It seems like OP needs to provide a solution to hiding the credentials from the model in order to suggest CLI-mode only, and also a solution to the problem of agents without shell access.
I've been thinking about this. Technically mcp auth is also not secure, the keys are in env or in file and accessible to the agent.I think something like infiscial ai proxy could be useful here. Never store the creds on device.
Well, if your agent lacks shell access (or has some other sandboxing going on), it shouldn't have access to envs and MCP setup files.(leaving out cases where your genius GPT-12 Galaxy Ultra agent hacks the sandboxing from inside)
honoluluxyz · · focus · HN ↗
maharshi365 · · focus · HN ↗
I think something like infiscial ai proxy could be useful here. Never store the creds on device.
vitamark · · focus · HN ↗
(leaving out cases where your genius GPT-12 Galaxy Ultra agent hacks the sandboxing from inside)