AI agents call show_csv to retrieve information from Restcsv without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'show_csv' most naturally implies displaying or retrieving CSV data, consistent with Read operations. The absence of verbs like 'delete', 'update', 'create', or 'execute' in the name, combined with the presence of other write/destructive operations on the server (delete_csv, bulk_store_csv_row), suggests this is a query-only function.
From the tool's definition Tool name 'show_csv' indicates retrieval/display functionality. No description provided, but naming convention and sibling tools (list_csvs, list_csv_rows) suggest data querying without modification.
Attacks that exploit this kind of access
show_csv. It is categorised as a Read tool in the Restcsv MCP Server, which means it retrieves data without modifying state.
Register the Restcsv MCP server in PolicyLayer and add a rule for show_csv: 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 Restcsv. Nothing to install.
show_csv 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 show_csv 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 show_csv. 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.
show_csv is provided by the Restcsv MCP server (restcsv-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 →