List all CSV files in the storage directory.
AI agents call list_csv_files to retrieve information from CSV MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about available CSV files without creating, modifying, deleting, or executing any operations. It is a simple directory listing function with no side effects, fitting the Read category definition of 'retrieves or queries data.' The severity is low because even if an AI agent misuses this by listing all files, the impact is limited to information disclosure of file metadata in the…
From the tool's definition Tool name 'list_csv_files' and description 'List all CSV files in the storage directory' indicate a query/listing operation with no data modification.
Attacks that exploit this kind of access
List all CSV files in the storage directory. It is categorised as a Read tool in the CSV MCP Server MCP Server, which means it retrieves data without modifying state.
Register the CSV MCP Server MCP server in PolicyLayer and add a rule for list_csv_files: 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 CSV MCP Server. Nothing to install.
list_csv_files 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_csv_files 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_csv_files. 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_csv_files is provided by the CSV MCP Server MCP server (novaai-innovation/csv-mcp-server). 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 →