使用华为云 OCR 服务识别图片中的文字内容。
AI agents call recognize_web_image to retrieve information from XMZ MCP Server 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 (OCR) on images to extract and return text content. This is fundamentally a read operation—it retrieves information from an image without side effects, modifications, or destructive actions.
From the tool's definition The tool description states it uses Huawei Cloud OCR service to 'recognize text content in images' (识别图片中的文字内容). OCR is a text extraction/recognition operation that retrieves data from images without modifying or deleting anything.
Attacks that exploit this kind of access
使用华为云 OCR 服务识别图片中的文字内容。. It is categorised as a Read tool in the XMZ MCP Server MCP Server, which means it retrieves data without modifying state.
Register the XMZ MCP Server MCP server in PolicyLayer and add a rule for recognize_web_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 XMZ MCP Server. Nothing to install.
recognize_web_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 recognize_web_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 recognize_web_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.
recognize_web_image is provided by the XMZ MCP Server MCP server (xiaomizhoubaobei/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 →