List indexes with usage statistics. Can filter by specific table or list all indexes in a schema. Shows index type, columns, uniqueness, size, and scan count to help identify unused or inefficient indexes.
AI agents call listIndexes to retrieve information from Postgresql without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about database indexes and their usage patterns. It performs a query to gather information but does not modify, delete, or execute any code. The blast radius is minimal—at worst, an AI agent could enumerate index details to understand database structure, but cannot change data or system state. Classified as Read with low severity.
From the tool's definition Tool name 'listIndexes' and description 'List indexes with usage statistics' indicate a retrieval operation. The description specifies only read-only operations: 'list all indexes', 'shows index type, columns, uniqueness, size, and scan count'.
Attacks that exploit this kind of access
List indexes with usage statistics. Can filter by specific table or list all indexes in a schema. Shows index type, columns, uniqueness, size, and scan count to help identify unused or inefficient indexes. It is categorised as a Read tool in the Postgresql MCP Server, which means it retrieves data without modifying state.
Register the Postgresql MCP server in PolicyLayer and add a rule for listIndexes: 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 Postgresql. Nothing to install.
listIndexes 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 listIndexes 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 listIndexes. 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.
listIndexes is provided by the Postgresql MCP server (vnikhilbuddhavarapu/postgresql-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 →