# Koma Gate MCP (npm · koma-gate-mcp)

Classifies prompt injection, jailbreaks, and out-of-scope user input before agents act on it.

- Trust score: 70/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-17

## Components

- npm · `koma-gate-mcp`: 70/100 (this document), [markdown](https://verifymcp.io/servers/swnotmetal-koma-gate-mcp/koma-gate-mcp.md), [page](https://verifymcp.io/servers/swnotmetal-koma-gate-mcp/koma-gate-mcp)

## Channel facts

- Registry: `npm`
- Package: `koma-gate-mcp`
- Version: `0.1.1`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-17.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 0 of 4 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 1 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 93 tokens (~93/item across 1 items; 1 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add swnotmetal-koma-gate-mcp -- npx -y koma-gate-mcp
```

### Codex

```bash
codex mcp add swnotmetal-koma-gate-mcp -- npx -y koma-gate-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "swnotmetal-koma-gate-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "koma-gate-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add swnotmetal-koma-gate-mcp --command npx --arg -y --arg koma-gate-mcp
```

### Hermes

```yaml
mcp_servers:
  swnotmetal-koma-gate-mcp:
    command: "npx"
    args: ["-y", "koma-gate-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "swnotmetal-koma-gate-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "koma-gate-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-08-15 (score 70)

First indexed and scored.

## MCP tools (1)

### `classify_input` (~93 tokens)

Check whether user input is safe and in-scope before an AI system processes it. Detects prompt injection, jailbreak attempts, instruction overrides, and off-topic requests. Use this to validate untrusted user text before passing it to an LLM or executing a tool.

Input parameters:

- `preset` (string): Which guard domain to use. Default: general knowledge assistant
- `text` (string, required): The untrusted user input to classify

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/swnotmetal-koma-gate-mcp/koma-gate-mcp#diagnostics

## Score history

- 2026-08-17: 70
- 2026-08-16: 70
- 2026-08-15: 70

## Links

- npm package: https://www.npmjs.com/package/koma-gate-mcp
- Socket report: https://socket.dev/npm/package/koma-gate-mcp
- Repository: https://github.com/swnotmetal/Project-Koma
- Website: https://github.com/swnotmetal/Project-Koma/blob/main/packages/koma-gate-mcp/README.md
- Changelog RSS feed: https://verifymcp.io/servers/swnotmetal-koma-gate-mcp/koma-gate-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/swnotmetal-koma-gate-mcp/koma-gate-mcp.json
- HTML version of this page: https://verifymcp.io/servers/swnotmetal-koma-gate-mcp/koma-gate-mcp