Searches through Cursor chat content using exact text matching (NOT semantic search) to find relevant discussions. WARNING: For project-specific searches, use list_conversations with projectPath instead of this tool! This tool is for searching message content, not project filtering.\n\nWHEN TO US...
AI agents call search_conversations to retrieve information from Cursor Conversations 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: it retrieves and filters conversation history based on search criteria. While the blast radius is medium (an agent could extract sensitive code snippets, API keys, credentials, or private information from chat histories), the tool itself performs no destructive, financial, or execution actions.
From the tool's definition Tool performs 'search through Cursor chat content' and 'find relevant discussions' with 'exact text matching' — a query-only operation that retrieves and filters existing conversation data without modification or side effects.
Documented attack patterns abuse exactly the kind of access search_conversations gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cursor Conversations MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_conversations:
{
"version": "1",
"default": "deny",
"tools": {
"search_conversations": {}
}
}search_conversations is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Searches through Cursor chat content using exact text matching (NOT semantic search) to find relevant discussions. WARNING: For project-specific searches, use list_conversations with projectPath instead of this tool! This tool is for searching message content, not project filtering.\n\nWHEN TO USE THIS TOOL:\n- Searching for specific technical terms in message content (e.g.,. It is categorised as a Read tool in the Cursor Conversations MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Cursor Conversations 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 Conversations 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 Conversations MCP Server MCP server (vltansky/cursor-chat-history-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 Cursor Conversations MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
8 Cursor Conversations MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.