Get cost data for a specific provider and time period
AI agents call cost_get to retrieve information from Cost Management MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries financial cost data without modifying, deleting, or executing any operations. While it accesses financial information, it does not move money, commit financial obligations, or perform any transactions—it only reads existing cost records. Therefore, it falls under the Read category with low severity, as misuse would only expose cost visibility rather than enable financial harm.
From the tool's definition Tool name 'cost_get' and description 'Get cost data for a specific provider and time period' clearly indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Get cost data for a specific provider and time period. It is categorised as a Read tool in the Cost Management MCP MCP Server, which means it retrieves data without modifying state.
Register the Cost Management MCP server in PolicyLayer and add a rule for cost_get: 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 Management MCP. Nothing to install.
cost_get 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 cost_get 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 cost_get. 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.
cost_get is provided by the Cost Management MCP server (knishioka/cost-management-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 →