Check if your current model usage fits within a daily budget. Gets a recommendation if over budget.
AI agents call check_budget to retrieve information from AgentCost 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 and queries budget status information without creating, modifying, deleting, or executing anything. It produces a read-only recommendation based on existing data. The severity is low because misuse by an AI agent would only result in incorrect budget assessments, not actual financial transactions or data loss.
From the tool's definition Tool description states 'Check if your current model usage fits within a daily budget' and 'Gets a recommendation if over budget' — purely informational operations with no modification or execution capabilities.
Attacks that exploit this kind of access
Check if your current model usage fits within a daily budget. Gets a recommendation if over budget. It is categorised as a Read tool in the AgentCost MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AgentCost MCP Server MCP server in PolicyLayer and add a rule for check_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 AgentCost MCP Server. Nothing to install.
check_budget 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 check_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 check_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.
check_budget is provided by the AgentCost MCP Server MCP server (oneagentlabs/agentcost-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 →