# mcp-guard (npm · mcp-guard-scan)

Security scanner for MCP servers: tool poisoning, shadowing, permissions, secrets, transport.

- Trust score: 81/100 (high trust)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `mcp-guard-scan`: 81/100 (this document), [markdown](https://verifymcp.io/servers/diegoperezg7-mcp-guard-scan/mcp-guard-scan.md), [page](https://verifymcp.io/servers/diegoperezg7-mcp-guard-scan/mcp-guard-scan)

## Channel facts

- Registry: `npm`
- Package: `mcp-guard-scan`
- Version: `1.1.1`
- 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 2026-11-05.

- **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.
  - 34 of 106 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to diegoperezg7/mcp-guard-scan).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 516 tokens (~129/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 3/100
  - Stability observed for 1 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.
  - Structured output schemas are declared (75% of tools); any adoption earns full credit.
- **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 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 mcp-guard server?

mcp-guard runs locally as an npm package, launched with npx -y mcp-guard-scan. 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 diegoperezg7-mcp-guard-scan -- npx -y mcp-guard-scan
```

### Cursor

```json
{
  "mcpServers": {
    "diegoperezg7-mcp-guard-scan": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-guard-scan"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "diegoperezg7-mcp-guard-scan": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-guard-scan"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add diegoperezg7-mcp-guard-scan -- npx -y mcp-guard-scan
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "diegoperezg7-mcp-guard-scan": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "mcp-guard-scan"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add diegoperezg7-mcp-guard-scan --command npx --arg -y --arg mcp-guard-scan
```

### Hermes

```yaml
mcp_servers:
  diegoperezg7-mcp-guard-scan:
    command: "npx"
    args: ["-y", "mcp-guard-scan"]
```

### Netclaw

```json
{
  "McpServers": {
    "diegoperezg7-mcp-guard-scan": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "mcp-guard-scan"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add diegoperezg7-mcp-guard-scan -t stdio -c npx -a -y mcp-guard-scan
```

### Other

```json
{
  "mcpServers": {
    "diegoperezg7-mcp-guard-scan": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-guard-scan"
      ]
    }
  }
}
```

## 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.

### 2026-11-05 (score 81, +11)

- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → 0.86

### 2026-11-04 (score 70)

First indexed and scored.

## MCP tools (4)

### `scan_tools_export` (~129 tokens)

Scan a tools/list export

Run every static mcp-guard rule over a tools/list result you already have: { "tools": [...] }, a bare array of tools, or { "servers": [{ "name", "tools" }] } to also check shadowing between servers. Nothing is started or contacted. Returns a Markdown report and the findings.

Input parameters:

- `export` (required): The tools/list result, or several servers under a servers key.
- `fail_on` (string): passed is false when a finding is at or above this severity.
- `name` (string): Server name used in the report when the export has none.

Output parameters:

- `findings` (array)
- `passed` (boolean): False when a finding reaches fail_on.
- `servers` (array)
- `summary` (object): Findings per severity.

### `scan_server` (~137 tokens)

Scan a live MCP server

Connect to a Streamable HTTP MCP endpoint, list its tools, resources and prompts, run every static rule and check the transport (TLS, auth, CORS, session handling). The scanned server's tools are never called. Only public https endpoints; local and private addresses are refused unless the server runs with MCP_GUARD_ALLOW_PRIVATE_NETWORK=1.

Input parameters:

- `fail_on` (string): passed is false when a finding is at or above this severity.
- `headers` (object): HTTP headers for the endpoint, e.g. Authorization.
- `url` (string, required): Streamable HTTP endpoint, e.g. https://example.com/mcp.

Output parameters:

- `findings` (array)
- `passed` (boolean): False when a finding reaches fail_on.
- `servers` (array)
- `summary` (object): Findings per severity.

### `list_rules` (~33 tokens)

List mcp-guard rules

List every MCPG rule with its category, default severity and whether it is static or needs the CLI's --probe mode.

Output parameters:

- `rules` (array)

### `explain_rule` (~55 tokens)

Explain an mcp-guard rule

Explain one rule, e.g. MCPG-002: what it detects, a bad and a good example, how to fix it and references.

Input parameters:

- `id` (string, required): Rule id, e.g. MCPG-002.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/diegoperezg7-mcp-guard-scan/mcp-guard-scan#diagnostics

## Score history

- 2026-11-05: 81
- 2026-11-04: 70

## Common questions

### What is the mcp-guard server?

mcp-guard is listed in the public MCP registry as io.github.diegoperezg7/mcp-guard-scan. Security scanner for MCP servers: tool poisoning, shadowing, permissions, secrets, transport. This page covers its npm package (mcp-guard-scan).

### Is the mcp-guard server safe to use?

mcp-guard scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 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 mcp-guard server expose?

mcp-guard exposes 4 tools: scan_tools_export, scan_server, list_rules, explain_rule. Their descriptions and schemas cost roughly 354 tokens of context every time the server is loaded.

### Is the mcp-guard server still maintained?

mcp-guard is still listed as active in the MCP registry. We last reached this channel on 5 November 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 mcp-guard server under?

mcp-guard declares the Apache-2.0 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/mcp-guard-scan
- Socket report: https://socket.dev/npm/package/mcp-guard-scan
- Repository: https://github.com/diegoperezg7/mcp-guard-scan
- Changelog RSS feed: https://verifymcp.io/servers/diegoperezg7-mcp-guard-scan/mcp-guard-scan.xml
- Changelog JSON feed: https://verifymcp.io/servers/diegoperezg7-mcp-guard-scan/mcp-guard-scan.json
- HTML version of this page: https://verifymcp.io/servers/diegoperezg7-mcp-guard-scan/mcp-guard-scan