mcp-security-scanner - A security vulnerability scanner built with MCP pl

项目说明

MCP Security Scanner

MCP server for scanning Ja/TypeScript projects for security . Detects dangerous code patterns, insecure file permissions, risky dependencies, hardcoded credentials, and more.

Tools

| Tool | Description |
|------|-------------|
| securityScan | Full recursive scan of a directory for all types |
| scanFile | Scan a single JS/TS file for dangerous code patterns |
| auditDependencies | Check package.json for risky or unpinned dependencies |
| checkPermissions | Detect world-writable or overly permissi |
| memoryStatus | Report scanner process memory usage |

Detected Types

Quick Start

Install

Run locally (stdio)

Run o (Streamable HTTP)

Transport Notes

En

| | Default | Description |
|----------|---------|-------------|
| MCP_TRANSPORT | stdio | Transport mode: stdio or http |
| MCP_SER | 0.0.0.0 | HTTP bind address |
| MCP_SER | 8100 | HTTP port |
| MCP_ALLOWED_ORIGINS | (none) | Comma-separated allowed Origins; returns 403 for others |

Docker

Usage Examples

Full project scan

Scan single file

Audit dependencies

---

Appendix: MCP in Practice (Code Execution, Tool Scale, and Safety)

Last updated: 2026-03-23

Why This Appendix Exists

Model Context Protocol (MCP) is still one of the most useful interoperability layers for tools and agents. The tradeoff is that large MCP servers can expose many tools, and nai can flood context windows with schemas, tool chatter, and irrelevant call traces.

In practice, "more tools" is not always "better outcomes." Tool surface area must be paired with execution patterns that keep token use bounded and behavior predictable.

The Shift to Code Execution / Code Mode

Recent workflows increasingly mo orchestration out of chat context and into code execution loops. This reduces repetiti tokens and makes tool usage auditable and testable.

Core reading:

Recommended Setup for Power Users

For users who want reproducible and lower-noise MCP usage, start with a codemode-oriented setup:

Client Fit Guide (Short )

Prompt Injection: Risks, Impact, and Mitigations

Prompt injection remains an open security problem for tool-using agents. It is manageable, but not "solved."

Primary risks:

Mitigation baseline:

Treat every tool output as untrusted input unless explicitly .

MCP Compliance State

This ser MCP protocol 2025-11-25 and SDK /sdk@^1.27.1.

| Feature | Status |
|---------|--------|
| stdio transport | Supported (default) |
| Streamable HTTP transport | Supported (MCP_TRANSPORT=http) |
| Tool annotations | All tools annotated with title, readOnlyHint, destructi, idempotentHint, openWorldHint |
| Origin (HTTP) | 403 on invalid Origin when MCP_ALLOWED_ORIGINS is set |
| JSON Schema 2020-12 | Zod-generated schemas |
| Structured tool errors | isError flag with descripti for model self-correction |

项目信息

开发语言：JavaScript

Star 数：13

技术要点

该项目属于安全软件方向的开源资源，代码结构清晰，适合安全研究人员学习参考。项目围绕A security vulnerability scanner built with MCP plugins展开，提供了可运行的实现，对理解相关安全机制、工具原理与攻防技术具有较高的研究价值。

从技术实现角度看，此类项目的核心在于对底层原理的深入理解与工程化落地。开发者在研究过程中可以结合官方文档与社区讨论，梳理项目的初始化流程、核心模块职责与数据流转，逐步掌握其中的技术细节与设计思路。

使用与学习建议

1. 下载源码压缩包，解压到本地环境。

2. 根据项目类型准备对应的运行环境与依赖。

3. 按照 README 中的步骤完成配置与部署。

4. 在隔离的测试环境中运行验证，避免影响生产系统。

免责声明

本资源来源于开源社区，仅供安全研究、技术学习与合法授权范围内的攻防演练使用，请勿用于任何非法或侵害他人权益的用途。使用本项目产生的一切后果由使用者自行承担。