STEP 4 of ATOMIC ACTION 2 (install safely into this repo) — the escape. Roll back a previous TokRepo Codex install session when verify/apply fails or the user rejects the result. Defaults to dry_run=true and last=true. The four-step install atomic action (plan → verify → apply → rollback) is cont...
AI agents call tokrepo_rollback to permanently remove resources in TokRepo — AI Asset Registry — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
A rollback operation reverts previously applied changes, which constitutes an irreversible destructive action on the installed state. While it may restore a prior state, it destroys the current installed configuration. The tool is part of an install pipeline and can undo applied file changes across a repo, giving it a high blast radius if triggered incorrectly.
From the tool's definition 'Roll back a previous TokRepo Codex install session' and 'escape... when verify/apply fails or the user rejects the result' — rollback irreversibly undoes applied changes, removing installed assets and reverting the repository state
Attacks that exploit this kind of access
STEP 4 of ATOMIC ACTION 2 (install safely into this repo) — the escape. Roll back a previous TokRepo Codex install session when verify/apply fails or the user rejects the result. Defaults to dry_run=true and last=true. The four-step install atomic action (plan → verify → apply → rollback) is contractually incomplete without this escape. It is categorised as a Destructive tool in the TokRepo — AI Asset Registry MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the TokRepo — AI Asset Registry MCP server in PolicyLayer and add a rule for tokrepo_rollback: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches TokRepo — AI Asset Registry. Nothing to install.
tokrepo_rollback is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the tokrepo_rollback rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for tokrepo_rollback. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
tokrepo_rollback is provided by the TokRepo — AI Asset Registry MCP server (tokrepo-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →