secretscan
secretscan-mcp-server
一个 MCP 服务器,用于扫描 diff、文件内容或粘贴的片段,以发现意外提交的机密——这样任何兼容 MCP 的代理都可以在提交、打开 PR 或粘贴日志摘录之前自我检查其更改。完全本地化:无需 API 密钥,无需网络调用,除了 MCP SDK 和 Zod 之外没有其他依赖。
为什么
泄露的凭据是导致账户和基础设施受损的最常见现实原因之一,也是在大规模 diff 中最容易犯的错误之一——调试用的 console.log 中带有真实的 API 密钥、意外提交的配置文件、在寻求帮助时粘贴到聊天中的 .env。即将提交、推送或分享文本的代理,如果有一种廉价的方式来检查,就完全有能力在发生之前捕获这一点。
Related MCP server: opzyai
工具
scan_for_secrets
根据一组固定的提供商格式签名以及一个通用的、基于熵的启发式规则扫描文本:
检测器 | 捕获内容 |
| AWS 访问密钥 ID( |
| AWS 秘密密钥,当上下文有标签时 |
| GitHub PAT( |
| Slack 令牌( |
| Stripe 秘密/可发布密钥 |
| Google API 密钥( |
| npm 发布令牌( |
| PEM 私钥块 |
| JSON Web 令牌 |
| 分配给听起来像机密的变量名( |
发现结果始终经过脱敏——AKIAIOSFODNN7EXAMPLE 会报告为 AKIA************MPLE (20 chars),绝不会完整显示。因此,该工具自身的输出可以安全地记录或显示,而不会进一步传播它发现的内容。
这是固定模式 + 启发式扫描,并非穷尽式。干净的结果意味着“没有已知模式匹配”,而不是“绝对安全”——应用内输出会明确说明这一点。
安装和配置
git clone https://github.com/wedo911/secretscan-mcp-server.git
cd secretscan-mcp-server
npm install
npm run build将其添加到您的 MCP 客户端配置中(例如 claude_desktop_config.json,或 Claude Code 项目的 .mcp.json):
{
"mcpServers": {
"secretscan": {
"command": "node",
"args": ["/absolute/path/to/secretscan-mcp-server/dist/index.js"]
}
}
}运行测试
npm run build
node --test tests/entropy.test.mjs tests/detectors.test.mjs24 个测试,包括针对每个命名检测器的测试、通用检测器的占位符和低熵过滤行为,以及一个显式检查,确保脱敏输出永远不会包含完整的秘密值。
无需客户端即可试用
npx @modelcontextprotocol/inspector --cli node dist/index.js \
--method tools/call --tool-name scan_for_secrets \
--tool-arg text='aws_access_key_id = AKIAIOSFODNN7EXAMPLE'(这是 AWS 官方公开文档中的示例密钥 —— 不是真实凭据。)
许可证
MIT — 参见 LICENSE。
Maintenance
Tools
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables scanning diffs or code blobs for leaked secrets, returning a verdict with severity and masked findings, all processed locally with no data sent externally.1MIT
- AlicenseNot gradedqualityBmaintenanceLocal-first security check for AI coding agents — finds hardcoded secrets, exposed .env files, git-history leaks and vulnerable dependencies (OSV), entirely on your machine. Ask your agent "is this safe to ship?" and get a Launch Readiness score with a fix for every finding.MIT
- AlicenseNot gradedqualityAmaintenanceScans text and files for common secrets (AWS, GitHub, etc.) and redacts them to prevent credential leakage in AI-assisted development. Runs entirely locally with no telemetry.MIT
- AlicenseAqualityDmaintenanceScans projects for hardcoded secrets, unprotected .env files, and console.log leaks to prevent credential exposure.544MIT
Related MCP Connectors
Risk-scan a diff, flag AI-generated-code tells, find secrets. 5 of 7 tools need no account.
Generate SBOMs, scan vulnerabilities, and analyze dependencies from local projects or Git repos.
Screens public GitHub repos and PRs to generate risk maps, findings, and merge-readiness signals.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/wedo911/secretscan-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server