Execute a SELECT query on the PostgreSQL database and return formatted results
AI agents invoke query_database to trigger actions in PostgreSQL MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Although described as read-only and SELECT-only, this tool executes arbitrary SQL against a production database. Even SELECT queries can be expensive, expose sensitive data, or (depending on server enforcement) be abused with subqueries or functions with side effects.
From the tool's definition "Execute a SELECT query on the PostgreSQL database" — runs arbitrary SQL queries against a database
Attacks that exploit this kind of access
Execute a SELECT query on the PostgreSQL database and return formatted results. It is categorised as a Execute tool in the PostgreSQL MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the PostgreSQL MCP Server MCP server in PolicyLayer and add a rule for query_database: 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.
query_database is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the query_database 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 query_database. 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.
query_database is provided by the PostgreSQL MCP Server MCP server (jplwunder/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 →