AI agents call 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.
This tool retrieves data without side effects. The read-only constraint prevents Write, Destructive, Execute (in the dangerous sense), or Financial operations. Risk is low since queries cannot modify state, though verbose result sets could cause DoS in edge cases.
From the tool's definition Tool name 'query' with description 'Execute a read-only SQL query against the database.' The explicit constraint 'read-only' and server description stating 'tools for executing read-only queries' confirm no data modification or deletion is possible.
Attacks that exploit this kind of access
Execute a read-only SQL query against the database. 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 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.
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 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 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.
query is provided by the Postgres MCP server (madhurprash/postgres-mcp-agentcore). 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 →