screenshot_capture
Captures a single frame of a display, window, or region to a PNG. Requires Screen Recording permission; without it returns an explicit permission_required, never a blank image.
This record as markdown: /tools/com-local-mcp-local-mcp/screenshot-capture.md
What screenshot_capture does on Local
AI agents call screenshot_capture to retrieve information from Local without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
target | object | Yes | |
output_path | string | — | Where to write the PNG (default: temp file). |
Parameters from the server's own tool schema.
Why screenshot_capture is rated Low
This tool reads visual data from the screen and saves it as an image file. It is a read/capture operation with no side effects on external systems. However, the blast radius is medium because it can capture sensitive on-screen content (passwords, private messages, confidential documents) visible at the time of capture, making it a privacy risk if misused by an AI agent.
From the tool's definition Captures a single frame of a display, window, or region to a PNG
Attacks that exploit this kind of access
The rule that runs screenshot_capture safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Local, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For screenshot_capture, this is the rule to start with:
screenshot_capture is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Local, apply this rule, and every screenshot_capture call is checked against it from then on.
Questions about screenshot_capture
Captures a single frame of a display, window, or region to a PNG. Requires Screen Recording permission; without it returns an explicit permission_required, never a blank image. It is categorised as a Read tool in the Local MCP Server, which means it retrieves data without modifying state.
screenshot_capture accepts 2 parameters: target, output_path. Required: target. The full parameter table on this page comes from the server's own tool schema.
Register the Local MCP server in PolicyLayer and add a rule for screenshot_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 Local. Nothing to install.
screenshot_capture 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 screenshot_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 screenshot_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.
screenshot_capture is provided by the Local MCP server (local-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Local, and thousands of servers like it.
This server
Across the catalogue