Re:From MCP to Shell: MCP Auth Flaws Enable RCE in Claude Co...
by CuriouslyC on Tuesday September 23, 2025 @01:25PM
(#45350177)
MCP is legit bad, and it won't last long, just polluting context with MCP output alone is enough to make it a poor long term solution. We're going to end up with some sort of agent VM, where tool data can be conditionally expanded for processing in a given turn without persistently polluting context (think context templates).
Re:From MCP to Shell: MCP Auth Flaws Enable RCE in Claude Co...
by mehdibl on Tuesday September 23, 2025 @01:56PM
(#45350564)
MCP is only transport protocol here.
And you need tools to connect to external "systems", the context "pollution" can be managed easily. Also even if you don't use MCP you need to use tools and they need to expose their schema to the AI model.
I feel the MCP hype over bad security got a lot confused and very defensive over MCP or more globally tools use.
Re:From MCP to Shell: MCP Auth Flaws Enable RCE in Claude Co...
by greysteil on Tuesday September 23, 2025 @12:50PM
(#45349627)
I dunno, I’m still pretty surprised the MCP server auth process could pop a calculator on widely adopted clients. The protocol isn’t perfect but that’s totally unnecessary unsafe. Glad it’s fixed!
Re:From MCP to Shell: MCP Auth Flaws Enable RCE in Claude Co...
by orphea on Tuesday September 23, 2025 @01:20PM
(#45350118)
> Glad it’s fixed!
...and they used some random package with version 0.0.1 instead of writing 20 lines of code themselves.It's astonishing how allergic some people are to writing their own code, even the simplest shit has to be a dependency. Let's increase the attack surface, that's fine, what can go wrong, right?
https://github.com/modelcontextprotocol/use-mcp/commit/96063...
Re:From MCP to Shell: MCP Auth Flaws Enable RCE in Claude Co...
by chrisweekly on Tuesday September 23, 2025 @02:04PM
(#45350675)
You have a valid point about dependency management in general, but in this case, the v0.0.1 package was created by the same author "geelen" as the commit you linked. So, they're not allergic to writing the code, and it's not "some random package".
Re:From MCP to Shell: MCP Auth Flaws Enable RCE in Claude Co...
by moduspol on Tuesday September 23, 2025 @02:13PM
(#45350790)
LLMs are supposed to be smart. Why can't I point it to API docs and have it call an API?
And why wouldn't we move toward that direction instead of inventing a new protocol?
Re:From MCP to Shell: MCP Auth Flaws Enable RCE in Claude Co...
by queenkjuul on Wednesday September 24, 2025 @03:46AM
(#45357466)
Exactly this
Re:From MCP to Shell: MCP Auth Flaws Enable RCE in Claude Co...
by amannm on Tuesday September 23, 2025 @09:24PM
(#45355118)
MCP doesn't make any sense to exist at this point in time. All you need is CLIs and existing service interfaces. We don't need a new protocol for something whose purpose is to make more protocols unnecessary
I'm still not sure why everyone's acting like it's some well thought out system and not just tool descriptions shoveled into JSON and then shoved at an LLM. It's not a fundamental architectural change to enhance tool calls, it just got given a fancy name.
I do get that having a common structure for tool calling is very convenient but it's not revolutionary. What's revolutionary is everyone training their models for a tool calling spec and I'm just not sure that we've seen that yet.