Skip to main content
Alpha · v0.0.0 · not production security software

What's being considered next

The capabilities below are not built. Nothing here can be turned on today, and nothing on this page collects information about your Circinus sessions, prompts, or code — only which idea you're interested in, and an email address if you choose to give one. This page exists to find out which directions are worth building before we build them.

Early access · not yet available · being validated

MCP / tool-description protection

Circinus already tracks where content came from and what it's allowed to cause when an agent reads an issue, a web page, or a changelog. This extends that same seam to an MCP server's own tool descriptions and definitions — so a malicious or silently-drifted tool description can't quietly expand what an agent is permitted to do, the same way untrusted document text can't today.

Early access · not yet available · being validated

GitHub / CI agent protection

Bring the same action-boundary decision to an agent running inside a GitHub Actions workflow or other CI context — not only an interactive Claude Code session on a laptop — so a compromised workflow file or a malicious pull-request body can't silently escalate what a CI-triggered agent is allowed to do.

Early access · not yet available · being validated

Team policy & centralized authority rules

Let a team define and share a set of authority rules across their own installs — without a hosted control plane or dashboard — so a lead can express "block this class of action for the whole team" once, instead of every teammate hand-editing their own local configuration.