Start or switch screen capture to a window or full screen. Captures are streamed through the Pipecat pipeline. Use list_windows() to find available window IDs. Args: window_id: Window ID to capture (from list_windows()). If not provided, captures the full screen. Returns the window ID if the wind...
AI agents invoke screen_capture to trigger actions in Pipecat MCP Server. 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.
This tool initiates or switches an ongoing screen capture stream, which is an external operation with side effects (streaming screen content through a pipeline). It's not a simple read/query but an action that starts or changes a continuous capture process. Misuse could expose sensitive screen content to unauthorized parties, making it medium severity.
From the tool's definition 'Start or switch screen capture to a window or full screen. Captures are streamed through the Pipecat pipeline.'
Documented attack patterns abuse exactly the kind of access screen_capture gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pipecat MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for screen_capture:
{
"version": "1",
"default": "deny",
"tools": {
"screen_capture": {
"limits": [
{
"counter": "screen_capture_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}screen_capture 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.
Start or switch screen capture to a window or full screen. Captures are streamed through the Pipecat pipeline. Use list_windows() to find available window IDs. Args: window_id: Window ID to capture (from list_windows()). If not provided, captures the full screen. Returns the window ID if the window was found, or None if it was not found or capturing full screen. It is categorised as a Execute tool in the Pipecat MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pipecat MCP Server MCP server in PolicyLayer and add a rule for screen_capture: 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 Pipecat MCP Server. Nothing to install.
screen_capture 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 screen_capture 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 screen_capture. 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.
screen_capture is provided by the Pipecat MCP Server MCP server (pipecat-ai/pipecat-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 7 Pipecat MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
7 Pipecat MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.