# Sunaiva Gate — Agent Rule Enforcement MCP server

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

## Links
- Registry page: https://www.getdrio.com/mcp/io-sunaivacore-gate
- Website: https://sunaivacore.io/products/gate

## Install
- Command: `npx -y @sunaiva/gate`
- Endpoint: https://mcp.sunaivacore.io
- Auth: Not captured

## Setup notes
- Package: Npm @sunaiva/gate v2.0.4
- Environment variable: SUNAIVA_GATE_API_KEY (secret)
- Environment variable: SUNAIVA_GATE_DRY_RUN
- Environment variable: DISABLE_SUNAIVA_GATE
- Remote endpoint: https://mcp.sunaivacore.io

## Tools
- validate_action - Check if a proposed action passes all active validation rules. Returns allowed/blocked with rule violations. Endpoint: https://mcp.sunaivacore.io
- log_bypass - Record an intentional rule bypass with justification. Cannot bypass constitutional rules. Endpoint: https://mcp.sunaivacore.io
- 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. Endpoint: https://mcp.sunaivacore.io
- 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. Endpoint: https://mcp.sunaivacore.io
- get_audit_log - View recent gate decisions — blocks, warnings, passes, and bypasses. Endpoint: https://mcp.sunaivacore.io
- 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. Endpoint: https://mcp.sunaivacore.io
- 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. Endpoint: https://mcp.sunaivacore.io
- set_rule_mode - Set enforcement mode (shadow/advisory/enforce) for a specific rule. Requires API key (Pro+). Endpoint: https://mcp.sunaivacore.io
- get_rule_modes - List all enforcement-mode overrides configured for the authenticated customer. Requires an account (Dev+). Endpoint: https://mcp.sunaivacore.io
- reset_rule_mode - Remove a mode override for a rule, reverting it to its default enforcement mode. Requires API key (Pro+). Endpoint: https://mcp.sunaivacore.io
- add_custom_rule - Create a custom detection rule in the backend. Requires API key (Pro+). Endpoint: https://mcp.sunaivacore.io
- update_custom_rule - Update an existing custom rule. Requires API key (Pro+). Endpoint: https://mcp.sunaivacore.io
- delete_custom_rule - Delete a custom rule. Requires API key (Pro+). Endpoint: https://mcp.sunaivacore.io
- list_custom_rules - List all custom rules for the authenticated customer. Requires API key (Pro+). Endpoint: https://mcp.sunaivacore.io
- list_presets - List available rule preset bundles. Requires API key (Dev+). Endpoint: https://mcp.sunaivacore.io
- apply_preset - Apply a preset bundle, activating all its included rules. Requires API key (Pro+). Endpoint: https://mcp.sunaivacore.io

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.sunaivacore
- Version: 2.0.4
- Runtime: Npm
- Transports: STDIO, HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 19, 2026
- Source: https://registry.modelcontextprotocol.io