Roll back an app to a previous release
AI agents invoke faber_rollback to trigger actions in Faber MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
A rollback triggers an external deployment operation that switches the running application to a previous release. While it restores a prior state (making it partially reversible), it actively executes a deployment pipeline operation with significant blast radius — it changes the live production environment and could disrupt running services, active users, or ongoing transactions.
From the tool's definition Roll back an app to a previous release
Attacks that exploit this kind of access
Roll back an app to a previous release. It is categorised as a Execute tool in the Faber MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Faber MCP Server MCP server in PolicyLayer and add a rule for faber_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 Faber MCP Server. Nothing to install.
faber_rollback is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the faber_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 faber_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.
faber_rollback is provided by the Faber MCP Server MCP server (joshtrebilco/faber-mcp). 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 →