capture_screen · MCP ScreenCatch MCP: Risk & Policy

WHAT IT DOES

What capture_screen does on MCP ScreenCatch

AI agents use capture_screen to create or update resources in MCP ScreenCatch — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP ScreenCatch environment.

WHY IT NEEDS A POLICY

Why capture_screen needs a policy

This tool captures a screenshot and writes/saves the resulting image file to disk. It creates new files (timestamped images) in a directory, which is a Write operation. It is marked LEGACY and the description is truncated/uninformative beyond that, slightly lowering confidence.

From the tool's definition 'screen capture' and 'automatically saving timestamped images to a configurable directory'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

capture_screen Rate-limited

capture_screen stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "capture_screen": {
      "limits": [
        {
          "counter": "capture_screen_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about capture_screen

What does the capture_screen tool do? +

LEGACY: Single-region screen capture. Use. It is categorised as a Write tool in the MCP ScreenCatch MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on capture_screen? +

Register the MCP ScreenCatch MCP server in PolicyLayer and add a rule for capture_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 MCP ScreenCatch. Nothing to install.

What risk level is capture_screen? +

capture_screen is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit capture_screen? +

Yes. Add a rate_limit block to the capture_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.

How do I block capture_screen completely? +

Set action: deny in the PolicyLayer policy for capture_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.

What MCP server provides capture_screen? +

capture_screen is provided by the MCP ScreenCatch MCP server (johnelamont/mcp-screencatch). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.