这个是归一化输入图像，以当前图像的均值和标准差计算感兴趣的数值范围，拉伸到目标数值范围的工具。不改变图像位深，归一化后的结果图像与输入位深相同、通道数相同。对于彩色的多通道图像，输出也是彩色多通道图像，每个通道分别独立进行归一化。 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： ResultImg属性是输出结果图像URL地址。 belowMask属性是入图图像中超出感兴趣数值范围的像素的蒙版地址。白色像素表示这些位置的数值小于 fromMinValue 或者大于 fromMaxValue 。可基于该蒙版，将这些位置的数值设置为...
AI agents invoke il_image_op_normalize_mean_std_dev 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
k1 | number | — | 计算数值下限时使用的标准差系数，传入类型为double类型。 |
k2 | number | — | 计算数值上限时使用的标准差系数，负数表示使用与 k1 相同的系数，传入类型为double类型。 |
imageUrl | string | — | 图片的url地址，通过这个地址获取到图片 |
toMaxValue | number | — | 指定目标的数值范围，传入类型为double类型。表示使用图像位深的理论数值范围的最大值，对于 8 位图使用 0 ~ 255，对于 16 位图使用 0 ~ 65535 |
toMinValue | number | — | 指定目标的数值范围，传入类型为double类型。表示使用图像位深的理论数值范围的最小值，对于 8 位图使用 0 ~ 255，对于 16 位图使用 0 ~ 65535 |
Parameters from the server's own tool schema.
This tool executes an image processing operation (normalization by mean and standard deviation) on an input image and produces output image URLs. It is not a simple read/query, nor does it delete data. It performs a transformation computation that produces new artifacts, placing it in the Execute category. Severity is medium as misuse could produce incorrect image outputs used in downstream vision applications.
From the tool's definition 归一化输入图像，以当前图像的均值和标准差计算感兴趣的数值范围，拉伸到目标数值范围 — performs an image normalization transformation operation and returns processed image URLs
Attacks that exploit this kind of access
这个是归一化输入图像，以当前图像的均值和标准差计算感兴趣的数值范围，拉伸到目标数值范围的工具。不改变图像位深，归一化后的结果图像与输入位深相同、通道数相同。对于彩色的多通道图像，输出也是彩色多通道图像，每个通道分别独立进行归一化。 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： ResultImg属性是输出结果图像URL地址。 belowMask属性是入图图像中超出感兴趣数值范围的像素的蒙版地址。白色像素表示这些位置的数值小于 fromMinValue 或者大于 fromMaxValue 。可基于该蒙版，将这些位置的数值设置为统一个黑色或目标的最小最大值，或调用 FillHole() 进行修补。 aboveMask属性是入图图像中超出感兴趣数值范围的像素的蒙版地址。白色像素表示这些位置的数值小于 fromMinValue 或者大于 fromMaxValue 。可基于该蒙版，将这些位置的数值设置为统一个黑色或目标的最小最大值，或调用 FillHole() 进行修补。. 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.
il_image_op_normalize_mean_std_dev accepts 5 parameters: k1, k2, imageUrl, toMaxValue, toMinValue. 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 il_image_op_normalize_mean_std_dev: 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.
il_image_op_normalize_mean_std_dev is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the il_image_op_normalize_mean_std_dev 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 il_image_op_normalize_mean_std_dev. 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.
il_image_op_normalize_mean_std_dev 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 →