Low Risk

capture_screenshot

截取屏幕并保存为文件

How to control capture_screenshot ↓

What capture_screenshot does on PC-MCP

AI agents call capture_screenshot to retrieve information from PC-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why capture_screenshot needs a policy

This tool captures a screenshot and saves it to a file. It reads the current screen state (Read), but saving to a file is a minor Write side effect. However, the primary concern is privacy — it can capture sensitive on-screen information visible to the agent. The most accurate category is Read since it retrieves visual data from the screen.

From the tool's definition 截取屏幕并保存为文件 (Capture screen and save as file)

Documented attack patterns abuse exactly the kind of access capture_screenshot gives an agent:

How to control capture_screenshot

PolicyLayer is an MCP gateway — it sits between your AI agents and PC-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for capture_screenshot:

policy.json
{
  "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.

  1. Create a free account and register PC-MCP — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about capture_screenshot

What does the capture_screenshot tool do? +

截取屏幕并保存为文件. It is categorised as a Read tool in the PC-MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on capture_screenshot? +

Register the PC- 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 PC-MCP. Nothing to install.

What risk level is capture_screenshot? +

capture_screenshot is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit capture_screenshot? +

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.

How do I block capture_screenshot completely? +

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.

What MCP server provides capture_screenshot? +

capture_screenshot is provided by the PC- MCP server (shijianzhong/mcp-server-for-pc). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every PC-MCP tool call.

Start from PC-MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

6 PC-MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.