jadx-mcp-server

MCP server for JADX-AI Plugin

Runs with mockssource: GitHubPythonApache-2.0commit d99d130d53f1

Python, Apache-2.0 licensed. The project labels itself: ai, android hacking, android reverse engineering, application security, llm, mcp, mcp server and mcp servers.

jadx-mcp-server runs, with stand-ins for the services it depends on. An Argusic agent installed it in 1 minute and hit no errors on a clean machine with no GPU, and the whole session was recorded.

The jadx-mcp-server Python MCP server installs all dependencies, passes its shutdown test, and responds correctly to MCP initialize and tools/list requests over both stdio and HTTP transports, with 25+ tools registered and ready for JADX-GUI plugin integration.

What the agent ended up with on a clean machine, in its own words. How this is measured

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.03 (measured)
recorded runs
2
last tested
stars
852
forks
138
open issues
3
watchers
5
size
2 MB
created
last push

Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.

What was measured

From the run that decided this verdict. Every line is a recorded value, not an estimate.

Install time
1 minutes
Cold machine to finish
3 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
How the result was proved
python -m unittest tests/test_shutdown.py exited 0, 1 passed; python jadx_mcp_server.py --http --port 18659 started and responded to MCP initialize (200) and tools/list (200) over HTTP
Model tokens used
88,736
Exact commit tested
d99d130d53f1
Container image
sha256:cdd920bce783

What was not measured

The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.

Peak GPU memory
this ran on a CPU machine, so there was no GPU to sample
Behaviour over a long run
each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
Behaviour against real services
this run was verified against stand-in services only

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

Let me time-box what I've done and provide the final report. Here's my full assessment:
**Install**: `pip install -r requirements.txt` succeeded with all dependencies including fastmcp 4.…
**Errors encountered**: None — the install and launch went cleanly.
**Test suite**: `python -m unittest tests/test_shutdown.py` passed (1 test, 0.001s).
**Launch verification**:
- `--help` prints usage correctly
- Default stdio mode starts the MCP transport and waits for connections
- HTTP mode (`--http --port XYZ`) starts Uvicorn and responds to MCP requests
- MCP `initialize` request returns 200 with proper capabilities
- MCP `tools/list` returns 200 with all 25+ registered tools
**JADX Plugin dependency**: The server health-pings a JADX AI MCP Plugin on startup which is expect…
**No fixes needed** — everything worked out of the box.

Replay the whole session, every command from a clean machine to this point.

How it was tested

One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.

Strengths and limits

Measured facts, not opinions. How this is written.

What went well

  • Installed in 1 minute, faster than the median of the 236 comparable projects Argusic has measured.
  • Nothing broke on the way: zero errors between clone and running.
  • Licensed Apache-2.0, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

What did not, or is not known

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.

Of the 237 ai projects Argusic has installed and timed, jadx-mcp-server was the 36th fastest to reach a running state, and 168 of 237 reached one at all.

Also tested, in the same area

Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs with mocks92.000.03
Argusic Runner1/3Runs with mocks92.000.03

Topics (from GitHub)

aiandroid-hackingandroid-reverse-engineeringapplication-securityllmmcpmcp-servermcp-serversmobile-securitymodel-context-protocolmodel-context-protocol-serverpythonreverse-engineeringvapt

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/jadx-mcp-server.svg)](https://argusic.com/subject/jadx-mcp-server)

Questions

Does jadx-mcp-server run?
jadx-mcp-server runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 1 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test jadx-mcp-server?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit d99d130d53f1. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test jadx-mcp-server?
The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does jadx-mcp-server take to install?
1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does jadx-mcp-server need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing jadx-mcp-server?
Nothing did, in the recorded run: zero errors between clone and running.
How does jadx-mcp-server compare with the alternatives?
Of the 237 ai projects Argusic has installed and timed, jadx-mcp-server was the 36th fastest to reach a running state, and 168 of 237 reached one at all.
Where is the evidence for jadx-mcp-server?
All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion