jadx-headless-mcp: Headless MCP server for Android APK static analysis, built directly on jadx-core. No JADX GUI required

by 1013503897 · MCP Server · ★ 65

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

How to install jadx-headless-mcp

/plugin marketplace add 1013503897/jadx-headless-mcp
/plugin install jadx-headless@jadx-headless-mcp

Taken from the project's README on GitHub. Check the security audit before running it.

Security audit verdict: SAFE · quality 68/100

None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

Quick Facts

Stars65
Forks4
LanguageKotlin
CategoryMCP Server
Quality Score68/100
Open Issues3
Last Updated2026-10-13
Created2026-05-12
Platformsmcp
Est. Tokens~18k

About jadx-headless-mcp

jadx-headless-mcp English | 简体中文 Headless MCP server for Android APK static analysis, built directly on . No JADX GUI required, no Python adapter, no plugin to install — just one JVM process speaking MCP over stdio. Why jadx is two parts: the decompiler engine, and a GUI wrapped around it for a human to click through by hand.

Compatible Skills

These tools work well together with jadx-headless-mcp for enhanced workflows:

  • Mobile-Harness — semantic(0.22)+complementary+same_lang+similar_pop (53%)
  • and-code — semantic(0.19)+complementary+same_lang+similar_pop (52%)
  • andee — semantic(0.18)+complementary+same_lang+similar_pop (51%)
  • AndroidHarness — semantic(0.17)+complementary+same_lang+similar_pop (51%)

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Kotlin Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools