获取工具节点和下一层子节点的工具名称的方法，每次调用仅获取一层子节点，主要用于列出某个模块的方法和获取所有方法列表。 参数说明: - name: 要查询的节点名称，并根据name返回该节点及其下一层节点，不传则返回根节点和下一层结构。 返回结构是一个序列化树状结构的json，其中- Name: 节点名称，root表示根节点，其他为具体的库名、类名或方法名 - Type: 节点类型，包含: root(根节点)、directory(库目录)、class(工具类)、tool(具体方法) - Belong: 父节点名称，标识该节点属于哪个上级节点 - Children: 子节点列表，...
Admin/system-level operation
Part of the Leaper Vision Toolkit MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call get_tool_tree to retrieve information from Leaper Vision Toolkit without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though get_tool_tree only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
get_tool_tree:
rules:
- action: allowSee the full Leaper Vision Toolkit policy for all 169 tools.
获取工具节点和下一层子节点的工具名称的方法，每次调用仅获取一层子节点，主要用于列出某个模块的方法和获取所有方法列表。 参数说明: - name: 要查询的节点名称，并根据name返回该节点及其下一层节点，不传则返回根节点和下一层结构。 返回结构是一个序列化树状结构的json，其中- Name: 节点名称，root表示根节点，其他为具体的库名、类名或方法名 - Type: 节点类型，包含: root(根节点)、directory(库目录)、class(工具类)、tool(具体方法) - Belong: 父节点名称，标识该节点属于哪个上级节点 - Children: 子节点列表，仅包含该节点下的子项，不包含该节点的子节点的所有子项 . It is categorised as a Read tool in the Leaper Vision Toolkit MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for get_tool_tree. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Leaper Vision Toolkit MCP server.
get_tool_tree 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 get_tool_tree rule in your Intercept 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 Intercept policy for get_tool_tree. 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.
get_tool_tree is provided by the Leaper Vision Toolkit MCP server (leaper-mcp/leaper-mcp-proxy). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept