获取输入图像的图片信息。 返回结构是一个序列化的JSON字符串，包含以下字段： BytesPerLine : 每行像素数据的字节数，包含行末用于对齐的字节。 Height: 图像的高度，行的总数。 Width: 图像的宽度，列的总数。 ImageFormat: 图像类型(LPVImageFormatGrayscale8：该图像为 8 位灰度图。LPVImageFormatColor24 ：该图像为 24 位 BGR 彩色图，每个通道 8 位。LPVImageFormatGrayscale16:该图像为 16 位灰度图 ) Get the input image info. Returns...
AI agents call image_info 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 |
|---|---|---|---|
imageUrl | string | — | 当前图像的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 queries and returns image properties only. It has no side effects, performs no transformations, executes no code, and modifies no data. It is a straightforward read operation that retrieves image information for inspection purposes.
From the tool's definition Tool name 'image_info' and description 'Get the input image info' / '获取输入图像的图片信息' — retrieves metadata about an image (BytesPerLine, Height, Width, ImageFormat) without modifying, deleting, or executing operations.
Attacks that exploit this kind of access
获取输入图像的图片信息。 返回结构是一个序列化的JSON字符串，包含以下字段： BytesPerLine : 每行像素数据的字节数，包含行末用于对齐的字节。 Height: 图像的高度，行的总数。 Width: 图像的宽度，列的总数。 ImageFormat: 图像类型(LPVImageFormatGrayscale8：该图像为 8 位灰度图。LPVImageFormatColor24 ：该图像为 24 位 BGR 彩色图，每个通道 8 位。LPVImageFormatGrayscale16:该图像为 16 位灰度图 ) Get the input image info. Returns a serialized JSON string containing the following fields: BytesPerLine : The number of bytes contained in a row, include the padding bytes. Height: The height of the image, number of rows. Width: The width of the image, number of columns. ImageFormat: The format of the image. (LPVImageFormatGrayscale8：The image is stored using an 8-bit grayscale format. LPVImageFormatColor24 ：The image is stored using a 24-bit BGR color format (8-8-8).LPVImageFormatGrayscale16:The image is stored using an 16-bit grayscale format. ). It is categorised as a Read tool in the Leaper Vision Toolkit MCP Server, which means it retrieves data without modifying state.
image_info accepts 1 parameter: imageUrl. 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_info: 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_info 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_info 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_info. 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_info 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 →