Take a look at what's on screen. Use this when the user asks what you can see. Screen capture must already be started via screen_capture(). Returns the absolute path to the saved image file.
AI agents call capture_screenshot to retrieve information from Pipecat MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool captures and returns a screenshot—a read-only operation that retrieves visual information from the screen without modifying, executing code, deleting data, or moving money. While screenshot data could be sensitive (containing passwords, personal information, etc.), the tool itself performs only information retrieval.
From the tool's definition Tool description states 'Take a look at what's on screen' and 'Returns the absolute path to the saved image file.' The language 'take a look' and retrieval of a file path indicate data retrieval with no side effects.
Documented attack patterns abuse exactly the kind of access capture_screenshot 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 capture_screenshot:
{
"version": "1",
"default": "deny",
"tools": {
"capture_screenshot": {}
}
}capture_screenshot 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.
Take a look at what's on screen. Use this when the user asks what you can see. Screen capture must already be started via screen_capture(). Returns the absolute path to the saved image file. It is categorised as a Read tool in the Pipecat MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Pipecat MCP Server MCP server in PolicyLayer and add a rule for capture_screenshot: 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.
capture_screenshot 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 capture_screenshot 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 capture_screenshot. 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.
capture_screenshot 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.