AI agents call list_functions 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.
This tool retrieves metadata about PostgreSQL functions within a schema. It performs only a read operation—querying and returning information about existing database objects without creating, modifying, or deleting anything. The blast radius of misuse is minimal; an agent could learn function names and signatures but cannot execute arbitrary code or alter state. This is a classic Read category tool.
From the tool's definition Tool name 'list_functions' and description 'List all functions in the specified PostgreSQL schema' indicate a query/retrieval operation with no modification or deletion capability.
Attacks that exploit this kind of access
List all functions in the specified PostgreSQL schema. 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 list_functions: 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.
list_functions 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 list_functions 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 list_functions. 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.
list_functions 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 →