I can’t understand what this article is talking about.
When I create and run a simple MCP server, I decide what commands it’s able to run. I can decide if the interface is stdio or http with sse. So I can’t see how someone would send me a request for “rm -rf /” that would actually run it, unless running it is part of the intended features.
Maybe the protocol design leaves that in the open, but I think not even negligence would be enough to implement this flaw, because it’s easier to NOT do it.
So what I got is that the pre existing stocks will be split behind the scenes into stocks that are settled by a clearing house as usual, and settled by the same clearing house with blockchain.
I’m just confused, if you have one authority, a single one, responsible for settlement, then a database is enough. And a blockchain with one node that writes and many that read, is ridiculous.
I’d assume the firmware is the same shipped with the vendor or pretty much very close to the sample code.
Does it require something like an API key or password? Can these implement diff Hellman key exchange? Otherwise I’d just assume you can eavesdrop when someone is updating the contents.
I read because of your comment, it was a really fun read. A bit cringe on the “we’re white collar thugs and we will bully you until you do as we say”, but it’s hilarious how it failed spectacularly for multiple reasons.
I can’t understand what this article is talking about.
When I create and run a simple MCP server, I decide what commands it’s able to run. I can decide if the interface is stdio or http with sse. So I can’t see how someone would send me a request for “rm -rf /” that would actually run it, unless running it is part of the intended features.
Maybe the protocol design leaves that in the open, but I think not even negligence would be enough to implement this flaw, because it’s easier to NOT do it.