291–300 of 444 posts
Every time I read MCP, I think it means "master control program".
http://mcp.a1k.org/indexe.html
And I know I will forget again. "Model Context Protocol" is so bland I already forgot half of it by the time I'm at the third word, so that even some old Amiga stuff instantly overrides it.
Was this written by AI? MCP is essentially just JSON RPC with a few special fields that must be included. I have reservations about JSON RPC, but there needs to be some 'service discovery' layer for LLMs to interface with. It needs to be available in places like websites, desktop applications, backend services, etc. The CLI is only one place that these systems interface with. Whatever you replace MCP with will be in…
Every time I read articles about MCP I feel like the internet (or HN) is having a collective stroke. People are saying API are better than MCP. But MCP is just API with some instructions for the AI to discover how to use it. Nothing more nothing less. And some people are saying we should use 'CLI'... what does it even mean? LLMs are good with common CLI tools like ffmpeg because the knowledge is solidified inside the…
Earlier quoted context omitted.
MCP has a great advantage over agent using cli: MCP is much easier to secure so that it's hardwired that the agent can only call the pre-configured MCP server. We run our agents so that they don't have access to public internet, so they could not run any cli commands. It's all either built-in agent tools, or 3rd party mcp servers. The agents never have access to any credentials, which makes them much more safe to use…
Can you not just install/ restrict the available CLIs in the same way you do with MCPs? Or what else am I missing about why MCP is more secure than a CLI?
The good think about MCP is the authentication story. It is almost perfect. Compare this with CLIs which mostly piggy back on quirky browser authentication, env files and other bad practices. It is a security nightmare. It is certifiably insane.
So to compare MCPs to CLIs purely on token cost is missing the entire point that at the end of the day these agents need to operate safely and OAuth is the defacto standard where this can be done in somewhat consistent way across different vendors.
At cbk.ai we dynamically load MCPs into the context when the LLM needs them and unload them when finished. The cost for doing this is negligible and it scales well. The good think about MCP is the authentication story. It is almost perfect. Compare this with CLIs which mostly piggy back on quirky browser authentication, env files and other bad practices. It is a security nightmare. It is certifiably insane. So to com…
Earlier quoted context omitted.
No OP, but MCP really is just a logical next step once you've got an API. The API is the "low level" protocol, the MCP is the high level one, suited perfectly to an LLM that can call tools (since MCP essentially turns an API into a LLM tool). With just an API, the agent needs to "read your API docs" to know how to call it (that can be an OpenAPI spec or even just text). With MCP, the agent sees a bunch of tools it ca…
This is a great example of the AI-hype-induced reply. > to an LLM that can call tools (since MCP essentially turns an API into a LLM tool). "Tools" is literally an API call > With MCP, the agent sees a bunch of tools it can call, Yes, the agent first calls a specific API that returns the schema for that particular server. It's literally the same. > One more very important factor is authorization, which no one seems t…
I run the team at OpenAI that's responsible for the ChatGPT App Store, Codex plugins, and all things MCP. The thing that all these "MCP is dead" posts are missing is that whether or not MCP is used as a transport protocol is actually completely irrelevant. The reason MCP isn't dead is because practically ~every company on the planet is building an MCP server. I know this because we interact with all of them. Most of…
That's just because no one knows what they're doing and everyone is trying to copy everyone else. It's a giant mud hut made of shit.
MCP will go away, and something much simpler will play the same role.
Earlier quoted context omitted.
Did you consider that maybe he has different information than you do, and thus he holds a different opinion? I for one love MCP. It's way faster in my experience than skills / shell. And I like how (with Claude Code) I can setup the MCP in the web interface, use it in the chat and the CLI. Plus the flow to add an MCP via the browser is achievable to any user. And one thing I don't understand of skills is this. I have…
Usually with secrets in environment variables or headers.
Would pair well with direnv to set the right keys per project.