Delete all captured PyMOL screenshots.
AI agents call clear_screenshots to permanently remove resources in PyMOL-MCP-Vis — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes all screenshots from the system with no undo mechanism. While screenshots are typically lower-criticality data compared to experimental results or configuration files, the irreversible nature of deletion and the potential loss of visual documentation of important molecular analyses classifies this as Destructive.
From the tool's definition Tool name: 'clear_screenshots'. Description: 'Delete all captured PyMOL screenshots.' The verb 'Delete' combined with 'all' indicates irreversible removal of data without recovery options.
Attacks that exploit this kind of access
Delete all captured PyMOL screenshots. It is categorised as a Destructive tool in the PyMOL-MCP-Vis MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the PyMOL-MCP-Vis MCP server in PolicyLayer and add a rule for clear_screenshots: 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 PyMOL-MCP-Vis. Nothing to install.
clear_screenshots is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the clear_screenshots 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 clear_screenshots. 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.
clear_screenshots is provided by the PyMOL-MCP-Vis MCP server (ryannmperez/pymol-mcp-vis). 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 →