AI agents call select to retrieve information from Pgmcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
In SQL contexts, SELECT is a read operation that retrieves data. Given this is a PostgreSQL administration server, 'select' most likely executes a SELECT query. However, with an empty description, there is uncertainty — it could potentially allow arbitrary SQL execution including destructive statements. Confidence is reduced due to lack of description.
From the tool's definition Tool name 'select' suggests a SQL SELECT read operation, but description is empty and uninformative.
Attacks that exploit this kind of access
select. It is categorised as a Read tool in the Pgmcp MCP Server, which means it retrieves data without modifying state.
Register the Pg MCP server in PolicyLayer and add a rule for select: 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 Pgmcp. Nothing to install.
select 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 select 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 select. 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.
select is provided by the Pg MCP server (veloper/pgmcp). 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 →