AI agents use restore_pattern_version to create or update resources in Strudel — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Strudel environment.
This tool creates or updates data (the pattern state) by restoring from history. It is reversible because another restore or create operation can undo it, so it does not qualify as Destructive. The blast radius is medium: an agent could restore a pattern to an undesired version, disrupting a live coding session, but the change can be undone and does not affect external systems or financial operations.
From the tool's definition 'Restore a pattern to a previous version from history' — the tool modifies an existing pattern by reverting it to a prior state, which is a reversible write operation.
Attacks that exploit this kind of access
Restore a pattern to a previous version from history. It is categorised as a Write tool in the Strudel MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Strudel MCP server in PolicyLayer and add a rule for restore_pattern_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 Strudel. Nothing to install.
restore_pattern_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 restore_pattern_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 restore_pattern_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.
restore_pattern_version is provided by the Strudel MCP server (utenadev/strudel-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 →