AI agents call explain_query to retrieve information from Pgsql without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The explain_query tool is a read-only diagnostic utility that analyzes and returns query execution plans and cost information. It does not execute queries against data, create side effects, modify state, or trigger external operations. The sibling tools (analyze_db_health, get_object_details, get_top_queries, list_objects, list_schemas) further confirm this server's focus on safe introspection.
From the tool's definition Tool description states it 'Explains the execution plan for a SQL query' and 'provides detailed cost estimates' — analysis-only operations that return execution plans without executing the actual query or modifying data.
Attacks that exploit this kind of access
Explains the execution plan for a SQL query, showing how the database will execute it and provides detailed cost estimates. It is categorised as a Read tool in the Pgsql MCP Server, which means it retrieves data without modifying state.
Register the Pgsql MCP server in PolicyLayer and add a rule for explain_query: 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 Pgsql. Nothing to install.
explain_query 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 explain_query 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 explain_query. 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.
explain_query is provided by the Pgsql MCP server (surajmandalcell/pgsql-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 →