Skip to main content
Glama
BARMPlus

locklens

by BARMPlus
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Hybrid

locklens

locklens 是一个基于 audit-ci 的 lockfile 审计工具，支持三种运行模式：

  • CLI / npx

  • MCP Server（stdio）

  • Skill

它可以审计本地项目目录或远程 Git 仓库，并支持 npm、yarn、pnpm 的 lockfile。

特性

  • 支持本地项目目录与远程 Git 仓库审计

  • 支持公开仓库与私有仓库审计

  • 支持 package-lock.json、yarn.lock、pnpm-lock.yaml

  • 仅基于仓库中已存在的 lockFile 进行审计，保证结果与真实依赖状态一致

  • 支持中文、英文文本报告

  • 支持显式切换为 JSON 输出

Related MCP server: audit-mcp-cli

环境要求

  • Node >=18

  • (Optional) Yarn ^1.12.3 || Yarn >=2.4.0 && <4.0.0

  • (Optional) PNPM >=4.3.0

  • (Optional) Bun

结果示例

可以直接查看仓库内的示例输出：

安装与环境

本地仓库、线上仓库审计：

# 本地相对目录审计
npx -y locklens --source ./
# 本地绝对目录审计
npx -y locklens --source /path/to/project 
# Github 远程仓库审计
npx -y locklens --source https://github.com/BARMPlus/micro-app > audit.md
# Gitlab 远程仓库审计
npx -y locklens --output-format json --source https://gitlab.com/gitlab-org/gitlab-vscode-extension.git > audit.json

私有仓库审计：

# 对于 GitHub、GitLab、Gitee 的 HTTPS 地址，locklens 会先尝试通过 ssh -T 判断本机 SSH Key 是否可用于该 Git 服务器；
# 如果可用，会自动切换为 SSH 方式执行。其他私有 Git 服务器仍建议直接依赖本机已有权限的 SSH Key。
npx -y locklens --source https://git.company.local/group/repo.git
# 适合 CI 场景，仅支持 私有部署的 GitLab 服务器应用审计，设置 Personal access tokens 权限访问该仓库
LOCKLENS_GITLAB_PRIVATE_TOKEN=your-token npx -y locklens --source https://git.company.local/group/repo.git

CLI 使用方法

常见示例

输出英文文本报告：

npx -y locklens --source /path/to/project --output-format-language en

输出 JSON：

npx -y locklens --source /path/to/project --output-format json

指定阈值为高危：

npx -y locklens --source /path/to/project --threshold high

跳过 devDependencies：

npx -y locklens --source /path/to/project --skip-dev

CLI 参数

参数

说明

--source <value>

必填。本地目录路径或远程 Git 仓库地址

--threshold <value>

漏洞过滤阈值，可选：low、moderate、high、critical，默认：low

--registry <url>

自定义 npm registry，默认：https://registry.npmjs.org/

--skip-dev

跳过 dev dependencies

--retry-count <number>

审计执行重试次数

--output-format <value>

输出格式，可选：json、text，默认：text

--output-format-language <value>

文本报告语言，可选：zh、en，默认：zh

--help / -h

显示帮助

--version / -v

显示版本号

MCP 使用方法

locklens 支持通过 stdio 方式作为 MCP Server 接入，通过将以下配置添加到mcp服务器配置中。

Windows 平台：

{
  "mcpServers": {
    "locklens": {
      "command": "cmd",
      "args": ["/c", "npx", "--yes", "locklens"]
    }
  }
}

其他平台：

{
  "mcpServers": {
    "locklens": {
      "command": "npx",
      "args": ["--yes", "locklens"]
    }
  }
}

Tools

package_audit

审计指定项目目录或远程 Git 仓库的 lockfile，并返回统一格式的漏洞结果。

参数：

  • source

    • 必填。本地目录绝对路径，或远程 Git 仓库地址

  • threshold

    • 漏洞过滤阈值，可选：low、moderate、high、critical；默认：low

  • registry

    • 自定义 npm registry 地址；默认：https://registry.npmjs.org/

  • skipDev

    • 是否跳过 dev dependencies

  • retryCount

    • 审计执行重试次数

  • outputFormat

    • 输出格式，可选：text、json；默认：text

  • outputFormatLanguage

    • 文本报告语言，可选：zh、en；默认：zh

Skill

如果你的客户端支持 Skill，也可以直接使用 dependency-audit，不需要先接入 MCP。

当前仓库内的 Skill 目录位于：

dependency-audit/

默认会带上 --skip-dev，优先只带出线上风险；如果你希望带出开发和线上所有依赖风险，可以明确说明取消 --skip-dev。

示例：

1. 使用 dependency-audit 审计当前项目的依赖问题
2. https://github.com/BARMPlus/micro-app 审计这个项目的依赖，告知我开发和线上所有的依赖问题
3. 输出 https://github.com/BARMPlus/micro-app 这个项目严重的依赖问题

License

Copyright (c) 2026 chenglin

locklens is released under the MIT License

Available Tools

1 tool
package_auditB

Audit a local project or remote Git repository lockfile and return normalized package vulnerability results.

ParametersJSON Schema
NameRequiredDescriptionDefault
sourceYesRequired. Local directory path or remote Git repository URL
skipDevNoWhether to skip dev dependencies during audit
registryNoCustom registry URL used during audit execution. Defaults to https://registry.npmjs.org/.
thresholdNoMinimum threshold that controls the returned advisories list. Defaults to low.
retryCountNoRetry count passed to the audit executor
outputFormatNoResponse format. Defaults to text.
outputFormatLanguageNoText report language. Defaults to zh.

TDQS

B3.2/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It mentions 'audit' but does not state whether the tool modifies any files, requires authentication, or has side effects. The nature of the audit (read-only) is implied but not explicit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, well-formed sentence that conveys the core functionality without extraneous words. It is concise and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does not detail the structure of 'normalized package vulnerability results'. Also, the tool has several options (outputFormat, language, threshold) that affect the output, but the description does not summarize these nuances.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage with descriptions for all 7 parameters. The description adds no extra meaning or context beyond what is in the schema, so baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('audit'), the resource ('lockfile from local project or remote Git repository'), and the output ('normalized package vulnerability results'). It is specific and leaves no ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs alternatives (no siblings provided). The description does not mention any preconditions, such as requiring a lockfile or network access.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 1 tool updatev1.1.8
    • First observedpackage_audit
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.4/5.0
Disambiguation5/5

With only one tool, there is no possibility of ambiguity; the tool's purpose is clearly defined.

Naming Consistency5/5

The single tool name uses a consistent verb_noun pattern (package_audit), so naming is perfectly consistent.

Tool Count3/5

Having a single tool for lockfile auditing is borderline; it could be sufficient for a narrow scope but feels thin for a dedicated server.

Completeness2/5

The server offers only an audit operation, lacking obvious supporting tools such as listing supported formats or managing advisories, which may hinder agent workflows.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/BARMPlus/locklens'

If you have feedback or need assistance with the MCP directory API, please join our Discord server