Sobel gradient magnitude.
AI agents call edges_sobel 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 pure computational filter that reads an image and outputs gradient data. It retrieves/analyzes image features with no ability to delete, modify, execute code, move money, or trigger external side effects. Consistent with sibling tools (blur_*, denoise, detect_*) which are all image read/analysis operations. Severity is low because misuse poses minimal risk—at worst, it produces uninformative edge maps.
From the tool's definition edges_sobel computes Sobel gradient magnitude, a standard image analysis operation that detects edges without modifying input data. No side effects, no state changes, no external operations triggered.
Attacks that exploit this kind of access
Sobel gradient magnitude. 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 edges_sobel: 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.
edges_sobel 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 edges_sobel 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 edges_sobel. 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.
edges_sobel 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 →