Restore a project to a specified version from its local history. Use the historyId from openl_list_project_local_changes response. NOTE: Requires the project to be opened first; not available for repository
AI agents use restore_project_local_change to create or update resources in Openl — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Openl environment.
This tool modifies project state by restoring to a previous version from local history. It is a write operation because it changes the project's current state, but it remains reversible since other versions can be restored afterward. This differs from destructive operations (delete_project_file, delete_table) which permanently remove data.
From the tool's definition Tool description states 'Restore a project to a specified version from its local history', which modifies project state by reverting to a prior version. The action is reversible (can restore to another version), distinguishing it from destructive operations.
Attacks that exploit this kind of access
Restore a project to a specified version from its local history. Use the historyId from openl_list_project_local_changes response. NOTE: Requires the project to be opened first; not available for repository. It is categorised as a Write tool in the Openl MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Openl MCP server in PolicyLayer and add a rule for restore_project_local_change: 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 Openl. Nothing to install.
restore_project_local_change 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_project_local_change 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_project_local_change. 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_project_local_change is provided by the Openl MCP server (openl-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 →