Get available tag values
AI agents call get_tag_values to retrieve information from Cost Explorer MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about AWS tags in the cost explorer system. It performs a simple lookup query without creating, modifying, deleting, or executing any operations. The action is read-only and poses minimal risk—even if misused by an agent, it only exposes tag information already available through AWS permissions.
From the tool's definition Tool name 'get_tag_values' and description 'Get available tag values' indicate a retrieval operation with no modification or execution capability. The tool queries AWS Cost Explorer metadata to list available tag values without side effects.
Attacks that exploit this kind of access
Get available tag values. It is categorised as a Read tool in the Cost Explorer MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Cost Explorer MCP Server MCP server in PolicyLayer and add a rule for get_tag_values: 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 Cost Explorer MCP Server. Nothing to install.
get_tag_values 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 get_tag_values 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 get_tag_values. 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.
get_tag_values is provided by the Cost Explorer MCP Server MCP server (milan9527/costexplorermcp). 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 →