collect_images · Claude Stats MCP: Risk & Policy

WHAT IT DOES

What collect_images does on Claude Stats MCP

AI agents invoke collect_images to trigger actions in Claude Stats 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 collect_images needs a policy

This tool opens a browser, navigates to a specified URL, extracts all image links, and downloads files to the local desktop. It triggers external browser operations and writes arbitrary files from the internet to the local filesystem, constituting an Execute-level action with high severity due to the risk of downloading malicious content and writing files to the user's system without fine-grained control.

From the tool's definition 采集指定网页上的所有 jpg/png 图片并保存到桌面。打开浏览器访问网页，提取所有图片链接，下载到本地。

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

collect_images Rate-limited

collect_images 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": {
    "collect_images": {
      "limits": [
        {
          "counter": "collect_images_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 Claude Stats MCP, so you can run agents against it safely.

FAQ

Questions about collect_images

What does the collect_images tool do? +

采集指定网页上的所有 jpg/png 图片并保存到桌面。打开浏览器访问网页，提取所有图片链接，下载到本地。. It is categorised as a Execute tool in the Claude Stats 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 collect_images? +

Register the Claude Stats MCP server in PolicyLayer and add a rule for collect_images: 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 Claude Stats MCP. Nothing to install.

What risk level is collect_images? +

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

Can I rate-limit collect_images? +

Yes. Add a rate_limit block to the collect_images 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 collect_images completely? +

Set action: deny in the PolicyLayer policy for collect_images. 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 collect_images? +

collect_images is provided by the Claude Stats MCP server (upjiang/ai-mcp-study). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.