AI agents call read_clipboard_image to retrieve information from Qsw without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs optical character recognition on clipboard images to extract text content. It is a read-only operation that retrieves and processes existing data without any side effects, state changes, or capability to execute code or modify systems. No destructive, financial, or executable actions are possible.
From the tool's definition Tool name 'read_clipboard_image' and description '从系统剪贴板读取图片并识别文字（OCR），支持中英文等多种语言' (reads images from system clipboard and performs OCR/text recognition) indicates pure data retrieval with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
从系统剪贴板读取图片并识别文字（OCR），支持中英文等多种语言. It is categorised as a Read tool in the Qsw MCP Server, which means it retrieves data without modifying state.
Register the Qsw MCP server in PolicyLayer and add a rule for read_clipboard_image: 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 Qsw. Nothing to install.
read_clipboard_image is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the read_clipboard_image 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.
Set action: deny in the PolicyLayer policy for read_clipboard_image. 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.
read_clipboard_image is provided by the Qsw MCP server (qinouz/qsw-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →