Search conversations across all workspaces
AI agents call search_conversations to retrieve information from Cursor DB MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read operation that queries existing conversation data from SQLite databases without modifying or deleting anything. Severity is medium rather than low because conversation history may contain sensitive information (code snippets, API keys, personal context from developer chats), making unauthorized search access a privacy concern for an AI agent, though the blast radius is limited to information…
From the tool's definition Tool performs 'search conversations across all workspaces' - a retrieval operation on conversation history data. The server description emphasizes 'querying, searching, and analyzing' which are read operations.
Attacks that exploit this kind of access
Search conversations across all workspaces. It is categorised as a Read tool in the Cursor DB MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Cursor DB MCP Server MCP server in PolicyLayer and add a rule for search_conversations: 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 Cursor DB MCP Server. Nothing to install.
search_conversations 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 search_conversations 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 search_conversations. 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.
search_conversations is provided by the Cursor DB MCP Server MCP server (taylorchen/cursor-db-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 →