il_image_op_split · Leaper Vision Toolkit MCP: Risk & Policy

Q: What does the il_image_op_split tool do?

这个是按网格拆分一个图像的工具。为若干个小图 。 工具不需要通过其它工具设置参数，不需要传入ILImageOp的对象。 返回结构是一个序列化的json，其中： ResultImgList属性是输出结果图像URL地址列表。. It is categorised as a Execute tool in the Leaper Vision Toolkit MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

WHAT IT DOES

What il_image_op_split does on Leaper Vision Toolkit

AI agents invoke il_image_op_split to trigger actions in Leaper Vision Toolkit. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

PARAMETERS

Parameter	Type	Required	Description
`xStep`	integer	—	单次拆分的水平方向的步长，传入类型为int类型。对于非循环模式，其通常等于结果图像的宽和高。而对于循环模式，这表示每次拆分所收集的行列数，多次拆分组合为最终结果。
`yStep`	integer	—	单次拆分的垂直方向的步长，传入类型为int类型。
`xCount`	integer	—	指定水平方向的拆分数量，传入类型为int类型。
`xSpace`	integer	—	拆分的水平方向的间隔，传入类型为int类型。
`yCount`	integer	—	指定垂直方向的拆分数量，传入类型为int类型。
`ySpace`	integer	—	拆分的垂直方向的间隔，传入类型为int类型。
`imageUrl`	string	—	图片的url地址，通过这个地址获取到图片
`sameSize`	boolean	—	输出的结果图像图像队列，传入类型为bool类型。从上到下。
`cyclicMode`	boolean	—	是否启用循环拆分，传入类型为bool类型。默认启用。循环模型将循环重复拆分整张图像，再合并单次拆分的若干列为一张图像，作为最终结果。

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why il_image_op_split needs a policy

This tool performs an image transformation operation — splitting an image into multiple sub-images — and returns new image URLs. It goes beyond a simple read (it produces new artifacts), but is not purely a write to a store. It executes an image processing pipeline and generates output resources. Severity is medium as misuse could produce unintended outputs or consume resources, but blast radius is limited.

From the tool's definition 按网格拆分一个图像的工具。为若干个小图 (splits an image into a grid of smaller images); returns ResultImgList with output image URL list

Attacks that exploit this kind of access

Questions about il_image_op_split

What does the il_image_op_split tool do? +

这个是按网格拆分一个图像的工具。为若干个小图。工具不需要通过其它工具设置参数，不需要传入ILImageOp的对象。返回结构是一个序列化的json，其中： ResultImgList属性是输出结果图像URL地址列表。. It is categorised as a Execute tool in the Leaper Vision Toolkit MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does il_image_op_split accept? +

il_image_op_split accepts 9 parameters: xStep, yStep, xCount, xSpace, yCount, ySpace, imageUrl, sameSize, cyclicMode. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on il_image_op_split? +

Register the Leaper Vision Toolkit MCP server in PolicyLayer and add a rule for il_image_op_split: 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 il_image_op_split? +

il_image_op_split is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit il_image_op_split? +

Yes. Add a rate_limit block to the il_image_op_split 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 il_image_op_split completely? +

Set action: deny in the PolicyLayer policy for il_image_op_split. 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 il_image_op_split? +

il_image_op_split 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.