Apply Gaussian blur. ksize is forced to odd.
AI agents use blur_gaussian to create or update resources in farshid-mcp-imageProcessing — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your farshid-mcp-imageProcessing environment.
This tool modifies image data by applying a Gaussian blur filter. It creates a transformed version of the image, which is a reversible write/modification operation. It does not delete data, execute arbitrary code, or involve financial transactions. Severity is low as it only affects image processing outputs.
From the tool's definition Apply Gaussian blur. ksize is forced to odd.
Attacks that exploit this kind of access
Apply Gaussian blur. ksize is forced to odd. It is categorised as a Write tool in the farshid-mcp-imageProcessing MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the farshid-mcp-imageProcessing MCP server in PolicyLayer and add a rule for blur_gaussian: 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.
blur_gaussian is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the blur_gaussian 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 blur_gaussian. 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.
blur_gaussian 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 →