Shi-Tomasi good-features-to-track corner detection.
AI agents call detect_corners 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 computer vision detection function that analyzes an image to identify corner features using the Shi-Tomasi algorithm. Like the sibling tools 'detect_faces', 'detect_eyes', and 'detect_bodies', it performs feature extraction and returns results. There are no side effects, no data modification, no arbitrary code execution, and no destructive operations.
From the tool's definition Tool name 'detect_corners' and description 'Shi-Tomasi good-features-to-track corner detection' indicate image analysis that retrieves/identifies features without modifying data or executing arbitrary code.
Attacks that exploit this kind of access
Shi-Tomasi good-features-to-track corner detection. 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_corners: 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_corners 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_corners 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_corners. 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_corners 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 →