List table names in Tsurugi RDBMS.
AI agents call listTableNames to retrieve information from Tsurugi Python Mcp Tools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns metadata (table names) from the database without side effects. It is a non-destructive read operation similar to SHOW TABLES or information schema queries. No data is modified, executed, or deleted. Severity is low because listing table names presents minimal risk even if misused by an agent.
From the tool's definition Tool name is 'listTableNames' and description states it 'List table names in Tsurugi RDBMS' — a pure retrieval operation with no modification, deletion, or code execution capability.
Attacks that exploit this kind of access
List table names in Tsurugi RDBMS. It is categorised as a Read tool in the Tsurugi Python Mcp Tools MCP Server, which means it retrieves data without modifying state.
Register the Tsurugi Python Mcp Tools MCP server in PolicyLayer and add a rule for listTableNames: 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 Tsurugi Python Mcp Tools. Nothing to install.
listTableNames 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 listTableNames 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 listTableNames. 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.
listTableNames is provided by the Tsurugi Python Mcp Tools MCP server (septigram/tsurugi-python-mcp-tools). 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 →