GoMobSec MCP server
GoMobSec MCP server lets you scan local Android/iOS apps and review security findings and reports from an MCP client.
Check the connected GoMobSec account, plan, and monthly scan usage.
List recent scans and inspect a scan's status and severity counts.
Retrieve findings with severity, CWE, MASVS, CVSS, location, and description; filter by severity and optionally include false positives.
Start scans by uploading local
.apk,.xapk,.apks,.apkm, or.ipafiles in quick, static, or full mode.Wait for scans to finish with progress reporting and timeouts.
Download completed reports as DOCX, XLSX, JSON, or SARIF into the configured download folder.
Use the
security_reviewprompt to turn a finished scan into a prioritised fix plan.
Enables scanning Android app packages (.apk, .xapk, .apks, .apkm) for security issues and retrieving findings with severity, OWASP MASVS category, CWE, CVSS, location, and descriptions.
Enables scanning iOS app packages (.ipa) for security issues and retrieving findings with severity, OWASP MASVS category, CWE, CVSS, location, and descriptions.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@GoMobSec MCP server Scan ./build/app-release.apk and tell me what to fix first"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
GoMobSec MCP server
The official Model Context Protocol server for GoMobSec. Use it to scan Android and iOS apps for security issues from Claude, Cursor, VS Code or any other MCP client. Results are mapped to OWASP MASVS, CWE and CVSS, and you can download the full pentest-style report.
You: Scan ./build/app-release.apk and tell me what to fix first.
AI: start_scan → wait_for_scan → get_findings → a prioritised fix planUse it in Claude without installing anything
GoMobSec also runs this server for you at https://mcp.gomobsec.ai/mcp. In
Claude, go to Settings → Connectors → Add custom connector, enter that URL,
and sign in with your GoMobSec account (every plan, Free included). Setup,
tools, security and privacy are covered in docs/HOSTED.md.
The rest of this page is about the local server, which reads apps straight from your disk and authenticates with an API key.
Related MCP server: saglitzsecure-mcp
Requirements
A GoMobSec account with an API key. Create one under API keys in GoMobSec. API keys come with every plan, Free included. What the plan decides is the work a key can ask for: scans per month, and whether
fullscan mode is available.uv(recommended) or Python 3.10+.
Install
The server runs locally over stdio. Your API key stays on your machine, and the server reads the APK or IPA straight from disk.
Claude Code
claude mcp add gomobsec --env GOMOBSEC_API_KEY=your-key -- uvx gomobsec-mcpClaude Desktop, Cursor, Windsurf and others
Add this to the client's MCP config file. For Claude Desktop that is
claude_desktop_config.json; for Cursor it is ~/.cursor/mcp.json.
{
"mcpServers": {
"gomobsec": {
"command": "uvx",
"args": ["gomobsec-mcp"],
"env": { "GOMOBSEC_API_KEY": "your-key" }
}
}
}VS Code
Add this to .vscode/mcp.json. VS Code asks for the key on first use and
stores it securely:
{
"inputs": [
{ "type": "promptString", "id": "gomobsec-key", "description": "GoMobSec API key", "password": true }
],
"servers": {
"gomobsec": {
"command": "uvx",
"args": ["gomobsec-mcp"],
"env": { "GOMOBSEC_API_KEY": "${input:gomobsec-key}" }
}
}
}Without uv, run pip install gomobsec-mcp and use gomobsec-mcp as the command.
Tools
Tool | What it does |
| The account and plan the key belongs to |
| Scans used this month against the plan limit |
| Recent scans, newest first |
| Status of one scan and, once it is complete, the findings count by severity |
| Findings with severity, CWE, MASVS category, CVSS, location and description. Can filter by severity; false positives are hidden unless asked for |
| Uploads a local |
| Waits for a scan to finish and reports progress meanwhile |
| Saves the DOCX, XLSX, JSON or SARIF report to your download folder |
There is also one prompt, security_review, which turns a finished scan into
a prioritised fix plan.
Scans you start here count against your GoMobSec plan, exactly like scans from the web app or CI. The scan modes and limits are the ones your plan allows.
Configuration
Variable | Default | |
| — | Required. Your GoMobSec API key |
|
| The only folder |
|
| Change this only for a dedicated or on-prem GoMobSec |
|
| Base URL for the report links |
Security
Your key stays local. It is read from the environment and only ever sent to GoMobSec over HTTPS. It is never written to a file or included in tool output.
Uploads are limited to app packages.
start_scanonly sends files that are mobile app packages: the right extension, a zip archive, and at most 250 MB. It cannot be used to upload any other file from your machine.Downloads never overwrite.
download_reporttakes no path. It writes new files (mode0600) intoGOMOBSEC_DOWNLOAD_DIRand never replaces an existing file.Finding text is treated as untrusted. Titles and descriptions can contain strings from the scanned app, and an app author controls those. The server strips control and bidi characters, keeps the text inside a fenced data block, and tells the model to treat it as data. Still, review what your assistant does after reading the results of a scan of an app you don't trust.
