[dcherman]

How so? Let's use a common CLI tool as an example - kubectl. Config is generally stored in ~/.kube in a variety of config files. Running `kubectl config view` already redacts the auth information from the config. LLMs could invoke `kubectl` commands without having knowledge of how it's authenticated.

[simonw]

If the agent has permission to run kubectl config view what's to stop it from reading those config files directly?

[dcherman]

The same permissions model that works for other tools. In Claude Code terms, allow Bash(kubectl:*). Deny Read(**/.kube/**). That allows kubectl access without allowing the tool to read ~/.kube directly.

Your argument is the same for an MCP server - auth is stored somewhere on disk, what's to stop it from reading that file? The answer is the same as above.

[simonw]

Would that stop Claude from executing this code:

  python -c '
  print(open("~/.kube/config.txt").read())
  '

The point I'm making here is that with an MCP you can disable shell access entirely, at which point the agent cannot read credential files that it's not meant to be able to access.

[dcherman]

You can make the identical argument for the CLI tool. Allow kubectl, deny everything else.

[simonw]

I don't understand.

My argument here is that one of the reasons to use MCP is that it allows you to build smaller agents that do not have a full code execution environment, and those agents can then use MCPs to make calls to external services without revealing those credentials to the agent.

I think we both agree that if your agent has full Bash access it can access credentials.

[dcherman]

I think the gist of what we're debating is principle of least privilege - give the LLM the fewest privileges needed to accomplish the task and no more, that way you avoid issues like leaking credentials.

The approach you're proposing is that with a well designed MCP server, you can limit the permissions for your agent to only interacting with that MCP server, essentially limiting what it can do.

My argument is that you can accomplish the identical thing with an agent by limiting access to only invoking a specific CLI tool, and nothing more.

Both of our approaches accomplish the same thing. I'm just arguing that an MCP server is not required to accomplish it.