Count the pixels in the input image which is between or outside the given color bounds. For all of the channels, the pixel value is within the color bounds, then it's a "between" color pixel. Otherwise, for any of the channel, the pixel value is smaller or greater than the lower/upper bound, then...
AI agents call image_stats_count_pixel_color 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
lbRed | integer | — | 颜色范围下限，所有通道的数值需均小于或等于上限，红色通道值，范围0-255 |
ubRed | integer | — | 颜色范围上限，所有通道的数值需均大于或等于上限，红色通道值，范围0-255 |
lbBlue | integer | — | 颜色范围下限，所有通道的数值需均小于或等于上限，蓝色通道值，范围0-255 |
ubBlue | integer | — | 颜色范围上限，所有通道的数值需均大于或等于上限，蓝色通道值，范围0-255 |
lbGreen | integer | — | 颜色范围下限，所有通道的数值需均小于或等于上限，绿色通道值，范围0-255 |
ubGreen | integer | — | 颜色范围上限，所有通道的数值需均大于或等于上限，绿色通道值，范围0-255 |
imageUrl | string | — | 图片的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 |
Parameters from the server's own tool schema.
This tool analyzes image data and returns computed statistics (pixel counts within/outside color bounds). It performs read-only image analysis with no side effects, no data modification, and no capability to execute commands or access systems beyond the provided image. The operation is deterministic and safe, making it a Read category tool with low risk.
From the tool's definition Tool counts pixels matching color criteria in an image and returns statistics. The description states it 'Count the pixels' and 'Returns a JSON string with...BetweenCount...OutsideCount' — purely data retrieval with no modification, deletion, or execution of…
Attacks that exploit this kind of access
Count the pixels in the input image which is between or outside the given color bounds. For all of the channels, the pixel value is within the color bounds, then it's a "between" color pixel. Otherwise, for any of the channel, the pixel value is smaller or greater than the lower/upper bound, then it's a "outside" color pixel. 计算输入彩色图像中像素值在设置范围之内、之外的像素总数。 对于每一个像素，若其所有通道的颜色值均在指定范围内，则该像素为范围内"between"像素。 反之，若其任一通道的数值小于或大于指定颜色范围的下限或上限，则该像素为范围外"outside"像素。 Returns a JSON string with the following fields: BetweenCount: The count of pixels within the bounds OutsideCount: The count of pixels out of the bounds 返回结构是一个序列化的JSON字符串，包含以下字段： BetweenCount: 颜色值在颜色范围之间的像素总数 OutsideCount: 颜色值在颜色范围以外的像素总数. It is categorised as a Read tool in the Leaper Vision Toolkit MCP Server, which means it retrieves data without modifying state.
image_stats_count_pixel_color accepts 8 parameters: lbRed, ubRed, lbBlue, ubBlue, lbGreen, ubGreen, imageUrl, regionJson. 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_stats_count_pixel_color: 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_stats_count_pixel_color 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 image_stats_count_pixel_color 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_stats_count_pixel_color. 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_stats_count_pixel_color 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 →