AI agents use html_restore 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.
The tool performs a copy/restore operation that creates new data based on old versions. This is a Write operation (creates/modifies data reversibly) rather than Destructive because the action is reversible—the new version can be edited or deleted.
From the tool's definition Tool name 'html_restore' and description 'Restore an old HTML version by copying it forward as a new' indicates the tool creates a new copy of a previous HTML version, which is a reversible modification operation.
Attacks that exploit this kind of access
Restore an old HTML version by copying it forward as a new. 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 html_restore: 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.
html_restore 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 html_restore 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 html_restore. 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.
html_restore 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 →