# io.github.4hmetuyar/prompt-leak-scanner (npm · @guardbee/mcp-prompt-leak-scanner)

Catches leaked credentials and PII in outbound LLM prompts

- Trust score: 90/100 (high trust)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- npm · `@guardbee/mcp-prompt-leak-scanner`: 90/100 (this document), [markdown](https://verifymcp.io/servers/4hmetuyar-prompt-leak-scanner/guardbee-mcp-prompt-leak-scanner.md), [page](https://verifymcp.io/servers/4hmetuyar-prompt-leak-scanner/guardbee-mcp-prompt-leak-scanner)

## Channel facts

- Registry: `npm`
- Package: `@guardbee/mcp-prompt-leak-scanner`
- Version: `0.1.6`
- 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 2026-10-17.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 94 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to GuardBee/guardbee-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 1 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 80/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 355 tokens (~71/item across 5 items; 5 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 63/100
  - Stability observed for 19 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the io.github.4hmetuyar/prompt-leak-scanner MCP server?

io.github.4hmetuyar/prompt-leak-scanner runs locally as an npm package, launched with npx -y @guardbee/mcp-prompt-leak-scanner. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add 4hmetuyar-prompt-leak-scanner -- npx -y @guardbee/mcp-prompt-leak-scanner
```

### Cursor

```json
{
  "mcpServers": {
    "4hmetuyar-prompt-leak-scanner": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-prompt-leak-scanner"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "4hmetuyar-prompt-leak-scanner": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-prompt-leak-scanner"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add 4hmetuyar-prompt-leak-scanner -- npx -y @guardbee/mcp-prompt-leak-scanner
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "4hmetuyar-prompt-leak-scanner": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@guardbee/mcp-prompt-leak-scanner"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add 4hmetuyar-prompt-leak-scanner --command npx --arg -y --arg @guardbee/mcp-prompt-leak-scanner
```

### Hermes

```yaml
mcp_servers:
  4hmetuyar-prompt-leak-scanner:
    command: "npx"
    args: ["-y", "@guardbee/mcp-prompt-leak-scanner"]
```

### Netclaw

```json
{
  "McpServers": {
    "4hmetuyar-prompt-leak-scanner": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@guardbee/mcp-prompt-leak-scanner"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add 4hmetuyar-prompt-leak-scanner -t stdio -c npx -a -y @guardbee/mcp-prompt-leak-scanner
```

### Other

```json
{
  "mcpServers": {
    "4hmetuyar-prompt-leak-scanner": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-prompt-leak-scanner"
      ]
    }
  }
}
```

## 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.

### 2026-10-16 (score 90, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 89, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-12 (score 88, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-11 (score 87, +3)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 43. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-04 (score 84, 0)

- [security improvement] Known CVEs: partial → pass
- [functional] Dependency health: partial → 0.85

### 2026-10-03 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-02 (score 83, +11)

- [security regression] Known CVEs: pass → partial
- [security improvement] Provenance: fail → pass
- [security] The attested source repository moved: GuardBee/guardbee-mcp
- [functional] Dependency health: 0.85 → partial
- [functional] Package version: 0.1.5 → 0.1.6

### 2026-10-01 (score 72, +11)

- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → 0.85

## MCP tools (5)

### `scan_text` (~95 tokens)

Scan a raw text string (e.g. a prompt you're about to send to an LLM) for leaked credentials (API keys, private keys, JWTs) and PII (TC Kimlik No, credit card, IBAN, email, phone) — checksum-validated where applicable to keep false positives low.

Input parameters:

- `content` (string, required): The text to scan
- `label` (string): Optional label shown in findings

### `scan_messages` (~87 tokens)

Scan an OpenAI/Anthropic-style chat request body (a JSON object with a `messages` array and/or a `system` field) for leaked credentials and PII in every message's text content, before it would be sent to the model.

Input parameters:

- `body` (object, required): The chat request body object, e.g. { model, system, messages: [{ role, content }] }

### `scan_file` (~52 tokens)

Scan a single file — plain text, or a JSON chat-request-body fixture (auto-detected) — for leaked credentials and PII

Input parameters:

- `path` (string, required): Absolute or relative path to the file to scan

### `scan_directory` (~98 tokens)

Recursively scan a directory of prompt logs or request-body fixtures for leaked credentials and PII

Input parameters:

- `exclude` (array): Skip files/dirs whose path contains one of these strings
- `include` (array): Only scan files whose path contains one of these strings
- `maxFiles` (integer): Maximum number of files to scan (default: 5000)
- `path` (string, required): Absolute or relative path to the directory to scan

### `list_patterns` (~23 tokens)

List every credential/PII pattern this scanner detects, grouped by category

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/4hmetuyar-prompt-leak-scanner/guardbee-mcp-prompt-leak-scanner#diagnostics

## Score history

- 2026-10-17: 90
- 2026-10-16: 90
- 2026-10-15: 89
- 2026-10-14: 89
- 2026-10-13: 88
- 2026-10-12: 88
- 2026-10-11: 87
- 2026-10-05: 84
- 2026-10-04: 84
- 2026-10-03: 84
- 2026-10-02: 83
- 2026-10-01: 72
- 2026-09-30: 61
- 2026-09-29: 71
- 2026-09-28: 56

## Common questions

### What is the io.github.4hmetuyar/prompt-leak-scanner MCP server?

io.github.4hmetuyar/prompt-leak-scanner is an MCP server listed in the public MCP registry as io.github.4hmetuyar/prompt-leak-scanner. Catches leaked credentials and PII in outbound LLM prompts. This page covers its npm package (@guardbee/mcp-prompt-leak-scanner).

### Is the io.github.4hmetuyar/prompt-leak-scanner MCP server safe to use?

io.github.4hmetuyar/prompt-leak-scanner scores 90 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 17 October 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.4hmetuyar/prompt-leak-scanner MCP server expose?

io.github.4hmetuyar/prompt-leak-scanner exposes 5 tools: scan_text, scan_messages, scan_file, scan_directory, list_patterns. Their descriptions and schemas cost roughly 355 tokens of context every time the server is loaded.

### Is the io.github.4hmetuyar/prompt-leak-scanner MCP server still maintained?

io.github.4hmetuyar/prompt-leak-scanner is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.github.4hmetuyar/prompt-leak-scanner MCP server under?

io.github.4hmetuyar/prompt-leak-scanner declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@guardbee/mcp-prompt-leak-scanner
- Socket report: https://socket.dev/npm/package/@guardbee/mcp-prompt-leak-scanner
- Repository: https://github.com/GuardBee/guardbee-mcp
- Changelog RSS feed: https://verifymcp.io/servers/4hmetuyar-prompt-leak-scanner/guardbee-mcp-prompt-leak-scanner.xml
- Changelog JSON feed: https://verifymcp.io/servers/4hmetuyar-prompt-leak-scanner/guardbee-mcp-prompt-leak-scanner.json
- HTML version of this page: https://verifymcp.io/servers/4hmetuyar-prompt-leak-scanner/guardbee-mcp-prompt-leak-scanner