Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, email [email protected] and we’ll put it right.

Sunaiva Gate — Agent Rule Enforcement

NPM · @SUNAIVA/GATE · 2 COMPONENTS · SCANNED AUG 3

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

+40 this week 58 Trust /100
Trust breakdown (6 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →

Supply Chain Security87
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency6
Schema Quality & AI Usability66
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 819 tokens (~51/item across 16 items; 16 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management23
  • Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage94
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 81% of tool parameters carry a description.Partial
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · @sunaiva/gate

# add to Claude Code
claude mcp add io-sunaivacore-gate -- npx -y @sunaiva/gate
# add to Codex CLI
codex mcp add io-sunaivacore-gate -- npx -y @sunaiva/gate
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-sunaivacore-gate": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@sunaiva/gate"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add io-sunaivacore-gate --command npx --arg -y --arg @sunaiva/gate
# ~/.hermes/config.yaml
mcp_servers:
  io-sunaivacore-gate:
    command: "npx"
    args: ["-y", "@sunaiva/gate"]
// mcp.json
{
  "mcpServers": {
    "io-sunaivacore-gate": {
      "command": "npx",
      "args": [
        "-y",
        "@sunaiva/gate"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 2 Aug 26 +38
    • Provenance: unverified → fail security
    • Install scripts: unverified → pass security
    • Known CVEs: unverified → partial security
    • Malware scan: unverified → pass security
    • Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. security
    • License: unverified → fail functional
    • Capabilities: pass → unverified functional
    • Maintenance: unverified → pass functional
    • Stability: unverified → 0.20 functional
    • Dependency health: unverified → partial functional
    • Schema quality: unverified → good functional
    • Licence: BUSL-1.1 functional
  • 1 Aug 26 +5
    • Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
    • MCP protocol: unverified → pass functional
  • 31 Jul 26 −24
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 28 Jul 26 +21
    • Tool coverage: unverified → 100 functional
    • First check of Schema quality: pass functional
    • First check of Schema quality: fail functional
    • First check of Tool coverage: 81 functional
    • First check of Schema quality: unverified functional
  • 27 Jul 26 18

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 3 Aug 2026 · Analysed npm/@sunaiva/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 95 packages

95 packages in the resolved dependency tree · 95 deprecated · 29 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 16 exposed · ~819 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.

Tool Tokens
add_custom_rule ~89

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

NameTypeReqDescription
descriptionstringOptional description
detection_patternstringCompiled regex detection pattern
namestringyesRule name
patternstringDetection pattern (regex or keyword)
severitystringyesSeverity on match
tierstringOptional tier restriction

No output schema declared.

No examples provided.

apply_preset ~41

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

NameTypeReqDescription
preset_idstringyesID of the preset to apply

No output schema declared.

No examples provided.

audit_verify ~44

Verify the forward-linked cryptographic hash chain of the Gate audit log (Patent Claim 19). Reports chain integrity, tamper evidence, and ed25519 signature validity per entry.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

delete_custom_rule ~32

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

NameTypeReqDescription
idstringyesRule ID to delete

No output schema declared.

No examples provided.

get_audit_log ~52

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

NameTypeReqDescription
limitnumberMax entries to return (default 50)
rule_idstringFilter by rule ID

No output schema declared.

No examples provided.

get_rule_modes ~27

List all enforcement-mode overrides configured for the authenticated customer. Requires API key (Pro+).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_rules ~41

List active validation rules, optionally filtered by category or preset.

NameTypeReqDescription
categorystringFilter by category
presetstringFilter by preset name

No output schema declared.

No examples provided.

list_custom_rules ~25

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

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_presets ~22

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

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

log_bypass ~48

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

NameTypeReqDescription
reasonstringyesJustification for the bypass
rule_idstringyesID of the rule to bypass

No output schema declared.

No examples provided.

reset_rule_mode ~46

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

NameTypeReqDescription
rule_idstringyesRule ID whose override to remove

No output schema declared.

No examples provided.

set_rule_mode ~70

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

NameTypeReqDescription
agent_idstringOptional: scope override to a specific agent ID
modestringyesEnforcement mode
rule_idstringyesRule ID to configure

No output schema declared.

No examples provided.

ship_confidence_check ~116

Ship Confidence Gate (Rule 42). Verifies dual-tier authorization for publish-class actions: HMAC-signed Verdict (paid) OR approval token (free). Returns allow/block with self-stamped evidence.

NameTypeReqDescription
artifact_idstringyesThe artifact being shipped (e.g. '@sunaiva/[email protected]')
command_previewstringFirst 300 chars of the command that triggered the check (optional)
labelstringHuman-readable label of the publish action (optional)

No output schema declared.

No examples provided.

update_custom_rule ~76

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

NameTypeReqDescription
descriptionstring
detection_patternstring
idstringyesRule ID to update
namestring
patternstring
severitystring
tierstring

No output schema declared.

No examples provided.

update_rules ~42

Enable or disable validation rules. Constitutional rules cannot be disabled.

NameTypeReqDescription
disablearrayRule IDs to disable
enablearrayRule IDs to enable

No output schema declared.

No examples provided.

validate_action ~48

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

NameTypeReqDescription
actionstringyesThe action to validate
contextstringOptional additional context

No output schema declared.

No examples provided.