Get image information
AI agents call get_image to retrieve information from NapCat MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves or queries image data without altering, deleting, or executing operations. It fits the Read category as it only fetches information. Severity is low because image metadata retrieval poses minimal risk even if misused by an agent. Confidence is high given the clear retrieval semantics in both name and description.
From the tool's definition Tool name is 'get_image' and description states 'Get image information' - this is a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get image information. It is categorised as a Read tool in the NapCat MCP Server MCP Server, which means it retrieves data without modifying state.
Register the NapCat MCP Server MCP server in PolicyLayer and add a rule for get_image: 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 NapCat MCP Server. Nothing to install.
get_image 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 get_image 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 get_image. 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.
get_image is provided by the NapCat MCP Server MCP server (1021143806/napcat_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
get_image is one line of NapCat MCP Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →