Detect full bodies with the bundled Haar cascade (low recall, demo only).
AI agents call detect_bodies 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 tool reads image data and applies a pre-trained cascade classifier to identify bodies within that image. It produces output (detections) as a side effect of analysis but does not create, modify, delete, or execute arbitrary code. The capability is bounded to image analysis, placing it firmly in the Read category.
From the tool's definition Tool is named "detect_bodies" and described as detecting full bodies using a Haar cascade for demo purposes.
Attacks that exploit this kind of access
Detect full bodies with the bundled Haar cascade (low recall, demo only). 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_bodies: 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_bodies 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_bodies 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_bodies. 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_bodies 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 →