Count the pixels in the input image which is below, between or above the given threshold bounds. 计算输入图像中灰度值在设置范围之下、之内、之上的像素总数。 Returns a JSON string with the following fields: BelowCount: The count of pixels below the lower bound of threshold range BetweenCount: The count of pixels in the thresho...
AI agents call image_stats_count_pixel 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 |
|---|---|---|---|
lb | integer | — | 阈值范围下限，对于 8 位图像数值在 0 ~ 255 范围内，对于 16 位图像数值在 0 ~ 65535 范围内 |
ub | integer | — | 阈值范围上限，对于 8 位图像数值在 0 ~ 255 范围内，对于 16 位图像数值在 0 ~ 65535 范围内 |
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 is a data retrieval and analysis operation that queries image properties without side effects. It reads pixel data and computes aggregate statistics, which is characteristic of Read category tools. The tool does not create, modify, delete, or execute any code—it merely analyzes and reports on existing image data.
From the tool's definition The tool 'image_stats_count_pixel' analyzes and counts pixels in an image based on threshold values, returning statistical data (BelowCount, BetweenCount, AboveCount).
Attacks that exploit this kind of access
Count the pixels in the input image which is below, between or above the given threshold bounds. 计算输入图像中灰度值在设置范围之下、之内、之上的像素总数。 Returns a JSON string with the following fields: BelowCount: The count of pixels below the lower bound of threshold range BetweenCount: The count of pixels in the threshold range AboveCount: The count of pixels above the upper bound of threshold range 返回结构是一个序列化的JSON字符串，包含以下字段： BelowCount: 灰度值在阈值范围以下的像素总数 BetweenCount: 灰度值在阈值范围之间的像素总数 AboveCount: 灰度值在阈值范围以上的像素总数. 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 accepts 4 parameters: lb, ub, 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: 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 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 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. 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 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 →