AI agents use brief_restore_version to create or update resources in Llama — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Llama environment.
This tool modifies existing data by reverting brief blocks to previous versions. While it restores rather than deletes, it still constitutes a write operation that changes the current state of the data. It is reversible (the current state can be restored in turn), so it does not qualify as Destructive.
From the tool's definition Tool description states 'Restore a brief block to a specific historical version', which is a modification operation that reverts data to a previous state. The tool name contains 'restore', indicating a write-type action on existing data.
Attacks that exploit this kind of access
Restore a brief block to a specific historical version (find historyId via brief_history). It is categorised as a Write tool in the Llama MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Llama MCP server in PolicyLayer and add a rule for brief_restore_version: 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 Llama. Nothing to install.
brief_restore_version is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the brief_restore_version 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 brief_restore_version. 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.
brief_restore_version is provided by the Llama MCP server (llama-ventures/llama-cli). 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 →