Live data from Hacker News

MCP server for Ghidra

github.com

1–10 of 77 posts

Re: MCP server for Ghidra

#3

my experience with just copying and pasting things from ghidra into LLMs and asking it to figure it out wasn't so successful. it'd be cool to have benchmarks for this stuff though.

I actually have only tried this once but had the opposite experience. Gave it 5 or so related functions from a ps2 game and it correctly inferred they were related to graphics code, properly typing and naming the parameters. I’m sure this sort of thing is extremely hit or miss though

Re: MCP server for Ghidra

#4

my experience with just copying and pasting things from ghidra into LLMs and asking it to figure it out wasn't so successful. it'd be cool to have benchmarks for this stuff though.

I actually have only tried this once but had the opposite experience. Gave it 5 or so related functions from a ps2 game and it correctly inferred they were related to graphics code, properly typing and naming the parameters. I’m sure this sort of thing is extremely hit or miss though

Most likely there was just a mangled symbol somewhere that it recognised from its training data.

Re: MCP server for Ghidra

#7
post #4

Earlier quoted context omitted.

I actually have only tried this once but had the opposite experience. Gave it 5 or so related functions from a ps2 game and it correctly inferred they were related to graphics code, properly typing and naming the parameters. I’m sure this sort of thing is extremely hit or miss though

Most likely there was just a mangled symbol somewhere that it recognised from its training data.

Where is that coming from? The chances that some random ps2 games code symbols are in the training data are infinitesimal. It's much more likely that it can understand code and rewrite it. Basically what LLM have been capable of for years now.

Re: MCP server for Ghidra

#8
post #4

Earlier quoted context omitted.

Most likely there was just a mangled symbol somewhere that it recognised from its training data.

Where is that coming from? The chances that some random ps2 games code symbols are in the training data are infinitesimal. It's much more likely that it can understand code and rewrite it. Basically what LLM have been capable of for years now.

Parent is supposing w/o any experience. LLMs can see in hex, bytecode and base64, rot13, etc. I use LLMs to decompile bytecode all the time.

Re: MCP server for Ghidra

#9

my experience with just copying and pasting things from ghidra into LLMs and asking it to figure it out wasn't so successful. it'd be cool to have benchmarks for this stuff though.

I've been thinking on how to build a benchmark for this stuff for a while, and don't have a good idea other than LLM-as-judge (which quickly gets messy). I guess there's a reason why current neural decompilation attempts are all evaluated on "seemingly meaningless" benchmarks like "can it recompile without syntax error" or "functional equivalence of recompilation" etc.

Re: MCP server for Ghidra

#10
Which tools can currently invoke MCP? I have read only a little about MCP and got to know that Claude's desktop application is capable of using MCP locally.

Are there any chat interfaces which allow using MCP remotely?

I would like to be able to specify MCP endpoints and the functions they offer in ChatGPT's, Claude's and Gemini's web interfaces so that I can have them call my servers remotely. A bit like "GPTs" and "Gems".

Post reply on HN