Run a read-only SQL query against the database. ONLY SELECT queries are allowed for safety.
AI agents call run_query to retrieve information from PostgreSQL MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool is explicitly restricted to SELECT queries, making it a read-only data retrieval operation. However, it still carries medium severity because SELECT queries can expose sensitive data from the database, and enforcement of the read-only constraint depends on implementation (e.g., whether it truly prevents SET, CALL, or other non-destructive but side-effecting statements).
From the tool's definition "Run a read-only SQL query" and "ONLY SELECT queries are allowed for safety"
Attacks that exploit this kind of access
Run a read-only SQL query against the database. ONLY SELECT queries are allowed for safety. It is categorised as a Read tool in the PostgreSQL MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PostgreSQL MCP Server MCP server in PolicyLayer and add a rule for run_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 PostgreSQL MCP Server. Nothing to install.
run_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 run_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 run_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.
run_query is provided by the PostgreSQL MCP Server MCP server (kannakim/postgresqlmcpserver). 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 →