Learn the pattern template features from the provided image. 训练模板，使用输入的图像。 The template center can be modified later. 模板中心可根据需求修改。 This function extracts features from the input image for pattern matching. 该函数从输入图像中提取特征用于模板匹配。 It may fail if no proper feature is found on the input image. 训练过程可能失败...
AI agents use pat_match_learn to create or update resources in Leaper Vision Toolkit — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Leaper Vision Toolkit environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
imageUrl | string | — | 图片的url地址，通过这个地址获取到需要输入的图像 |
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)。这两 |
regionClassObjDescriptionJson | string | — | 输入的Roi区域，用于限定模板在输入图像中的位置。 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。LpvClassNam |
Parameters from the server's own tool schema.
This tool creates and stores learned pattern templates from input images. While it does not delete or move money, it irreversibly generates new configuration objects in the system that persist and affect subsequent operations.
From the tool's definition pat_match_learn learns pattern template features from images and returns a serialized JSON configuration object (LpvClassName, InputParameterFile) that is stored and can be reused by other tools.
Attacks that exploit this kind of access
Learn the pattern template features from the provided image. 训练模板，使用输入的图像。 The template center can be modified later. 模板中心可根据需求修改。 This function extracts features from the input image for pattern matching. 该函数从输入图像中提取特征用于模板匹配。 It may fail if no proper feature is found on the input image. 训练过程可能失败，若在输入图像中没有找到任何可用的特征。 如果别的工具需要训练后的模板匹配的功能对象，可以使用当前对象Json。 返回结构是一个序列化的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)。 LpvClassName 表示模板匹配的功能对象名称，目前名称应为：ILMatch (模板匹配的功能对象); InputParameterFile 表示模板匹配的功能对象的参数文件名称。. It is categorised as a Write tool in the Leaper Vision Toolkit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
pat_match_learn accepts 3 parameters: imageUrl, matchClassObjDescriptionJson, regionClassObjDescriptionJson. 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_learn: 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_learn is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the pat_match_learn 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_learn. 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_learn 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 →