基于执行计划与查询形态给出索引建议（只读）
AI agents call indexAdvisor to retrieve information from SQL MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The indexAdvisor tool performs read-only analysis of database execution plans and query patterns to generate index recommendations. It does not create, modify, delete, or execute any data-altering operations. The explicit "只读" (read-only) designation confirms this is a Read category tool with low severity, as it only retrieves and analyzes existing metadata without side effects.
From the tool's definition Tool description explicitly states "只读" (read-only). The tool analyzes execution plans and query patterns to provide index suggestions without modifying data, schema, or executing any write operations. It is a metadata analysis tool.
Attacks that exploit this kind of access
基于执行计划与查询形态给出索引建议（只读）. It is categorised as a Read tool in the SQL MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SQL MCP Server MCP server in PolicyLayer and add a rule for indexAdvisor: 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 MCP Server. Nothing to install.
indexAdvisor 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 indexAdvisor 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 indexAdvisor. 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.
indexAdvisor is provided by the SQL MCP Server MCP server (polarisxb/sql-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 →