识别验证码文本内容
AI agents call ocr_recognize to retrieve information from ddddocr CAPTCHA Recognition MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though ocr_recognize only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
识别验证码文本内容. It is categorised as a Read tool in the ddddocr CAPTCHA Recognition MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ddddocr CAPTCHA Recognition MCP Server MCP server in PolicyLayer and add a rule for ocr_recognize: 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 ddddocr CAPTCHA Recognition MCP Server. Nothing to install.
ocr_recognize 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 ocr_recognize 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 ocr_recognize. 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.
ocr_recognize is provided by the ddddocr CAPTCHA Recognition MCP Server MCP server (ymeng98/ddddocr-captcha-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.