11 min ago.
Every AI tool call runs as the person who asked, under your rules, fully audited.
Today is the operative word: we check Acutis Gate 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 11 min ago.
claude mcp add gate --transport http https://app.acutisgo.com/api/v1/gate/mcp
https://app.acutisgo.com/api/v1/gate/mcp
[mcp_servers.gate]
url = "https://app.acutisgo.com/api/v1/gate/mcp"
{
"mcpServers": {
"gate": {
"url": "https://app.acutisgo.com/api/v1/gate/mcp"
}
}
}
{
"servers": {
"gate": {
"type": "http",
"url": "https://app.acutisgo.com/api/v1/gate/mcp"
}
}
}
This endpoint answered with an authorization challenge. The server is running, but it did not say what kind of credentials it expects.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://app.acutisgo.com/api/v1/gate/mcp | streamable-http | needs auth | 573 ms | 11 min ago |
Claude, connected to your own Oracle EPM. Each person as themselves, every call checked and logged.
The safety gate between AI agents and your servers: typed, policy-checked, audited ops tools.
The open routing layer for AI tools: tool calls routed per policy, decision on every result.
CacheTank MCP server gives every AI tool your personal context so you never start from zero.
Pre-execution gate for AI-agent tool calls. Touch ID approval. Tamper-evident audit log.
Whether AI answers name and cite your business: runs, gaps, cited sources, published evidence.
One memory for every AI tool on your team. Facts show who checked them and when.
Wraps any MCP server: identical write-tool calls run once, and every tool call is audit-logged.
Answers built from our own checks of this server.