image_compare_compare_symmetric · Leaper Vision Toolkit MCP

Q: What does the image_compare_compare_symmetric tool do?

比较输入图像中的两个对称区域，生成差异图和蒙版图。 返回结构是一个序列化的json，其中： DiffResultImg属性是差异图像URL地址， MaskResultImg属性是差异蒙版图像URL地址. It is categorised as a Read tool in the Leaper Vision Toolkit MCP Server, which means it retrieves data without modifying state.

WHAT IT DOES

What image_compare_compare_symmetric does on Leaper Vision Toolkit

AI agents call image_compare_compare_symmetric to retrieve information from Leaper Vision Toolkit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

PARAMETERS

Parameter	Type	Required	Description
`x1`	integer	—	对称轴，用于定义两个对称区域的对称轴
`x2`	integer	—	对称轴，用于定义两个对称区域的对称轴
`y1`	integer	—	对称轴，用于定义两个对称区域的对称轴
`y2`	integer	—	对称轴，用于定义两个对称区域的对称轴
`imageUrl`	string	—	图片的url地址，通过这个地址获取到输入图像
`regionClassObjDescriptionJson`	string	—	原始的Roi区域。在调用此工具前要保证前处理中一定要有且仅有一次的 Region 初始化工具调用，可用的初始化工具有：ILAnnulusRegion (圆环区域对象)、ILAnnulusSectorRegion(环状扇形区域对象)、ILCircleRegion (圆形区域对象)、ILCompoundRegion (复合
`imageCompareClassObjDescriptionJson`	string	—	用于图像比较功能调用的对象。在调用此工具前要保证前处理中一定要有且仅有一次的 ImageCompareNew 初始化工具调用。如果用户指定图像比较功能相关对象，传入一个序列化的JSON字符串，属性包括：LpvClassName(调用工具函数的名称) 和 InputParameterFile(调用工具函数需要传入的参数文

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why image_compare_compare_symmetric needs a policy

This tool performs image comparison and analysis, returning URLs to generated difference and mask images. It reads/analyzes input images and produces output image URLs — no data is deleted, financial transactions are made, or external systems are modified. The generated images are returned as URLs (likely ephemeral/temporary), making this primarily a Read/analysis operation.

From the tool's definition 比较输入图像中的两个对称区域，生成差异图和蒙版图 (Compare two symmetric regions in input images, generate difference map and mask map)

Attacks that exploit this kind of access

Questions about image_compare_compare_symmetric

What does the image_compare_compare_symmetric tool do? +

比较输入图像中的两个对称区域，生成差异图和蒙版图。返回结构是一个序列化的json，其中： DiffResultImg属性是差异图像URL地址， MaskResultImg属性是差异蒙版图像URL地址. It is categorised as a Read tool in the Leaper Vision Toolkit MCP Server, which means it retrieves data without modifying state.

What parameters does image_compare_compare_symmetric accept? +

image_compare_compare_symmetric accepts 7 parameters: x1, x2, y1, y2, imageUrl, regionClassObjDescriptionJson, imageCompareClassObjDescriptionJson. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on image_compare_compare_symmetric? +

Register the Leaper Vision Toolkit MCP server in PolicyLayer and add a rule for image_compare_compare_symmetric: 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 Leaper Vision Toolkit. Nothing to install.

What risk level is image_compare_compare_symmetric? +

image_compare_compare_symmetric is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit image_compare_compare_symmetric? +

Yes. Add a rate_limit block to the image_compare_compare_symmetric 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.

How do I block image_compare_compare_symmetric completely? +

Set action: deny in the PolicyLayer policy for image_compare_compare_symmetric. 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.

What MCP server provides image_compare_compare_symmetric? +

image_compare_compare_symmetric is provided by the Leaper Vision Toolkit MCP server (leaper-mcp/leaper-mcp-proxy). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.