Get the feature points of trained pattern. 获取模板的特征点。 The feature points are extracted from the trained template. 特征点通过给定的形状区域提取。 Level parameter specifies the level of required features: Level 0 (default) for level 0 of original size, 1 for level 1 in scaled size. 层级参数指定获取特征的层级：0（默认值）表示原始尺度的 0 层特...
AI agents call pat_match_get_pat_feature 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 |
|---|---|---|---|
level | integer | — | 指定获取特征的层级。可能的取值有：-1 表示所有层级，0（默认值）表示原始尺度的 0 层特征，1 表示缩小尺度的 1 层特征 。 |
matchClassObjDescriptionJson | string | — | 模板匹配的功能对象用于训练模板匹配的功能。如果用户没有指定模板匹配的功能对象，请创建一个模板匹配的功能对象后传入。 如果用户指定模板匹配的功能对象，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)。 |
Parameters from the server's own tool schema.
This tool extracts and retrieves feature point data from a pre-trained pattern template. It performs a query/read operation that returns structured information about pattern features without modifying, deleting, or executing external operations. The output is read-only data suitable for analysis or display in image processing workflows.
From the tool's definition Tool name 'pat_match_get_pat_feature' and description 'Get the feature points of trained pattern' indicates data retrieval.
Attacks that exploit this kind of access
Get the feature points of trained pattern. 获取模板的特征点。 The feature points are extracted from the trained template. 特征点通过给定的形状区域提取。 Level parameter specifies the level of required features: Level 0 (default) for level 0 of original size, 1 for level 1 in scaled size. 层级参数指定获取特征的层级：0（默认值）表示原始尺度的 0 层特征，1 表示缩小尺度的 1 层特征。 返回结构是一个序列化的JSON字符串，属性包括： Count(点位的数量) 和 Empty(是否为空，ture为空，false则不为空) 和 Item(点的位置的数组，数组中的对象包含X,Y属性分别代表x和y的坐标) 。. It is categorised as a Read tool in the Leaper Vision Toolkit MCP Server, which means it retrieves data without modifying state.
pat_match_get_pat_feature accepts 2 parameters: level, matchClassObjDescriptionJson. 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 pat_match_get_pat_feature: 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.
pat_match_get_pat_feature 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 pat_match_get_pat_feature 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 pat_match_get_pat_feature. 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.
pat_match_get_pat_feature 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 →