ghidra-mcp
Ghidra MCP Server, 200+ MCP tools for AI-powered reverse engineering. GUI plugin + headless server, lazy tool loading, convention enforcement, batch operations, Ghidra Server integration, and Docker deployment.
Runssource: GitHubJavaApache-2.0commit 1e0211388d9f
Java, Apache-2.0 licensed. The project labels itself: ai, binary analysis, ghidra, ghidra extension, java, mcp, mcp server and model context protocol.
ghidra-mcp runs. An Argusic agent installed it in 3 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Python MCP bridge installed and operational on both stdio and HTTP transports; unit test suite passes 557/557.
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 93.5 of 100 (the mean of this project's run scores).
At a glance
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.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- JDK 21 not installed2 minutes
- uv not installed1 minute
- Install time
- 3 minutes
- Cold machine to finish
- 3 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- pytest tests/unit/ --no-cov: 557 passed, 7 skipped, 0 failed; bridge-mcp-ghidra --transport stdio/streamable-http responds to MCP initialize with 200 OK
- Model tokens used
- 58,184
- Exact commit tested
- 1e0211388d9f
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
- streamable-http transport: `POST /mcp` returns `200 OK` with proper SSE initialize response
**Limitations**: The Java Ghidra extension can't be compiled (requires Ghidra 12.1.2 JARs in `~/.m2…
tokens used
58,184
Everything works. Here's the full report:
**Install**: `uv sync` installed 61 packages including the bridge. JDK 21 was missing — downloaded …
**Tests**: 557 passed, 7 skipped (Windows-only process detection tests), 0 failed. The 5 gradle tes…
**Launch verified** via three methods:
- `bridge-mcp-ghidra --help` prints full usage
- stdio transport: MCP initialize responds with `{"jsonrpc":"2.0","id":1,"result":{"protocolVersion…
- streamable-http transport: `POST /mcp` returns `200 OK` with proper SSE initialize response
**Limitations**: The Java Ghidra extension can't be compiled (requires Ghidra 12.1.2 JARs in `~/.m2…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
- Reached a running state on a clean machine, with the session recorded.
- Installed in 3 minutes, faster than the median of the 36 comparable projects Argusic has measured.
- Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed Apache-2.0, as reported by its host.
- Measured 2 times, so the result is not a one-off.
Of the 37 ai projects Argusic has installed and timed, ghidra-mcp was the 11th fastest to reach a running state, and 30 of 37 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 3 minutes after the clone.
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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs | 100.00 | 0.02 | |
| Argusic Runner | 1/3 | Runs with mocks | 87.00 | 0.04 |
Topics (from GitHub)
aibinary-analysisghidraghidra-extensionjavamcpmcp-servermodel-context-protocolpythonreverse-engineeringstatic-analysis
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/ghidra-mcp)Questions
- Does ghidra-mcp run?
- Yes. ghidra-mcp runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test ghidra-mcp?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 1e0211388d9f. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test ghidra-mcp?
- The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does ghidra-mcp take to install?
- 3 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does ghidra-mcp need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing ghidra-mcp?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does ghidra-mcp compare with the alternatives?
- Of the 37 ai projects Argusic has installed and timed, ghidra-mcp was the 11th fastest to reach a running state, and 30 of 37 reached one at all.
- Where is the evidence for ghidra-mcp?
- 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.