Sunaiva Gate — Agent Rule Enforcement by sunaivacore.io
MCP server · indexed, not reviewed
HostedLocalvendor's own
Not reviewed
No score, grade or rank. This listing is facts from the official MCP registry and our own checks, and it stays out of the rankings until the panel reviews it.
MCP enforcement layer that intercepts AI agent actions and blocks rule violations before execution.
Facts
- MCP registry
io.sunaivacore/gate· 2.0.4- Endpoint
https://mcp.sunaivacore.io- Packages
npm@sunaiva/gate stdio- Website
- sunaivacore.io/products/gate
- npm / week
- 35
- Registry entry
- updated 19 Jul 2026
From the official MCP registry, the package registries and our own checks. JSON · Markdown
Why it's listed
- It's published in the registry under sunaivacore.io, a namespace the registry only gives to whoever proves they control that domain.
Being indexed says nothing about quality, and nobody can pay for it. Is this yours? Ask for a review.
Tools it lists 16 · about 2,374 tokens of context · checked 11 minutes ago
| Tool | What it does | Hint |
|---|---|---|
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… | |
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… | |
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+). |
What https://mcp.sunaivacore.io answered to tools/list, asked without credentials. answered without the initialize handshake. The token figure is the size of the list as sent, divided by four; a model sees about that much before it calls anything. Full definitions, input schemas included, are in the listing's JSON under mcpTools.
How its tools read to an agent 0 errors · 17 warnings · 1 note
- warnTC11update_custom_rule4 parameters without a description: description, name, severity, tier
- warnTC16add_custom_ruleno readOnlyHint or destructiveHint
- warnTC16apply_presetno readOnlyHint or destructiveHint
- warnTC16audit_verifyno readOnlyHint or destructiveHint
- warnTC16delete_custom_ruleno readOnlyHint or destructiveHint
- warnTC16get_audit_logno readOnlyHint or destructiveHint
- warnTC16get_rule_modesno readOnlyHint or destructiveHint
- warnTC16get_rulesno readOnlyHint or destructiveHint
- warnTC16list_custom_rulesno readOnlyHint or destructiveHint
- warnTC16list_presetsno readOnlyHint or destructiveHint
- warnTC16log_bypassno readOnlyHint or destructiveHint
- warnTC16reset_rule_modeno readOnlyHint or destructiveHint
- warnTC16set_rule_modeno readOnlyHint or destructiveHint
- warnTC16ship_confidence_checkno readOnlyHint or destructiveHint
- warnTC16update_custom_ruleno readOnlyHint or destructiveHint
- warnTC16update_rulesno readOnlyHint or destructiveHint
- warnTC16validate_actionno readOnlyHint or destructiveHint
- noteTC24server16 of 16 tools have no outputSchema
The checks from /check and anchor check, run each day on the list above: about 2,374 tokens of definitions. Not part of the score yet. Check your own server.