Update an existing service in an estimate by replacing its config. Use this to tweak values without recreating the entire estimate. Identifies the service by its key (and optionally group). Merges new config over existing config unless replace=true.
AI agents use update_service to create or update resources in Aws Calculator — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Aws Calculator environment.
The tool creates or modifies data reversibly by updating service configurations within an AWS cost estimate. This is a Write operation rather than Execute because it modifies data structure, not executing arbitrary code or commands. It is not Destructive because changes can be reverted (the estimate remains intact and editable).
From the tool's definition Tool description states it "Update[s] an existing service in an estimate" and "Merges new config over existing config", which are reversible modification operations. The tool modifies cost estimate data without permanently deleting or destroying it.
Documented attack patterns abuse exactly the kind of access update_service gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Aws Calculator, and nothing reaches the server without passing your rules. This is the rule we recommend for update_service:
{
"version": "1",
"default": "deny",
"tools": {
"update_service": {
"limits": [
{
"counter": "update_service_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_service stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Update an existing service in an estimate by replacing its config. Use this to tweak values without recreating the entire estimate. Identifies the service by its key (and optionally group). Merges new config over existing config unless replace=true. It is categorised as a Write tool in the Aws Calculator MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Aws Calculator MCP server in PolicyLayer and add a rule for update_service: 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 Aws Calculator. Nothing to install.
update_service 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_service 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_service. 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_service is provided by the Aws Calculator MCP server (musheer360/aws-calculator-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Aws Calculator, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 Aws Calculator tools catalogued and risk-classified — across an index of 43,000+ MCP servers.