Sunaiva Gate — Agent Rule Enforcement is an MCP server with 16 tools an agent can call, among them add_custom_rule, apply_preset, audit_verify. It answers at https://mcp.sunaivacore.io over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 24 October 2026, succeeded.
MCP enforcement layer that intercepts AI agent actions and blocks rule violations before execution.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
add_custom_rule | Create a custom detection rule in the backend. Requires API key (Pro+). Inputs: name, description, detection_pattern, severity, tier |
apply_preset | Apply a preset bundle, activating all its included rules. Requires API key (Pro+). Inputs: preset_id |
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. |
delete_custom_rule | Delete a custom rule. Requires API key (Pro+). Inputs: id |
get_audit_log | View recent gate decisions — blocks, warnings, passes, and bypasses. Inputs: limit, rule_id |
get_rule_modes | List all enforcement-mode overrides configured for the authenticated customer. Requires an account (Dev+). |
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. Inputs: category, preset |
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+). |
log_bypass | Record an intentional rule bypass with justification. Cannot bypass constitutional rules. Inputs: rule_id, reason |
reset_rule_mode | Remove a mode override for a rule, reverting it to its default enforcement mode. Requires API key (Pro+). Inputs: rule_id |
set_rule_mode | Set enforcement mode (shadow/advisory/enforce) for a specific rule. Requires API key (Pro+). Inputs: rule_id, mode, agent_id |
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. Inputs: artifact_id, command_preview, label |
update_custom_rule | Update an existing custom rule. Requires API key (Pro+). Inputs: id, name, description, detection_pattern, severity, tier |
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. Inputs: enable, disable |
validate_action | Check if a proposed action passes all active validation rules. Returns allowed/blocked with rule violations. Inputs: action, context |
Every block below points at https://mcp.sunaivacore.io. Pick your client and copy.
claude mcp add --transport http sunaiva-gate-agent-rule-enforcem https://mcp.sunaivacore.io
{
"mcpServers": {
"sunaiva-gate-agent-rule-enforcem": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.sunaivacore.io"]
}
}
}{
"mcpServers": {
"sunaiva-gate-agent-rule-enforcem": {
"url": "https://mcp.sunaivacore.io"
}
}
}{
"servers": {
"sunaiva-gate-agent-rule-enforcem": {
"type": "http",
"url": "https://mcp.sunaivacore.io"
}
}
}{
"context_servers": {
"sunaiva-gate-agent-rule-enforcem": {
"url": "https://mcp.sunaivacore.io"
}
}
}{
"mcpServers": {
"sunaiva-gate-agent-rule-enforcem": {
"serverUrl": "https://mcp.sunaivacore.io"
}
}
}{
"mcpServers": {
"sunaiva-gate-agent-rule-enforcem": {
"url": "https://mcp.sunaivacore.io"
}
}
}name: Sunaiva Gate — Agent Rule Enforcement
version: 0.0.1
schema: v1
mcpServers:
- name: Sunaiva Gate — Agent Rule Enforcement
type: streamable-http
url: https://mcp.sunaivacore.io{
"mcpServers": {
"sunaiva-gate-agent-rule-enforcem": {
"httpUrl": "https://mcp.sunaivacore.io"
}
}
}{
"mcpServers": {
"sunaiva-gate-agent-rule-enforcem": {
"type": "http",
"url": "https://mcp.sunaivacore.io"
}
}
}{
"mcpServers": {
"sunaiva-gate-agent-rule-enforcem": {
"url": "https://mcp.sunaivacore.io"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.sunaivacore.io&type=streamable_http&id=sunaiva-gate-agent-rule-enforcem&name=Sunaiva%20Gate%20%E2%80%94%20Agent%20Rule%20Enforcement
It answered our last check on 24 October 2026 in 130 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by sunaivacore.io and served from mcp.sunaivacore.io, the vendor's own domain: https://mcp.sunaivacore.io.
16, as returned by the server's own tools/list on 22 September 2026: add_custom_rule, apply_preset, audit_verify, delete_custom_rule, get_audit_log, get_rule_modes, get_rules, list_custom_rules, and 8 more.
It answered our last check on 24 October 2026 in 130 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.sunaivacore.io. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.sunaivacore. Endpoint host: mcp.sunaivacore.io. ARD identifier: urn:air:io.sunaivacore:mcp:gate.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.