Update the daily budget of a campaign
AI agents use update_campaign_budget to create or update resources in Amazon Ads MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Amazon Ads MCP environment.
This tool modifies campaign parameters (budget allocation) but does not delete data or trigger irreversible actions. It qualifies as Write rather than Execute because it directly updates a specific data field rather than running arbitrary code or scripts.
From the tool's definition Tool name 'update_campaign_budget' and description 'Update the daily budget of a campaign' indicate modification of existing campaign data. This is a reversible change—budgets can be adjusted up or down without destroying data.
Attacks that exploit this kind of access
Update the daily budget of a campaign. It is categorised as a Write tool in the Amazon Ads MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Amazon Ads MCP server in PolicyLayer and add a rule for update_campaign_budget: 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 Amazon Ads MCP. Nothing to install.
update_campaign_budget 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 update_campaign_budget 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 update_campaign_budget. 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.
update_campaign_budget is provided by the Amazon Ads MCP server (ppcprophet/amazon-ads-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 →