Hacker News

points by KaiserPro 2 days ago | 0 comments

I mean I get the appeal, but that does mean that your agents also have the same level of access as you, and no way to limit actions to agents.

For us, most of our MCPs have non-undoable actions disabled. This is to stop agents writing a tool that recursively doing something silly.

[–] HumanOstrich 2 days ago

As stated in the second paragraph of TFA, the machine workloads get their own infrastructure identity. Each identity can have different policies and permissions.

[–] saligrama 2 days ago

Yes, exactly, a cloud agent always authenticates itself (via OIDC) as an agent (machine) identity, with the option for the identity of the human who launched it to ride along.

We then have the ability to enforce (extremely fine grained) policies based on that combined identity, plus any of the claims in the OIDC token (e.g., the repo URL), plus any of the data on the protocol itself (e.g., block non-read-only queries; redact anything sensitive).

https://docs.formal.ai/docs/guides/policies/introduction