# io.github.GuardBee/tool-poisoning-scanner (npm · @guardbee/mcp-tool-poisoning-scanner)

Scans MCP tool definitions for hidden instructions and confused-deputy sinks

- Trust score: 87/100 (high trust)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-25

## Components

- npm · `@guardbee/mcp-tool-poisoning-scanner`: 87/100 (this document), [markdown](https://verifymcp.io/servers/guardbee-tool-poisoning-scanner/guardbee-mcp-tool-poisoning-scanner.md), [page](https://verifymcp.io/servers/guardbee-tool-poisoning-scanner/guardbee-mcp-tool-poisoning-scanner)

## Channel facts

- Registry: `npm`
- Package: `@guardbee/mcp-tool-poisoning-scanner`
- Version: `0.3.2`
- 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 2026-10-25.

- **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.
  - 30 of 94 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - 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 2 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 82/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 266 tokens (~66/item across 4 items; 4 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 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 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 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.GuardBee/tool-poisoning-scanner MCP server?

io.github.GuardBee/tool-poisoning-scanner runs locally as an npm package, launched with npx -y @guardbee/mcp-tool-poisoning-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 guardbee-tool-poisoning-scanner -- npx -y @guardbee/mcp-tool-poisoning-scanner
```

### Cursor

```json
{
  "mcpServers": {
    "guardbee-tool-poisoning-scanner": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-tool-poisoning-scanner"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "guardbee-tool-poisoning-scanner": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-tool-poisoning-scanner"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add guardbee-tool-poisoning-scanner -- npx -y @guardbee/mcp-tool-poisoning-scanner
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add guardbee-tool-poisoning-scanner --command npx --arg -y --arg @guardbee/mcp-tool-poisoning-scanner
```

### Hermes

```yaml
mcp_servers:
  guardbee-tool-poisoning-scanner:
    command: "npx"
    args: ["-y", "@guardbee/mcp-tool-poisoning-scanner"]
```

### Netclaw

```json
{
  "McpServers": {
    "guardbee-tool-poisoning-scanner": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@guardbee/mcp-tool-poisoning-scanner"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add guardbee-tool-poisoning-scanner -t stdio -c npx -a -y @guardbee/mcp-tool-poisoning-scanner
```

### Other

```json
{
  "mcpServers": {
    "guardbee-tool-poisoning-scanner": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-tool-poisoning-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.

### 2026-10-25 (score 87, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 86, +47)

- [security improvement] Injection markers: unverified → pass
- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Dependency health: unverified → 0.86
- [functional improvement] Stability: unverified → 0.27
- [functional improvement] MCP protocol: unverified → pass

### 2026-10-22 (score 39, −45)

- [security regression] Known CVEs: partial → unverified
- [security regression] Stability: 0.20 → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Dependency health: partial → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional improvement] Security disclosure: fail → pass
- [functional] Package version: 0.2.18 → 0.3.2
- [functional] Package version: 0.2.18 → 0.3.1
- [functional] Package version: 0.2.18 → 0.3.0

### 2026-10-21 (score 84, +11)

- [security improvement] Known CVEs: unverified → partial
- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Dependency health: unverified → 0.85
- [functional] Package version: 0.2.17 → 0.2.18

### 2026-10-20 (score 73, −10)

- [security regression] Known CVEs: pass → unverified
- [functional regression] Dependency health: 0.85 → unverified
- [functional] Package version: 0.2.15 → 0.2.17
- [functional] Package version: 0.2.15 → 0.2.16

### 2026-10-19 (score 83, 0)

- [functional] Package version: 0.2.14 → 0.2.15

### 2026-10-17 (score 83, +34)

- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.07
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 100

### 2026-10-16 (score 49, +11)

- [security improvement] Injection markers: unverified → pass
- [security improvement] Known CVEs: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Dependency health: unverified → 0.85
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 100
- [functional] Package version: 0.2.13 → 0.2.14

## MCP tools (4)

### `scan_text` (~97 tokens)

Scan MCP server source for tool poisoning (hidden instructions embedded in a tool's `description` string, read by the calling LLM as trusted context) and confused-deputy tools (a name/description promising read-only behavior while the handler has a shell/eval/file-write/env-dump sink).

Input parameters:

- `content` (string, required): The source code to scan
- `label` (string): Optional label shown in findings (e.g. filename)

### `scan_file` (~44 tokens)

Scan a single file for tool-poisoning and confused-deputy patterns in MCP tool registrations

Input parameters:

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

### `scan_directory` (~100 tokens)

Recursively scan a directory of MCP server source for tool-poisoning and confused-deputy patterns

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` (~25 tokens)

List every description-injection phrase and confused-deputy sink rule this scanner detects

## Diagnostics

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

## Score history

- 2026-10-25: 87
- 2026-10-24: 86
- 2026-10-23: 86
- 2026-10-22: 39
- 2026-10-21: 84
- 2026-10-20: 73
- 2026-10-19: 83
- 2026-10-18: 83
- 2026-10-17: 83
- 2026-10-16: 49
- 2026-10-15: 38
- 2026-10-14: 49
- 2026-10-13: 49
- 2026-10-12: 49
- 2026-10-11: 49

## Common questions

### What is the io.github.GuardBee/tool-poisoning-scanner MCP server?

io.github.GuardBee/tool-poisoning-scanner is an MCP server listed in the public MCP registry as io.github.GuardBee/tool-poisoning-scanner. Scans MCP tool definitions for hidden instructions and confused-deputy sinks. This page covers its npm package (@guardbee/mcp-tool-poisoning-scanner).

### Is the io.github.GuardBee/tool-poisoning-scanner MCP server safe to use?

io.github.GuardBee/tool-poisoning-scanner scores 87 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 25 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.GuardBee/tool-poisoning-scanner MCP server expose?

io.github.GuardBee/tool-poisoning-scanner exposes 4 tools: scan_text, scan_file, scan_directory, list_patterns. Their descriptions and schemas cost roughly 266 tokens of context every time the server is loaded.

### Is the io.github.GuardBee/tool-poisoning-scanner MCP server still maintained?

io.github.GuardBee/tool-poisoning-scanner is still listed as active in the MCP registry. We last reached this channel on 25 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.GuardBee/tool-poisoning-scanner MCP server under?

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