Execute a SELECT query on PostgreSQL database
AI agents call postgres_query to retrieve information from Multi-Database 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 described as executing SELECT queries, which are read-only data retrieval operations. However, severity is medium rather than low because the server description mentions configurable read/write permissions and the enforcement of the SELECT-only restriction depends on implementation.
From the tool's definition 'Execute a SELECT query on PostgreSQL database' — explicitly limited to SELECT queries
Attacks that exploit this kind of access
Execute a SELECT query on PostgreSQL database. It is categorised as a Read tool in the Multi-Database MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Multi-Database MCP Server MCP server in PolicyLayer and add a rule for postgres_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 Multi-Database MCP Server. Nothing to install.
postgres_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 postgres_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 postgres_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.
postgres_query is provided by the Multi-Database MCP Server MCP server (nam088/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 →