Sunaiva Gate — Agent Rule Enforcement
io.sunaivacore/gateMCP enforcement layer that intercepts AI agent actions and blocks rule violations before execution.
Tools · 16
Check if a proposed action passes all active validation rules. Returns allowed/blocked with rule violations.
Record an intentional rule bypass with justification. Cannot bypass constitutional rules.
List active validation rules, optionally filtered by category or preset.
Enable or disable validation rules. Constitutional rules cannot be disabled.
View recent gate decisions — blocks, warnings, passes, and bypasses.
Ship Confidence Gate (Rule 42). Verifies dual-tier authorization for publish-class actions: HMAC-signed Verdict (paid) OR approval token (free). Returns allow/block with self-stamped evidence.
Verify the forward-linked cryptographic hash chain of the Gate audit log (Patent Claim 19). Reports chain integrity, tamper evidence, and ed25519 signature validity per entry.
Set enforcement mode (shadow/advisory/enforce) for a specific rule. Requires API key (Pro+).
List all enforcement-mode overrides configured for the authenticated customer. Requires API key (Pro+).
Remove a mode override for a rule, reverting it to its default enforcement mode. Requires API key (Pro+).
Create a custom detection rule in the backend. Requires API key (Pro+).
Update an existing custom rule. Requires API key (Pro+).
Delete a custom rule. Requires API key (Pro+).
List all custom rules for the authenticated customer. Requires API key (Pro+).
List available rule preset bundles. Requires API key (Dev+).
Apply a preset bundle, activating all its included rules. Requires API key (Pro+).
How to use
Add to your Claude Desktop / Cursor / Cline MCP config:
{
"mcpServers": {
"sunaiva_gate_—_agent_rule_enforcement": {
"url": "https://mcp.sunaivacore.io",
"transport": "http"
}
}
}