Stretch the input image and output the result image. Each output pixel represents the difference between the greyscale value of each input pixel and the threshold lower bound. For example, if a pixel value is 100 and the threshold lower bound is 25, then the output pixel value will be 75. If the ...
AI agents invoke il_image_threshold_stretch 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 |
|---|---|---|---|
imageUrl | string | — | 图片的url地址，通过这个地址获取到图片 |
InputParameterFile | string | — | 指定的 ILImageThreshold 类的文件地址，调用工具函数需要传入的参数文件名称。在调用此工具前要保证前处理中一定要有且仅有一次的 ILImageThreshold 初始化工具调用。这个属性的值需要从前处理的MCP工具的返回值 InputParameterFile 字段中获取。 |
Parameters from the server's own tool schema.
The tool runs an image processing pipeline (stretch transformation) that may invoke prior tool state and produces an output artifact. It is not a simple read/query but an execution of a transformation operation. No data is deleted or financial operations performed, so Execute is the most appropriate category. Severity is low as the blast radius is limited to image processing outputs.
From the tool's definition 'execute the set threshold tool first, then execute this tool' and 'Stretch the input image and output the result image' — triggers a multi-step image processing operation and returns a result URL
Attacks that exploit this kind of access
Stretch the input image and output the result image. Each output pixel represents the difference between the greyscale value of each input pixel and the threshold lower bound. For example, if a pixel value is 100 and the threshold lower bound is 25, then the output pixel value will be 75. If the user has set threshold values, execute the set threshold tool first, then execute this tool. Returns a serialized JSON structure containing: LpvClassName indicating the function name; InputParameterFile representing the parameter file name; result property representing the URL address of the stretched image;这个是拉伸图像工具。拉伸输入图像并输出结果图像。计算输入图像中的每个像素，其灰度值与阈值范围下限的距离。如若阈值范围下限为 25，灰度值为 100 的像素，其输出值为 75。如果用户同时设置了阈值，要先执行设置阈值工具，然后再执行此工具。返回结构是一个序列化的json，其中LpvClassName 表示调用工具函数的名称；InputParameterFile 表示调用工具函数需要传入的参数文件名称;result 属性是输入图像拉伸结果的图片地址. 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_threshold_stretch accepts 2 parameters: imageUrl, InputParameterFile. 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_threshold_stretch: 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_threshold_stretch 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_threshold_stretch 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_threshold_stretch. 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_threshold_stretch 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 →