Clear the temporary database and remove all loaded tables.
AI agents call clear_database to permanently remove resources in Mcp Csv Database — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes all loaded tables and their data with no undo mechanism. While the database is described as 'temporary', the action itself is destructive and irreversible within an AI agent's session. An agent misusing this tool could erase all analyzed data, necessitating full data reloads.
From the tool's definition Tool named 'clear_database' with description 'Clear the temporary database and remove all loaded tables' — irreversibly deletes all data in the database.
Attacks that exploit this kind of access
Clear the temporary database and remove all loaded tables. It is categorised as a Destructive tool in the Mcp Csv Database MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Csv Database MCP server in PolicyLayer and add a rule for clear_database: 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 Mcp Csv Database. Nothing to install.
clear_database is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the clear_database 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 clear_database. 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.
clear_database is provided by the Mcp Csv Database MCP server (lasitha-jayawardana/mcp-csv-database). 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 →