查询可用的命令列表
AI agents call queryCommands to retrieve information from SiYuan 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 or enumerates available commands—a read-only information query operation. It does not execute commands, modify data, or trigger side effects. The sibling tool 'executeCommand' is distinct and handles actual execution. Querying a command list poses minimal risk as it only exposes available operations without executing them.
From the tool's definition Tool name 'queryCommands' and description '查询可用的命令列表' (query available commands list) indicates retrieval of command metadata without modification or execution.
Attacks that exploit this kind of access
查询可用的命令列表. It is categorised as a Read tool in the SiYuan MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SiYuan MCP Server MCP server in PolicyLayer and add a rule for queryCommands: 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 SiYuan MCP Server. Nothing to install.
queryCommands 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 queryCommands 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 queryCommands. 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.
queryCommands is provided by the SiYuan MCP Server MCP server (rexding97/siyuan-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
queryCommands is one line of SiYuan MCP Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →