Get PostgreSQL built-in prompt by name.
AI agents call pgsql_get_builtin_prompt to retrieve information from Database MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves configuration or template data from PostgreSQL without modifying, executing code, or deleting anything. It is a simple lookup/get operation with no destructive or executable side effects. The low severity reflects that retrieving a prompt poses minimal security risk even if misused by an agent.
From the tool's definition Tool name 'pgsql_get_builtin_prompt' and description 'Get PostgreSQL built-in prompt by name' indicates a retrieval operation with no side effects. It fetches a built-in prompt resource by identifier.
Attacks that exploit this kind of access
Get PostgreSQL built-in prompt by name. It is categorised as a Read tool in the Database MCP MCP Server, which means it retrieves data without modifying state.
Register the Database MCP server in PolicyLayer and add a rule for pgsql_get_builtin_prompt: 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 Database MCP. Nothing to install.
pgsql_get_builtin_prompt 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 pgsql_get_builtin_prompt 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 pgsql_get_builtin_prompt. 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.
pgsql_get_builtin_prompt is provided by the Database MCP server (swoiow/database_mcp). 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 →