screenshot_chat

THE RISK

Low Risk

Why screenshot_chat needs a policy

The tool name suggests it may capture a screenshot of a chat, which would typically be a Read operation. However, with no description available, the exact behavior is unknown. Given the server context (QQ messaging), it likely reads/captures chat content, but confidence is low due to missing description. Severity is medium because screenshots could capture sensitive conversation data.

From the tool's definition Tool name is 'screenshot_chat'; description is empty or uninformative.

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

POLICY

How to control screenshot_chat

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "screenshot_chat": {
      "limits": [
        {
          "counter": "screenshot_chat_rate",
          "window": "minute",
          "max": 60,
          "scope": "grant"
        }
      ]
    }
  }
}

screenshot_chat gets a rate cap, and everything else on the server is denied unless you say otherwise.

Create a free account and register Amadeus-QQ-MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

SET A RULE FOR THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Amadeus-QQ-MCP tools

Write send_image send_image Write send_message send_message Write send_voice send_voice Read batch_get_recent_context batch_get_recent_context Read check_status Check QQ login status and NapCat connection status. Other compress_context compress_context Read get_friend_list Get the list of QQ friends. Read get_group_list Get the list of QQ groups the bot has joined.

All 10 Amadeus-QQ-MCP tools →

Other tools on other servers

Android Forensics ADB MCP Server generate_app_analysis_report Ethereum Tools add Math MCP Server complex_analysis_suite Crypto_MCP aes_encrypt

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Tool risk categories → How PolicyLayer classifies MCP tools by what they can do.
MCP tool → What an MCP tool is and how clients discover and call it.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about screenshot_chat

What does the screenshot_chat tool do? +

screenshot_chat. It is categorised as a Other tool in the Amadeus-QQ-MCP MCP Server, which means it performs auxiliary operations.

How do I enforce a policy on screenshot_chat? +

Register the Amadeus-QQ- MCP server in PolicyLayer and add a rule for screenshot_chat: 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 Amadeus-QQ-MCP. Nothing to install.

What risk level is screenshot_chat? +

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

Can I rate-limit screenshot_chat? +

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

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

screenshot_chat is provided by the Amadeus-QQ- MCP server (julesliu390/amadeus-qq-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Amadeus-QQ-MCP tool call.

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

CHECK YOUR STACK →