Detect faces with the bundled Haar cascade. Returns bounding boxes.
AI agents call detect_faces 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.
The detect_faces tool performs computer vision analysis to identify and locate faces in an image, returning bounding box coordinates. This is purely observational with no side effects: it does not modify the image, delete data, execute arbitrary code, or trigger external operations. It aligns with the Read category as a query/detection operation.
From the tool's definition Tool description states it 'Detect faces with the bundled Haar cascade. Returns bounding boxes.' — a read-only operation that analyzes an image and returns detection results without modifying data or executing external code.
Attacks that exploit this kind of access
Detect faces with the bundled Haar cascade. Returns bounding boxes. 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_faces: 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_faces 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_faces 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_faces. 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_faces 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 →