Open CleanShot
AI agents call cleanshot_capture_window to retrieve information from Cleanshot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the tool name 'cleanshot_capture_window', this likely captures a screenshot of a window, which is a read/query operation with no side effects. However, the description is uninformative ('Open CleanShot'), which reduces confidence. In context with sibling tools (capture_area, capture_fullscreen), this is almost certainly a screenshot/read operation.
From the tool's definition Tool name: cleanshot_capture_window; description only says 'Open CleanShot'
Documented attack patterns abuse exactly the kind of access cleanshot_capture_window gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cleanshot, and nothing reaches the server without passing your rules. This is the rule we recommend for cleanshot_capture_window:
{
"version": "1",
"default": "deny",
"tools": {
"cleanshot_capture_window": {}
}
}cleanshot_capture_window is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Open CleanShot. It is categorised as a Read tool in the Cleanshot MCP Server, which means it retrieves data without modifying state.
Register the Cleanshot MCP server in PolicyLayer and add a rule for cleanshot_capture_window: 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 Cleanshot. Nothing to install.
cleanshot_capture_window is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the cleanshot_capture_window 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 cleanshot_capture_window. 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.
cleanshot_capture_window is provided by the Cleanshot MCP server (jdorfman/cleanshot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Cleanshot, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
19 Cleanshot tools catalogued and risk-classified — across an index of 43,000+ MCP servers.