HexForge Gateway
Related Servers
Alternatives to HexForge Gateway
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityDmaintenanceMCP server for analyzing Android APK, DEX, or JAR files via a headless jadx engine, enabling LLM agents to query decompiled code, symbols, call graphs, and more.2GPL 3.0
- AlicenseBqualityCmaintenanceFully automated MCP server built to communicate with JADX-AI-MCP Plugin to analyze Android APKs using LLMs like Claude — uncover vulnerabilities, parse manifests, and reverse engineer effortlessly.321Apache 2.0
- AlicenseAqualityDmaintenanceAn MCP server that integrates with Apktool to provide live reverse engineering support for Android applications using Claude and other LLMs through the Model Context Protocol.16691Apache 2.0
- AlicenseAqualityAmaintenanceA minimal, secure MCP server for AI-assisted mobile development, enabling build, install, interact, and inspect Android/iOS apps.5215 npm14Apache 2.0
- AlicenseNot gradedqualityBmaintenanceProvides AI agents with a unified MCP interface for Android APK reverse engineering, metadata analysis, Smali/resource editing, rebuilding, signing, verification, and ADB device testing.MIT
- AlicenseBqualityBmaintenanceA Model Context Protocol server that connects to a custom JADX fork (JADX-AI) and enables local LLMs to interact with decompiled Android app code for live reverse engineering assistance.32811Apache 2.0
TDQS
Scored across 29 tools
Most tools target distinct resource+action pairs and the descriptions explicitly cross-reference each other (decompile_apk vs decode_apk, scan_secrets vs search_code, chat_with_workspace vs summarize_text). The only mild overlaps are in the reading surface: list_knowledge (which includes reports), get_report and list_findings all expose findings-like content, and get_graph_entity vs list_graph_entities require reading the descriptions to pick correctly.
Almost everything follows a verb_noun pattern (list_findings, create_finding, verify_finding, read_file, search_code) or a domain-prefixed variant (adb_*, frida_*) that stays readable. Minor deviations like adb_devices (noun-only, unlike list_workspaces) and frida_list_processes (prefix before verb) break the pattern slightly but never cause confusion.
29 tools is heavy, though the server genuinely spans several sub-domains: workspaces, findings, knowledge graph, file ops, apktool, adb, Frida and AI helpers. Each tool is individually justified, but the surface is at the upper bound of what an agent can hold in context comfortably.
Coverage is broad (workspace lifecycle, findings create/update/verify/report, decompile/decode/build, device and Frida operations), but there are real dead ends: build_apk produces an unsigned APK and adb_install rejects unsigned APKs, yet no sign_apk tool exists, so the edit-rebuild-install loop can't be closed. There are also no delete operations for findings, artifacts or workspaces.