golf-scanner - Discover and audit MCP servers for security vulner

项目说明

<di="center">

<h1 align="center">
<br>
<span style="font-size: 80px;">🔍 Golf Scanner</span>
<br>
</h1>

<h3 align="center">
Discover and audit MCP servers across your IDEs
</h3>

<br>

<p>
<a href=" src=" alt="License"></a>
<a href=" src=" alt="PRs"></a>
<a href=" src=" alt="Support"></a>
</p>

<p>
<a href=" Documentation</strong></a> · <a href=" Quick Start</strong></a> · <a href=" Golf</strong></a>
</p>

</div>

---

Free, open-source CLI that discovers MCP ser across your machine and runs security checks to produce a risk score. Single binary. Zero telemetry. No account required.

Quick Start

Install :

Or with Go:

Discover your MCP servers:

Run a security audit:

What It Does

Golf Scanner is a single static binary (pure Go, 3 dependencies) that:

1. Discovers MCP ser across 7 IDEs — Claude Code, Cursor, VS Code, Windsurf, Gemini CLI, Kiro, and Antigravity
2. Runs 20 security checks — 9 offline (no network) + 11 online (queries OS, npm, PyPI, OCI registries, MCP Registry)
3. Produces a 0–100 risk score per server with se scoring and hard caps

No account required. Runs offline. Zero telemetry.

Supported IDEs

Claude Code · Cursor · VS Code · Windsurf · Gemini CLI · Kiro · Antigravity

Usage

audit

Disco and run security checks with risk scoring.

Skip network checks (offline mode):

output with remediation details:

CI/CD integration — fail if high or critical findings:

| Flag | Default | Description |
|------|---------|-------------|
| --offline | false | Skip network checks (OS, npm, PyPI, MCP Registry, OCI registries) |
| --format | table | Output format: table or json |
| --json | false | Shorthand for --format json |
| --fail-on | | Exit code 1 if findings at or abo: note, medium, high, critical |
| --, -v | false | Show full finding details including remediation |
| --quiet, -q | false | Show only the summary table |

-- and --quiet are mutually exclusive.

Security Checks

| Check | What It Detects | Online |
|-------|-----------------|--------|
| Server Type | Classifies the server as package manager, container, binary, script, or HTTP | |
| Command Safety | Identifies risky patterns including pri escalation and shell injection threats | |
| Credentials | Finds plaintext credentials in args, URLs, and en | |
| Script Location | Flags scripts running from unsafe locations like /tmp or home directories | |
| Script Permissions | Detects world-writable script files | |
| Binary Location | Assesses executable placement across system paths and home directories | |
| Binary Permissions | Detects world-writable or group-writable binaries | |
| Container Isolation | Flags --pri mode, dangerous capabilities, host namespace sharing | |
| Container | Flags dangerous mounts — root filesystem, /etc, Docker socket | |
| Registry Listing | Confirms MCP Registry inclusion status | Yes |
| | Queries OSV.dev for known CVEs and malware in npm/PyPI packages | Yes |
| Typosquatting | Identifies similarly-named packages suggesting malicious imitation | Yes |
| Distribution | E adoption through download metrics and package age | Yes |
| Source Repository | Checks whether the package links to a source repository | Yes |
| Unscoped | Examines unscoped npm counterparts for security issues | Yes |
| GitHub Trust | E repository signals like activity, licensing, and contributor count | Yes |
| Container Image | Checks whether images use digest pinning (:) | Yes |
| Container Registry | image presence and flags potential tampering mismatch | Yes |
| Container Signature | cosign signatures with keyless authentication | Yes |
| OAuth | Discovers OAuth/OIDC configuration. Flags missing authentication | Yes |

For full details on each check, see the Security Checks reference.

Scoring

Each ser a 0–100 risk score:

1. Each check produces findings; the worst se determines the per-check score (0–10)
2. Scores are combined via se a (critical 10x, high 7.5x, medium 5x, note 1x)
3. The raw a is scaled to 0–100
4. Hard caps apply: any critical finding caps the score at 30, any high finding caps at 59
5. Risk level: Low (≥60), Moderate (>30), High (≤30)

For the full scoring explanation, see Understanding Results.

En

| | Purpose |
|----------|---------|
| GITHUB_TOKEN | Optional. Increases GitHub API rate limit from 60 to 5,000 req/hr. |
| GOLF_GITHUB_TOKEN | Optional. Fallback if GITHUB_TOKEN is not set. |

No token is needed for most scans. The scanner makes ~3 GitHub API calls per unique repo (metadata, commits, contributors) with results cached, so you'll only hit the unauthenticated limit if you have 20+ servers pointing to distinct GitHub repos.

Exit Codes

| Code | Meaning |
|------|---------|
| 0 | Success |
| 1 | No args, unknown command, --fail-on threshold exceeded, or flag conflict |
| 2 | JSON error or invalid --fail-on value |

License

Apache 2.0 — see LICENSE.

<di="center">
Made with ❤️ by the <a href=" team
</div>

项目信息

开发语言：Go

Star 数：8

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Discover and audit MCP servers for security vulnerabilities across Claude Code, Cursor, VS Code, and more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。