Close a project. If the project has unsaved changes (status EDITING), you must either save (saveChanges: true with comment) or discard (discardChanges: true). When discarding, ask the user for confirmation and then call again with confirmDiscard: true. Prevents accidental data loss.
AI agents use close_project 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 closing it and potentially discarding unsaved work. Although discarding changes is somewhat destructive, the explicit confirmation requirement and the ability to save changes first (saveChanges: true) mean the primary action is Write (state modification) rather than Destructive. The confirmation safeguard and reversibility through saving place this in Write rather than Destructive.
From the tool's definition The tool closes a project and can discard unsaved changes. The description states 'discardChanges: true' which modifies the project state by removing edits.
Attacks that exploit this kind of access
Close a project. If the project has unsaved changes (status EDITING), you must either save (saveChanges: true with comment) or discard (discardChanges: true). When discarding, ask the user for confirmation and then call again with confirmDiscard: true. Prevents accidental data loss. 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 close_project: 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.
close_project 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 close_project 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 close_project. 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.
close_project 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 →