Detect eyes with the bundled Haar cascade.
AI agents call detect_eyes to retrieve information from farshid-mcp-imageProcessing without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a detection/analysis tool that reads image data and returns metadata (eye locations/coordinates). It has no side effects—it does not modify, delete, or execute arbitrary code. It retrieves and queries visual features from an image, consistent with the Read category. The severity is low because misuse would only result in incorrect eye detection outputs, with no destructive or financial impact.
From the tool's definition Tool name 'detect_eyes' with description 'Detect eyes with the bundled Haar cascade' performs computer vision analysis on images using a pre-trained cascade classifier. No image modification, deletion, or external state changes occur.
Attacks that exploit this kind of access
Detect eyes with the bundled Haar cascade. It is categorised as a Read tool in the farshid-mcp-imageProcessing MCP Server, which means it retrieves data without modifying state.
Register the farshid-mcp-imageProcessing MCP server in PolicyLayer and add a rule for detect_eyes: 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 farshid-mcp-imageProcessing. Nothing to install.
detect_eyes 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 detect_eyes 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 detect_eyes. 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.
detect_eyes is provided by the farshid-mcp-imageProcessing MCP server (pirahansiah/farshid-mcp-imageprocessing). 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 →