AI agents call analyze_query_indexes to retrieve information from Postgres without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads query patterns and database metadata to recommend indexes, but does not execute writes, deletes, or code. It is purely informational analysis. No side effects occur on the database state. Severity is low because recommendations alone cannot cause harm—they require a separate execute step to implement.
From the tool's definition Tool performs analysis on SELECT queries and provides recommendations; explicit mention of 'SELECT queries' and 'recommendations' indicates read-only analysis with no data modification.
Attacks that exploit this kind of access
Recommend indexes for specific SQL queries. Provide up to 10 SELECT queries and get index recommendations. It is categorised as a Read tool in the Postgres MCP Server, which means it retrieves data without modifying state.
Register the Postgres MCP server in PolicyLayer and add a rule for analyze_query_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 Postgres. Nothing to install.
analyze_query_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 analyze_query_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 analyze_query_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.
analyze_query_indexes is provided by the Postgres MCP server (teja-sudo/postgres-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 →