获取云端 Agent 的会话历史，包括所有用户提问与助手回复。
AI agents call get_cursor_agent_conversation_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 and queries conversation history data with no side effects. It falls squarely into the Read category as it only fetches existing information. Severity is low because reading conversation history poses minimal risk—it cannot modify, delete, execute code, or affect financial systems.
From the tool's definition Tool name contains 'get' and description states '获取云端 Agent 的会话历史' (fetches cloud Agent conversation history). The action is purely retrieving historical conversation data without modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
获取云端 Agent 的会话历史，包括所有用户提问与助手回复。. 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 get_cursor_agent_conversation_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.
get_cursor_agent_conversation_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 get_cursor_agent_conversation_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 get_cursor_agent_conversation_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.
get_cursor_agent_conversation_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 →