Diagnose storage keys in each workspace to help locate chat data
AI agents call diagnose_storage 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 diagnostic/introspection tool that reads storage metadata to help users understand the structure and location of their chat data. It has no side effects, does not modify or delete data, and does not execute arbitrary code.
From the tool's definition The tool 'diagnose_storage' queries and analyzes storage keys across workspaces to help locate chat data. The description explicitly states it helps users 'locate' data, indicating data inspection and retrieval without modification.
Attacks that exploit this kind of access
Diagnose storage keys in each workspace to help locate chat data. 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 diagnose_storage: 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.
diagnose_storage 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 diagnose_storage 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 diagnose_storage. 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.
diagnose_storage 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 →