AI agents call list_indexes to retrieve information from Mssql without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
schema | string | — | Schema name (default: dbo) |
tableName | string | — | Filter by specific table name |
connectionName | string | — | Named connection to use (e.g., 'production', 'staging') |
connectionString | string | — | SQL Server connection string (uses default if not provided) |
includeUsageStats | boolean | — | Include index usage statistics (default: true) |
Parameters from the server's own tool schema.
This tool retrieves and lists index information and usage statistics from the database. It performs no modifications, deletions, or code execution—purely a read operation against system schema tables. The verb 'list' and the focus on gathering usage statistics confirm it as a non-destructive information retrieval tool.
From the tool's definition Tool name 'list_indexes' and description 'List all indexes on tables with usage statistics and detailed information' indicate a retrieval operation that queries database metadata without modification or execution of code.
Attacks that exploit this kind of access
List all indexes on tables with usage statistics and detailed information. It is categorised as a Read tool in the Mssql MCP Server, which means it retrieves data without modifying state.
list_indexes accepts 5 parameters: schema, tableName, connectionName, connectionString, includeUsageStats. The full parameter table on this page comes from the server's own tool schema.
Register the Mssql MCP server in PolicyLayer and add a rule for list_indexes: 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 Mssql. Nothing to install.
list_indexes 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_indexes 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_indexes. 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_indexes is provided by the Mssql MCP server (mssql-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 →