Access is limited to your own scans. The key only sees scans on its own account or organisation. Revoke it in GoMobSec at any time.
To report a vulnerability, see SECURITY.md.
Privacy
The local server keeps nothing. It reads your API key from the environment, sends requests only to GoMobSec, and writes only the reports you ask for. What GoMobSec does with the apps you scan is in the GoMobSec privacy policy. For the hosted connector, see its privacy policy.
Development
python -m venv .venv && . .venv/bin/activate
pip install -e ".[test]"
pytestTry it with the MCP Inspector: npx @modelcontextprotocol/inspector gomobsec-mcp.
The hosted connector's tests (tests/test_hosted.py) run a real HTTP server on a
free port and go through the whole OAuth flow, with GoMobSec's side faked.
Releasing
Bump the version in
src/gomobsec_mcp/__init__.pyand bothversionfields inserver.json(the tests and the release workflow check they match), and add aCHANGELOG.mdentry.Publish a GitHub release tagged
vX.Y.Z. ThePublishworkflow tests and builds it, uploads it to PyPI (Trusted Publishing), then lists it in the MCP Registry (GitHub OIDC). No tokens are stored in the repository.
License
MIT
Available Tools
8 toolsdownload_reportDownload reportAInspect
Download the full report of a completed scan — DOCX (pentest report), XLSX, JSON or SARIF (for code-scanning tools) — into the GoMobSec download folder (GOMOBSEC_DOWNLOAD_DIR, default ~/Downloads/gomobsec). Never overwrites an existing file. Returns the saved path.
Inputs: scan_id (required), format. Returns: result
get_findingsScan findingsARead-onlyInspect
Findings of a completed scan: severity, title, CWE, MASVS category, CVSS, location and description, most severe first. Optionally filter by severity. False positives are left out unless include_false_positives is true.
Inputs: scan_id (required), limit, severity, include_false_positives. Returns: result
get_scanScan statusBRead-onlyInspect
Status of one scan and, once complete, its findings count by severity.
Inputs: scan_id (required). Returns: result
get_usagePlan usageBRead-onlyInspect
How many scans the account has used this month against its plan limit.
Inputs: no named parameters. Returns: result
list_scansList scansARead-onlyInspect
List the account's most recent scans, newest first (1-50).
Inputs: limit. Returns: result
start_scanStart a scanAInspect
Upload a local Android (.apk, .xapk, .apks, .apkm) or iOS (.ipa) app to GoMobSec and start a security scan. Uses one scan from the account's plan — confirm with the user first. 'quick' and 'static' work on every plan; 'full' (static + dynamic) needs a paid plan. Returns the scan id; follow it with wait_for_scan.
Inputs: file_path (required), scan_mode, project_name. Returns: result
wait_for_scanWait for a scanARead-onlyInspect
Wait until a scan finishes (or the timeout passes, 1-60 minutes), reporting progress, then return its status and findings count. Scans can take longer than one wait; call it again if the scan is still running.
Inputs: scan_id (required), timeout_minutes. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool targets a distinct action/resource: account identity, usage, scan listing, individual scan status, findings, waiting, starting scans, and report download. The only potentially neighboring tools—get_scan, wait_for_scan, and get_findings—are clearly differentiated by description: status polling versus blocking wait versus detailed findings.
Most names follow a clear snake_case verb_noun pattern (get_scan, list_scans, start_scan, download_report). The only deviation is 'whoami', which is a well-known conventional command but not part of the same pattern.
Eight tools is well-scoped for a focused mobile security scanning service. Each tool has a clear role in the scan lifecycle and there is no obvious filler.
The surface covers account checks, scan creation, waiting, status/findings retrieval, and report download, forming a complete core workflow. Minor gaps exist, such as scan cancellation or deletion, but these are not necessary for the main lifecycle.
Maintenance
Related MCP Connectors
Scan iOS and Android project files for common App Store and Play review issues over MCP.
Zero-config MCP security scanner for AI-generated apps. 25K+ vulnerability patterns.
Security, SEO and AI-visibility scanner for web apps · free scans and focused checks via MCP.
Compliance & security scan for your app: secrets, exposed files, headers, privacy, AI-disclosure.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceAutomatically discovers and tests MCP services for security vulnerabilities including command injection, SQL injection, SSRF, path traversal, and sensitive data exposure with detailed reports and remediation guidance.1-
- AlicenseNot gradedqualityDmaintenanceEnables security scanning of source code and Apple configuration files, providing evidence-based findings, explanations, remediation plans, threat modeling, and knowledge base access through MCP tools.MIT
- FlicenseBqualityDmaintenanceEnables local-first static and optional controlled dynamic analysis of Android APK artifacts, with provenance-aware downloads, Markdown reports, and structured security findings via MCP stdio tools.9-
- AlicenseBqualityBmaintenanceEnables developers and security teams to run evidence-first Android and iOS security audits, manage jobs and reports, query public vulnerability intelligence, evaluate policies, and plan runtime checks through stdio MCP tools and resources.2480 PyPIMIT