Open CleanShot
AI agents invoke cleanshot_record_screen to trigger actions in Cleanshot. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Screen recording triggers an external operation (capturing video of the screen) which has side effects beyond simple data retrieval. The description 'Open CleanShot' is uninformative, but the tool name and server context strongly imply it starts a screen recording session. This is an Execute-category action as it triggers an ongoing external operation.
From the tool's definition Tool name 'cleanshot_record_screen' and server description mentions 'recordings' — initiates screen recording via CleanShot X
Documented attack patterns abuse exactly the kind of access cleanshot_record_screen 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_record_screen:
{
"version": "1",
"default": "deny",
"tools": {
"cleanshot_record_screen": {
"limits": [
{
"counter": "cleanshot_record_screen_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}cleanshot_record_screen stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Open CleanShot. It is categorised as a Execute tool in the Cleanshot MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cleanshot MCP server in PolicyLayer and add a rule for cleanshot_record_screen: 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_record_screen is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the cleanshot_record_screen 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_record_screen. 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_record_screen 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.