Run a read-only query (SELECT, WITH, SHOW, EXPLAIN, VALUES, TABLE) against a configured Postgres connection. Runs inside a READ ONLY transaction, so writes are rejected by the database itself. Returns rows up to the connection
AI agents call execute_read_query to retrieve information from Postgres Mcp Query Tool without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool is explicitly constrained to read-only SQL operations enforced at the database transaction level. It retrieves data without side effects. Severity is medium rather than low because arbitrary SELECT queries against a Postgres database can expose sensitive data at scale (row caps noted but still present), and the AI agent has broad query flexibility within the read-only constraint.
From the tool's definition 'Run a read-only query (SELECT, WITH, SHOW, EXPLAIN, VALUES, TABLE) against a configured Postgres connection. Runs inside a READ ONLY transaction, so writes are rejected by the database itself.'
Attacks that exploit this kind of access
Run a read-only query (SELECT, WITH, SHOW, EXPLAIN, VALUES, TABLE) against a configured Postgres connection. Runs inside a READ ONLY transaction, so writes are rejected by the database itself. Returns rows up to the connection. It is categorised as a Read tool in the Postgres Mcp Query Tool MCP Server, which means it retrieves data without modifying state.
Register the Postgres Mcp Query Tool MCP server in PolicyLayer and add a rule for execute_read_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 Mcp Query Tool. Nothing to install.
execute_read_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 execute_read_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 execute_read_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.
execute_read_query is provided by the Postgres Mcp Query Tool MCP server (nskha101/postgres-mcp-query-tool). 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 →