List all currently loaded tables with their source CSV files
AI agents call list_loaded_tables to retrieve information from Mcp Csv Database without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple query to enumerate loaded tables and their associated CSV sources. There are no side effects, data is not modified, and the operation is read-only. The blast radius if misused is minimal—an AI agent could only discover which tables exist in the temporary database. This is a canonical Read operation.
From the tool's definition Tool name and description indicate it 'List all currently loaded tables' — a retrieval operation with no modification or side effects. It queries metadata about existing tables.
Attacks that exploit this kind of access
List all currently loaded tables with their source CSV files. It is categorised as a Read tool in the Mcp Csv Database MCP Server, which means it retrieves data without modifying state.
Register the Mcp Csv Database MCP server in PolicyLayer and add a rule for list_loaded_tables: 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.
list_loaded_tables 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 list_loaded_tables 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 list_loaded_tables. 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.
list_loaded_tables 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 →