I have tested this exact scenario, and it works. Opus 5 had access to IDA over MCP, and I simply asked it HOW certain things were done in the target binary. Purely informational, educational, discovery, it was very helpful creating context documents. Then I took those over to GLM-5.2 to actually accomplish something.
I didn't feel like installing a whole redis-server service on my Windows machine, so instead I built a lightweight yet very capable clone. Maybe you'll find it handy for local development.
Yeah, it's token intensive but worth it. I built a very dumb example harness which used IDA via MCP and analyzed/renamed/commented all ~67k functions in a binary, using Claude Haiku for about $150. A local model could've accomplished it for much less/free. The knowledge base it outputs and the marked up IDA db are super valuable.
I did something similar using ghidramcp for digging around this keyboard firmware, repo contains the ghidra project, linux driver and even patches to the original stock fw. https://github.com/echtzeit-solutions/monsgeek-akko-linux
I remember being an early teenager on IRC and joining a small BBS development team. I said I knew Pascal, but that was a fib... I did learn it quickly, though, and used it for many years. I can still find the code online, and see my contribution which I get a kick out of... It was a tool that you entered colored ascii frames for an animated "press any key to continue" prompt, and it output a valid pascal function file for that animation.
Same here... It's still amazing, and I have no legitimate reason to upgrade. Could be looked at as a failure of some sort, that they haven't given us a good reason.
reply