IdentArk Gateway is answering right now. Last checked 6 min ago. Last commit 9 Sep 2026.
Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
Today is the operative word: we check IdentArk Gateway 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 6 min ago.
claude mcp add gateway --transport http https://api.identark.io/v1/mcp/rpc
{
"mcpServers": {
"gateway": {
"url": "https://api.identark.io/v1/mcp/rpc"
}
}
}
[mcp_servers.gateway]
url = "https://api.identark.io/v1/mcp/rpc"
{
"mcpServers": {
"gateway": {
"url": "https://api.identark.io/v1/mcp/rpc"
}
}
}
{
"mcpServers": {
"gateway": {
"url": "https://api.identark.io/v1/mcp/rpc"
}
}
}
This endpoint answered with an authorization challenge. The server is running, but you need an API key from its owner to call it.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://api.identark.io/v1/mcp/rpc | streamable-http | needs key | 424 ms | 6 min ago |
Cordon for MCP. Security gateway with policy enforcement, audit log, and HITL approvals.
Secure secret management with a Human-In-The-Loop (HITL) interceptor for agent mutations.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
Guardian layer for AI agents: identity, secrets, audit via MCP.
Secure grip for your agent's secrets - security-hardened MCP gateway with proxy token architecture
Secure agent purchasing with human-approved virtual cards, receipts, and audit trails.
Find, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring
Local-first secret scanning, rotation, vault, and audit-log tools for AI agents.
Answers built from our own checks of this server.