AI agents use create_extension_if_not_exists to create or update resources in Pgmcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pgmcp environment.
Creating a PostgreSQL extension is a reversible write operation that modifies the database schema by adding new functionality. While extensions can have broad effects on the database, the action itself is not destructive (can be dropped) and does not execute arbitrary code directly—it loads pre-built extension code.
From the tool's definition Tool description states 'Create a new extension in the PostgreSQL database.' The verb 'create' and the action of adding a new extension to the database indicate a write operation that modifies database state.
Attacks that exploit this kind of access
Create a new extension in the PostgreSQL database. It is categorised as a Write tool in the Pgmcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pg MCP server in PolicyLayer and add a rule for create_extension_if_not_exists: 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.
create_extension_if_not_exists is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_extension_if_not_exists 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 create_extension_if_not_exists. 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.
create_extension_if_not_exists 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 →