AI agents call analyze_workload_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.
This tool reads performance statistics and generates advisory recommendations without executing any DDL/DML commands, modifying data, or triggering external operations. It is purely informational, making it a Read category tool with low severity since misuse would only expose query patterns and index suggestions, not cause data loss or side effects.
From the tool's definition Tool 'analyze_workload_indexes' analyzes database workload using pg_stat_statements (a read-only PostgreSQL extension that tracks query execution statistics) and provides recommendations.
Attacks that exploit this kind of access
Analyze database workload and recommend indexes. Uses pg_stat_statements to find slow queries and suggests indexes to improve them. 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_workload_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_workload_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_workload_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_workload_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_workload_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 →