AI agents call explain_query 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.
EXPLAIN statements retrieve query metadata and performance information but do not read, write, modify, or execute the actual query against data. This is a read-only introspection operation with no side effects. Severity is low because misuse would only expose query plans, not sensitive data or cause harmful operations.
From the tool's definition Tool name is 'explain_query' and description indicates it 'Show[s] PostgreSQL' (likely EXPLAIN output). EXPLAIN is a PostgreSQL meta-command that analyzes and displays query execution plans without executing the query or modifying data.
Attacks that exploit this kind of access
Show PostgreSQL. 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 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 Postgres. 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 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 →