# Sunaiva Gate — Agent Rule Enforcement (remote · mcp.sunaivacore.io)

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

- Trust score: 69/100 (medium)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.sunaivacore.io`: 69/100 (this document), [markdown](https://verifymcp.io/servers/io-sunaivacore-gate/mcp.md), [page](https://verifymcp.io/servers/io-sunaivacore-gate/mcp)
- npm · `@sunaiva/gate`: 58/100, [markdown](https://verifymcp.io/servers/io-sunaivacore-gate/sunaiva-gate.md), [page](https://verifymcp.io/servers/io-sunaivacore-gate/sunaiva-gate)

## Channel facts

- Endpoint: `https://mcp.sunaivacore.io`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.0.4`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 71/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS check failed: the endpoint is reachable over plaintext HTTP.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1003 tokens (~62/item across 16 items; 16 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability check failed: schema churn in the 8 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 0 additions.
- **Tool Coverage**: 96/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 87% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http io-sunaivacore-gate https://mcp.sunaivacore.io/
```

### Codex

```toml
[mcp_servers.io-sunaivacore-gate]
url = "https://mcp.sunaivacore.io/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-sunaivacore-gate": {
      "type": "remote",
      "url": "https://mcp.sunaivacore.io/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add io-sunaivacore-gate --url https://mcp.sunaivacore.io/ --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  io-sunaivacore-gate:
    url: "https://mcp.sunaivacore.io/"
```

### Other

```json
{
  "mcpServers": {
    "io-sunaivacore-gate": {
      "type": "http",
      "url": "https://mcp.sunaivacore.io/"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 16 to 19.

### 2026-07-31 (score 68, +3)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 65, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 0 to 3.

### 2026-07-27 (score 63, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 63)

First indexed and scored.

## MCP tools (16)

### `validate_action` (~68 tokens)

Check if a proposed action passes all active validation rules. Returns allowed/blocked with rule violations.

Input parameters:

- `action` (string, required): The action to validate
- `context` (string): Optional additional context, appended to `action` before rule matching — it can change which rules match and therefore the verdict.

### `log_bypass` (~48 tokens)

Record an intentional rule bypass with justification. Cannot bypass constitutional rules.

Input parameters:

- `reason` (string, required): Justification for the bypass
- `rule_id` (string, required): ID of the rule to bypass

### `get_rules` (~75 tokens)

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.

Input parameters:

- `category` (string): Filter by category
- `preset` (string): Filter by preset name

### `update_rules` (~89 tokens)

[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.

Input parameters:

- `disable` (array): Rule IDs to disable
- `enable` (array): Rule IDs to enable

### `get_audit_log` (~74 tokens)

View recent gate decisions — blocks, warnings, passes, and bypasses.

Input parameters:

- `limit` (number): Max entries to return (default 50)
- `rule_id` (string): Accepted for forward-compatibility but NOT applied server-side — the backend only honors limit/cursor. Filter the returned entries client-side.

### `ship_confidence_check` (~111 tokens)

[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.

Input parameters:

- `artifact_id` (string, required): The artifact being shipped (e.g. '@sunaiva/gate@1.1.0')
- `command_preview` (string): First 300 chars of the command that triggered the check (optional)
- `label` (string): Human-readable label of the publish action (optional)

### `audit_verify` (~44 tokens)

[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` (~70 tokens)

Set enforcement mode (shadow/advisory/enforce) for a specific rule. Requires API key (Pro+).

Input parameters:

- `agent_id` (string): Optional: scope override to a specific agent ID
- `mode` (string, required): Enforcement mode
- `rule_id` (string, required): Rule ID to configure

### `get_rule_modes` (~27 tokens)

List all enforcement-mode overrides configured for the authenticated customer. Requires an account (Dev+).

### `reset_rule_mode` (~46 tokens)

Remove a mode override for a rule, reverting it to its default enforcement mode. Requires API key (Pro+).

Input parameters:

- `rule_id` (string, required): Rule ID whose override to remove

### `add_custom_rule` (~134 tokens)

Create a custom detection rule in the backend. Requires API key (Pro+).

Input parameters:

- `description` (string, required): Rule description (required — the backend 400s on a missing/empty description)
- `detection_pattern` (string, required): Compiled regex detection pattern (required — the backend 400s on a missing/empty detection_pattern). There is no 'pattern' field: 'detection_pattern' is the only field name the evaluator reads; the b…
- `name` (string, required): Rule name
- `severity` (string, required): Severity on match
- `tier` (string): Optional tier restriction

### `update_custom_rule` (~97 tokens)

Update an existing custom rule. Requires API key (Pro+).

Input parameters:

- `description` (string)
- `detection_pattern` (string): There is no 'pattern' field — 'detection_pattern' is the only field name the evaluator reads; the backend explicitly rejects 'pattern'.
- `id` (string, required): Rule ID to update
- `name` (string)
- `severity` (string)
- `tier` (string)

### `delete_custom_rule` (~32 tokens)

Delete a custom rule. Requires API key (Pro+).

Input parameters:

- `id` (string, required): Rule ID to delete

### `list_custom_rules` (~25 tokens)

List all custom rules for the authenticated customer. Requires API key (Pro+).

### `list_presets` (~22 tokens)

List available rule preset bundles. Requires API key (Dev+).

### `apply_preset` (~41 tokens)

Apply a preset bundle, activating all its included rules. Requires API key (Pro+).

Input parameters:

- `preset_id` (string, required): ID of the preset to apply

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/io-sunaivacore-gate/mcp#diagnostics

## Score history

- 2026-08-03: 69
- 2026-08-02: 69
- 2026-08-01: 68
- 2026-07-31: 68
- 2026-07-30: 65
- 2026-07-29: 64
- 2026-07-28: 64
- 2026-07-27: 63
- 2026-07-26: 63

## Links

- Remote endpoint: https://mcp.sunaivacore.io/
- Website: https://sunaivacore.io/products/gate
- Changelog RSS feed: https://verifymcp.io/servers/io-sunaivacore-gate/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-sunaivacore-gate/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/io-sunaivacore-gate/mcp