AI agents call media_read_text_ocr to retrieve information from Browser-Debugger without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
OCR text extraction retrieves visible text from screenshots or media without side effects, placing it in the Read category. Severity is medium because OCR on browser content could expose sensitive information (credentials, personal data, confidential documents) displayed on screen, even though the tool itself performs no destructive or write operations.
From the tool's definition Tool name 'media_read_text_ocr' indicates OCR (Optical Character Recognition) text extraction from media. Server description confirms 'OCR text extraction' as a capability. The 'read' verb and OCR purpose indicate data retrieval without modification.
Documented attack patterns abuse exactly the kind of access media_read_text_ocr gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Browser-Debugger, and nothing reaches the server without passing your rules. This is the rule we recommend for media_read_text_ocr:
{
"version": "1",
"default": "deny",
"tools": {
"media_read_text_ocr": {}
}
}media_read_text_ocr is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
media_read_text_ocr. It is categorised as a Read tool in the Browser-Debugger MCP Server, which means it retrieves data without modifying state.
Register the Browser-Debugger MCP server in PolicyLayer and add a rule for media_read_text_ocr: 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 Browser-Debugger. Nothing to install.
media_read_text_ocr 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 media_read_text_ocr 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 media_read_text_ocr. 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.
media_read_text_ocr is provided by the Browser-Debugger MCP server (selvadinesh-giga/mcp-based-browser-debug-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Browser-Debugger, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
14 Browser-Debugger tools catalogued and risk-classified — across an index of 43,000+ MCP servers.