save_screenshot_to_host_workspace
AI agents use save_screenshot_to_host_workspace to create or update resources in Screenshot MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Screenshot MCP Server environment.
This tool creates or writes screenshot files to specified locations on the host system. While not destructive (files can be overwritten or deleted), it modifies the filesystem by creating new files, which qualifies as Write.
From the tool's definition Tool name 'save_screenshot_to_host_workspace' indicates writing/saving files to a host workspace location. Server description mentions 'saves them to file paths specified by client applications.' Tool description is empty, limiting full certainty.
Attacks that exploit this kind of access
save_screenshot_to_host_workspace. It is categorised as a Write tool in the Screenshot MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Screenshot MCP Server MCP server in PolicyLayer and add a rule for save_screenshot_to_host_workspace: 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 Screenshot MCP Server. Nothing to install.
save_screenshot_to_host_workspace 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 save_screenshot_to_host_workspace 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 save_screenshot_to_host_workspace. 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.
save_screenshot_to_host_workspace is provided by the Screenshot MCP Server MCP server (kunihiros/screenshot-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 →