start_screenshot_capture · Screen MCP: Risk & Policy

WHAT IT DOES

What start_screenshot_capture does on Screen MCP

AI agents invoke start_screenshot_capture to trigger actions in Screen MCP. 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.

WHY IT NEEDS A POLICY

Why start_screenshot_capture needs a policy

This tool actively captures the current screen state and stores it server-side, triggering an external operation (screen capture) with side effects (session creation). It goes beyond passive reading — it initiates a capture process and creates persistent session data. An AI misusing this could silently capture sensitive on-screen information, warranting medium severity.

From the tool's definition "Capture a screenshot and store it in a temporary server-side session"

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_screenshot_capture Rate-limited

start_screenshot_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "start_screenshot_capture": {
      "limits": [
        {
          "counter": "start_screenshot_capture_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Screen MCP, so you can run agents against it safely.

FAQ

Questions about start_screenshot_capture

What does the start_screenshot_capture tool do? +

Capture a screenshot and store it in a temporary server-side session. It is categorised as a Execute tool in the Screen MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_screenshot_capture? +

Register the Screen MCP server in PolicyLayer and add a rule for start_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 Screen MCP. Nothing to install.

What risk level is start_screenshot_capture? +

start_screenshot_capture is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit start_screenshot_capture? +

Yes. Add a rate_limit block to the start_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.

How do I block start_screenshot_capture completely? +

Set action: deny in the PolicyLayer policy for start_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.

What MCP server provides start_screenshot_capture? +

start_screenshot_capture is provided by the Screen MCP server (jeandelest/screen-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.