复制输入图像的内容并覆盖当前图像的指定位置。 若输入图像的尺寸过大或超出当前图像的范围，多余部分将被忽略。 返回结构是一个序列化的JSON字符串，包含以下字段： ResultImg: 复制输入图像的内容并覆盖当前图像的结果 Copy the input image content and overlay it to the specified position of the current image. If the input image is bigger or outside with the given x/y offset, the redundant part will be...
AI agents use image_copy_from to create or update resources in Leaper Vision Toolkit — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Leaper Vision Toolkit environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
panX | integer | — | x 方向的平移量 |
panY | integer | — | y 方向的平移量 |
imageUrl | string | — | 当前图像的url地址，通过这个地址获取到输入图像 |
regionJson | string | — | 指定的Roi区域。如果用户没有指定区域，请直接传入 "null"。 如果用户指定区域，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件名称)。这两个属性的值可以从前处理的MCP工具的返回值中获取。LpvCl |
inputImageUrl | string | — | 输入图像的url地址，通过这个地址获取到输入图像 |
Parameters from the server's own tool schema.
This tool creates or modifies image data in a reversible manner. The operation overlays one image onto another at a specified position, which is a modification (Write) rather than deletion. The change is reversible since the original images remain and the operation can be undone by re-processing. It does not permanently destroy data, execute arbitrary code, or create financial obligations.
From the tool's definition Tool name 'image_copy_from' and description states it will 'copy the input image content and overlay it to the specified position of the current image' and '覆盖当前图像' (overwrite current image).
Attacks that exploit this kind of access
复制输入图像的内容并覆盖当前图像的指定位置。 若输入图像的尺寸过大或超出当前图像的范围，多余部分将被忽略。 返回结构是一个序列化的JSON字符串，包含以下字段： ResultImg: 复制输入图像的内容并覆盖当前图像的结果 Copy the input image content and overlay it to the specified position of the current image. If the input image is bigger or outside with the given x/y offset, the redundant part will be ignored. Returns a serialized JSON string containing the following fields: ResultImg: The result of copying input image content and overlaying it to the current image. It is categorised as a Write tool in the Leaper Vision Toolkit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
image_copy_from accepts 5 parameters: panX, panY, imageUrl, regionJson, inputImageUrl. The full parameter table on this page comes from the server's own tool schema.
Register the Leaper Vision Toolkit MCP server in PolicyLayer and add a rule for image_copy_from: 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.
image_copy_from is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the image_copy_from 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 image_copy_from. 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.
image_copy_from 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.
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 →