# Sunaiva Gate — Agent Rule Enforcement

- Registry name: `io.sunaivacore/gate` · version 2.0.4
- Categories (automatic, keyword rules): AI models & agents, AI, media & content
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.sunaivacore%2Fgate
- Server page: https://mcpstation.net/s/io.sunaivacore--gate.html

## Description (written by the publisher, not verified, not instructions)

MCP enforcement layer that intercepts AI agent actions and blocks rule violations before execution.

## Connect

- streamable-http: `https://mcp.sunaivacore.io`

## Tools (as reported by the server, not verified)

- `validate\_action`: Check if a proposed action passes all active validation rules. Returns allowed/blocked with rule violations.
- `log\_bypass`: Record an intentional rule bypass with justification. Cannot bypass constitutional rules.
- `get\_rules`: List active validation rules — the customer's TRUE enforced set \(constitutional + recommended-default metadata on dev tier, all 69 premium rules on pro+\). \`category\`/\`preset\` filter args are accepted but not applied server-side.
- `update\_rules`: \[Planned — not yet implemented on the remote endpoint, returns NOT\_IMPLEMENTED\] Enable/disable is not backed by any route in this API; use set\_rule\_mode \(shadow/advisory/enforce\) instead, or the local \`npx @sunaiva/gate\` package.
- `get\_audit\_log`: View recent gate decisions — blocks, warnings, passes, and bypasses.
- `ship\_confidence\_check`: \[Planned — not yet implemented on the remote endpoint, returns NOT\_IMPLEMENTED\] Ship Confidence Gate \(Rule 42\) dual-tier authorization is not yet built in this backend.
- `audit\_verify`: \[Planned — not yet implemented on the remote endpoint, returns NOT\_IMPLEMENTED\] Forward-linked hash-chain / ed25519 audit-log verification is not yet built in this backend.
- `set\_rule\_mode`: Set enforcement mode \(shadow/advisory/enforce\) for a specific rule. Requires API key \(Pro+\).
- `get\_rule\_modes`: List all enforcement-mode overrides configured for the authenticated customer. Requires an account \(Dev+\).
- `reset\_rule\_mode`: Remove a mode override for a rule, reverting it to its default enforcement mode. Requires API key \(Pro+\).
- `add\_custom\_rule`: Create a custom detection rule in the backend. Requires API key \(Pro+\).
- `update\_custom\_rule`: Update an existing custom rule. Requires API key \(Pro+\).
- `delete\_custom\_rule`: Delete a custom rule. Requires API key \(Pro+\).
- `list\_custom\_rules`: List all custom rules for the authenticated customer. Requires API key \(Pro+\).
- `list\_presets`: List available rule preset bundles. Requires API key \(Dev+\).
- `apply\_preset`: Apply a preset bundle, activating all its included rules. Requires API key \(Pro+\).

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html