Return shape, dtype, channel count, file size, and basic stats.
AI agents call image_info 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 only queries and returns information about an image without creating, modifying, deleting, executing code, or triggering side effects. It is a straightforward read operation similar to a file stat or metadata lookup.
From the tool's definition Tool returns metadata (shape, dtype, channel count, file size, basic stats) with no modification or execution of external operations—pure data retrieval and analysis.
Attacks that exploit this kind of access
Return shape, dtype, channel count, file size, and basic stats. 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 image_info: 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.
image_info 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 image_info 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 image_info. 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.
image_info 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 →