vision_crop_verify
AI agents call vision_crop_verify to retrieve information from Local Mmcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Given the empty description, classification relies on the tool name and context within a vision processing suite. The name pattern (vision_*) combined with 'verify' suggests a read-only operation similar to sibling tools like 'vision_inspect' and 'vision_diff', which are typically non-destructive analysis operations. No evidence of side effects, data modification, deletion, code execution, or financial impact.
From the tool's definition Tool name 'vision_crop_verify' suggests inspection or verification of image crops with no indication of modification, deletion, or execution. The 'verify' prefix implies inspection/comparison rather than action.
Attacks that exploit this kind of access
vision_crop_verify. It is categorised as a Read tool in the Local Mmcp MCP Server, which means it retrieves data without modifying state.
Register the Local M MCP server in PolicyLayer and add a rule for vision_crop_verify: 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 Local Mmcp. Nothing to install.
vision_crop_verify 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 vision_crop_verify 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 vision_crop_verify. 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.
vision_crop_verify is provided by the Local M MCP server (rorojiao/local-mmcp). 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 →