
MobSF MCP Server
A Node.js-based Model Context Protocol implementation that provides a standardized interface for integrating Mobile Security Framework's security analysis capabilities into automated workflows and third-party tools.
README
MobSF-MCP
Architecture based on https://github.com/GH05TCREW/mobsf-mcp
📑 Overview
MobSF MCP is a Node.js-based Model Context Protocol implementation for Mobile Security Framework (MobSF). It provides a standardized interface for integrating MobSF's security analysis capabilities into automated workflows and third-party tools.
🛠️ Prerequisites
- Node.js (v14 or higher)
- npm (Node Package Manager)
- Running instance of MobSF with API access
⚙️ Installation And Usage
Clone the repository or navigate to the mobsf-mcp directory, and install dependencies:
npm install -g mobsf-mcp
Configure environment variables and start the MobSF MCP server by using the npx command:
📚 Open PowerShell as an administrator
$env:MOBSF_URL="http://localhost:8000";
$env:MOBSF_API_KEY="your_api_key_here";
npx mobsf-mcp
📂 API Reference
Available Endpoints
Endpoint | Description | Parameters |
---|---|---|
uploadFile |
Upload a mobile application file (APK, IPA, or APPX) for security analysis | file : File path to upload |
getScanLogs |
Retrieve detailed scan logs for analyzed application | hash : MD5 hash of the scan |
getJsonReport |
Get full JSON security analysis report | hash : MD5 hash of the scan |
getJsonReportSection |
Get specific section of the report | hash : MD5 hash, section : Section name |
getJsonReportSections |
List all available report sections | hash : MD5 hash of the scan |
getRecentScans |
Retrieve list of recent security scans | page : Page number, pageSize : Results per page |
searchScanResult |
Search scan results by various criteria | query : Search term (hash/name/package) |
deleteScan |
Delete scan results | hash : MD5 hash of the scan |
getScorecard |
Get application security scorecard | hash : MD5 hash of the scan |
generatePdfReport |
Generate PDF security report | hash : MD5 hash of the scan |
viewSource |
View source files from analysis | hash : MD5 hash, file : File path, type : File type |
getScanTasks |
Get scan tasks queue (async scan queue) | None |
compareApps |
Compare two scan results | hash1 : First scan hash, hash2 : Second scan hash |
suppressByRule |
Suppress findings by rule ID | hash : MD5 hash, type : code/manifest, rule : Rule ID |
suppressByFiles |
Suppress findings by files | hash : MD5 hash, type : code, rule : Rule ID |
listSuppressions |
View scan suppressions | hash : MD5 hash of the scan |
deleteSuppression |
Delete suppressions | hash : MD5 hash, type : code/manifest, rule : Rule ID, kind : rule/file |
listAllHashes |
Get all report MD5 hash values | page : Page number, pageSize : Results per page |
JSON Report Sections
The following sections are available when using getJsonReportSection
:
Basic Information
version
: MobSF versiontitle
: Report titlefile_name
: Analyzed file nameapp_name
: Application nameapp_type
: Application typesize
: File sizemd5
,sha1
,sha256
: File hashespackage_name
: Application package name
Application Components
main_activity
: Main activity nameexported_activities
: List of exported activitiesbrowsable_activities
: List of browsable activitiesactivities
: All activitiesreceivers
: Broadcast receiversproviders
: Content providersservices
: Serviceslibraries
: Native libraries
Security Analysis
target_sdk
,max_sdk
,min_sdk
: SDK versionsversion_name
,version_code
: App version infopermissions
: Declared permissionsmalware_permissions
: Potentially dangerous permissionscertificate_analysis
: Certificate security analysismanifest_analysis
: AndroidManifest.xml analysisnetwork_security
: Network security configurationbinary_analysis
: Binary file analysiscode_analysis
: Source code security analysisniap_analysis
: NIAP compliance analysis
Additional Analysis
permission_mapping
: Permission usage mappingurls
,domains
,emails
: Extracted stringsfirebase_urls
: Firebase URL analysisexported_count
: Count of exported componentsapkid
: APK identifier informationbehaviour
: Application behavior analysistrackers
: Tracking libraries detectionplaystore_details
: Google Play Store detailssecrets
: Detected secrets/keyslogs
: Analysis logssbom
: Software Bill of Materialsaverage_cvss
: Average CVSS scoreappsec
: Application security scorevirus_total
: VirusTotal scan results
🖥️ VSCode Cline Extension Configuration
To use this project with the cline extension in VSCode, add the following configuration to your cline configuration file:
{
"mcpServers": {
"MobSF MCP Server": {
"disabled": false,
"timeout": 60,
"command": "Nodejs\\node.exe",
"args": [
"index.js"
],
"env": {
"MOBSF_URL": "http://localhost:8000",
"MOBSF_API_KEY": "your_api_key_here"
},
"transportType": "stdio"
}
}
}
⚠️ Path to your Node.js executable (adjust according to your system, e.g.,
C:\\Program Files\\nodejs\\node.exe
). Make sure to fill in your actualMOBSF_API_KEY
in the configuration.
⚠️ Disclaimer and Legal Notice
This tool is designed and provided for security researchers, penetration testers, and developers for LEGAL USE ONLY. The primary purpose is to assist in:
- Security assessment of your own applications
- Applications you have explicit permission to test
- Research and educational purposes
The following uses are strictly prohibited:
- Any malicious or harmful activities
- Unauthorized access to systems or data
- Testing applications without proper authorization
- Any illegal activities or violation of laws
By using this tool, you agree to:
- Use it only for legal and authorized purposes
- Take full responsibility for your actions
- Comply with all applicable laws and regulations
- Hold the developers and contributors harmless from any claims
📄 License
This project is licensed under the Apache 2.0 License - see the LICENSE file for details.
✨ Acknowledgments
推荐服务器

Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。