find_similar_in_folder
AI agents call find_similar_in_folder to retrieve information from Imagefeatures without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to query/retrieve images matching similarity criteria from a folder. The lack of mutation language ('create', 'delete', 'update', 'execute') and the consistent read-only nature of sibling tools indicate this performs analysis and returns results. The confidence is slightly reduced due to empty description, but the context is clear enough to categorize as Read with high confidence.
From the tool's definition Tool name 'find_similar_in_folder' indicates a search/query operation that retrieves similar images from a directory.
Attacks that exploit this kind of access
find_similar_in_folder. It is categorised as a Read tool in the Imagefeatures MCP Server, which means it retrieves data without modifying state.
Register the Imagefeatures MCP server in PolicyLayer and add a rule for find_similar_in_folder: 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 Imagefeatures. Nothing to install.
find_similar_in_folder 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 find_similar_in_folder 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 find_similar_in_folder. 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.
find_similar_in_folder is provided by the Imagefeatures MCP server (kelkalot/imagefeatures-mcp). 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 →