Show the PostgreSQL execution plan for a query (EXPLAIN).
AI agents call explain_query to retrieve information from Postgres Safe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
EXPLAIN generates no side effects—it does not execute the query, create/modify data, or delete anything. It only returns metadata about how PostgreSQL would execute a query. While an AI agent could use this to learn about table structure or data volume through plan analysis, the tool itself performs only introspection.
From the tool's definition Tool executes EXPLAIN, which retrieves query execution plans without modifying, deleting, or executing the underlying query. EXPLAIN is a read-only SQL command that returns metadata about query optimization.
Attacks that exploit this kind of access
Show the PostgreSQL execution plan for a query (EXPLAIN). It is categorised as a Read tool in the Postgres Safe MCP Server, which means it retrieves data without modifying state.
Register the Postgres Safe 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 Safe. 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 Safe MCP server (sam-david/pg-redact-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 →