Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MOBILE_RE_MCP_ALLOWED_DIRSNoOptional sandbox: set MOBILE_RE_MCP_ALLOWED_DIRS (':' separated on macOS/Linux, ';' on Windows) to restrict the tools to specific directories, e.g. "/Users/me/apks".

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
android_api_extractorA

Decompiles an APK and extracts Retrofit HTTP annotations and OkHttp3 endpoints from smali bytecode. Outputs a list of API endpoints or a Postman collection.

apk_manifest_analyzerA

Parses AndroidManifest.xml from an APK. Extracts package info, activities, services, receivers, intent filters, and highlights security-relevant flags like exported components, debuggable, and allowBackup.

apk_permissions_checkerB

Extracts and categorizes permissions requested by an APK. Dangerous permissions (those that grant access to sensitive user data or device features) are highlighted separately.

android_google_servicesA

Extracts Google and Firebase configuration from an APK. Parses google-services.json if present, then scans resources.arsc for string values using the strings command. If a smali_folder (apktool output) is provided, parses res/values/strings.xml directly for structured key=value output.

android_secrets_scannerA

Scans an APK for hardcoded secrets and API keys. Without smali_folder: runs strings on classes*.dex and resources.arsc, plus scans text assets inside the APK. With smali_folder (apktool output): scans res/values/strings.xml and assets as plain text files.

ios_manifest_analyzerA

Parses Info.plist from an IPA file. Extracts bundle ID, version, URL schemes, App Transport Security settings, background modes, and highlights insecure configurations.

ios_permissions_checkerB

Extracts privacy permission usage descriptions from an IPA's Info.plist. Each permission is categorized by risk level (HIGH / MEDIUM / LOW) with an explanation.

ios_entitlements_checkerA

Extracts and analyzes entitlements embedded in the iOS app binary using codesign. Detects dangerous entitlements like get-task-allow (debug builds), iCloud containers, and keychain groups.

ios_binary_stringsB

Extracts printable strings from an iOS app binary and filters for security-relevant patterns: HTTP/S URLs, API keys, AWS/Firebase/Google credentials, email addresses, and private IP addresses.

ios_frameworks_detectorA

Lists all third-party frameworks bundled inside an IPA (from the Frameworks/ directory). Maps known frameworks to categories: networking, analytics, ads, attribution, crash reporting, etc. Highlights privacy-relevant SDKs.

ios_google_servicesA

Extracts Google and Firebase configuration from an IPA. Parses GoogleService-Info.plist for API key, project ID, database URL, storage bucket, GCM sender ID, and OAuth client IDs. Also applies Google pattern scanning across all text plist and JSON files in the IPA.

ios_secrets_scannerB

Scans an IPA for hardcoded secrets and API keys. Layer 1: scans text resource files (JSON, XML, .strings, XML plists) inside the IPA. Layer 2: extracts the app binary and runs the strings command to find constants in compiled code.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.7/5.0

Scored across 12 tools

Disambiguation4/5

Most tools are clearly separated by platform and artifact type, such as manifest, permissions, entitlements, and frameworks. However, several scanning tools overlap: ios_binary_strings and ios_secrets_scanner both hunt for credentials in binaries/resources, and Google/Firebase extraction overlaps with secret scanning on both platforms.

Naming Consistency4/5

Names are consistently snake_case and descriptive, generally following a platform/artifact/action pattern. There is a minor prefix inconsistency between android_ and apk_ for Android tools, but the convention remains predictable.

Tool Count5/5

The 12 tools are well-scoped for a mobile reverse-engineering server and are evenly split between Android and iOS analysis needs. Each tool appears to earn its place without excessive fragmentation.

Completeness4/5

The surface covers core static-analysis tasks: manifests, permissions, secrets, Google/Firebase config, API extraction, binary strings, frameworks, and entitlements. There are still notable gaps such as signing/certificate validation, Android third-party SDK/framework mapping, iOS endpoint extraction, and certificate pinning or network security configuration analysis.

Maintenance

ActivityMaintained
ResponsivenessNo issues