AI agents use pause_entity to create or update resources in Postgres — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Postgres environment.
This tool modifies the status of advertising entities (keywords, audiences, creatives, ad groups) by pausing them. This is a reversible state change (entities can be unpaused), making it Write rather than Destructive. However, pausing ad entities can have significant financial impact by stopping active campaigns, hence high severity.
From the tool's definition Pause a specific ad entity (keyword, audience, creative, or ad group). Changes the status of the entity.
Attacks that exploit this kind of access
Pause a specific ad entity (keyword, audience, creative, or ad group). ⚠️ ACTION TOOL: this changes the status of the entity to. It is categorised as a Write tool in the Postgres MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Postgres MCP server in PolicyLayer and add a rule for pause_entity: 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 Postgres. Nothing to install.
pause_entity 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 pause_entity 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 pause_entity. 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.
pause_entity is provided by the Postgres MCP server (santisanti13/postgres-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 →