Configure screenshot auto-cleanup threshold.
AI agents use configure_screenshots to create or update resources in PyMOL-MCP-Vis — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your PyMOL-MCP-Vis environment.
This tool writes to configuration state by adjusting when screenshots are automatically cleaned up. It is reversible (the threshold can be changed again) and has no destructive or side-effect-dependent execution characteristics. It does not read external data (Read), execute arbitrary code (Execute), irreversibly delete data (Destructive), or move money (Financial).
From the tool's definition Tool modifies screenshot auto-cleanup threshold, which is a configuration setting (reversible write operation). The description states 'Configure screenshot auto-cleanup threshold' - a clear modification of settings.
Attacks that exploit this kind of access
Configure screenshot auto-cleanup threshold. It is categorised as a Write tool in the PyMOL-MCP-Vis MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the PyMOL-MCP-Vis MCP server in PolicyLayer and add a rule for configure_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.
configure_screenshots 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 configure_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 configure_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.
configure_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 →