list_tables
AI agents call list_tables to retrieve information from Sql Explorer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or lists table metadata from a SQL database with no side effects. The empty description is typical for simple listing operations, and the server's read-only design with three-layer safety mechanisms (AST validation and linting) confirms no destructive operations are possible. Listed alongside other harmless read operations, this is clearly a data retrieval tool with minimal blast radius.
From the tool's definition Tool name 'list_tables' combined with server description stating 'Read-only MCP server for SQL databases' and sibling tools like 'list_databases', 'describe_table', and 'get_table_sample' that are clearly read-only operations.
Attacks that exploit this kind of access
list_tables. It is categorised as a Read tool in the Sql Explorer MCP Server, which means it retrieves data without modifying state.
Register the Sql Explorer MCP server in PolicyLayer and add a rule for list_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 Sql Explorer. Nothing to install.
list_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_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_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_tables is provided by the Sql Explorer MCP server (pawansingh3889/sql-explorer-mcp). 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 →