列出当前项目中已保存的自定义命令文件。
AI agents call list_learned_commands to retrieve information from Instrument MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about previously saved commands without modifying, executing, or deleting anything. It is a pure read operation that enumerates stored command definitions, posing minimal security risk even if an AI agent invokes it arbitrarily.
From the tool's definition Tool name 'list_learned_commands' and description indicate it 'lists saved custom command files in the current project' — a retrieval/query operation with no side effects.
Attacks that exploit this kind of access
列出当前项目中已保存的自定义命令文件。. It is categorised as a Read tool in the Instrument MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Instrument MCP Server MCP server in PolicyLayer and add a rule for list_learned_commands: 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 Instrument MCP Server. Nothing to install.
list_learned_commands 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 list_learned_commands 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 list_learned_commands. 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.
list_learned_commands is provided by the Instrument MCP Server MCP server (zeng-andrew/instrument-mcp). 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 →