列出当前已认证用户的所有云端代理。
AI agents call list_cursor_agents_tool to retrieve information from ShowDoc 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 information about cloud agents associated with an authenticated user. It performs a query/list operation with no side effects, data modification, deletion, or external execution. The blast radius of misuse is limited to information disclosure of agent metadata belonging to the user account, which represents low risk.
From the tool's definition Tool description states '列出当前已认证用户的所有云端代理' (list all cloud agents for the currently authenticated user). The verb 'list' and action of retrieving/querying existing agent data without modification indicate a read-only operation.
Attacks that exploit this kind of access
列出当前已认证用户的所有云端代理。. It is categorised as a Read tool in the ShowDoc MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ShowDoc MCP Server MCP server in PolicyLayer and add a rule for list_cursor_agents_tool: 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 ShowDoc MCP Server. Nothing to install.
list_cursor_agents_tool 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_cursor_agents_tool 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_cursor_agents_tool. 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_cursor_agents_tool is provided by the ShowDoc MCP Server MCP server (yfcyfc123234/showdoc_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 →