Custo Claude Code por janelas deslizantes de 5h com gap detection (entries separadas por >5h iniciam novo bloco — pattern ccusage). Retorna blocks[] com started_at, ended_at, total_usd, by_model, entry_count, is_active + shape canônico agregado. Triggers:
AI agents call cost-blocks to retrieve information from Kit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and returns cost/usage analytics data organized into sliding 5-hour windows. It retrieves and aggregates existing billing/usage records (blocks with timestamps, USD totals, model breakdown) but does not initiate any financial transactions or modify data. It is a reporting/read tool despite involving cost figures.
From the tool's definition 'Custo Claude Code por janelas deslizantes de 5h com gap detection' and 'Retorna blocks[] com started_at, ended_at, total_usd, by_model, entry_count, is_active' — the tool returns aggregated cost/usage data blocks
Attacks that exploit this kind of access
Custo Claude Code por janelas deslizantes de 5h com gap detection (entries separadas por >5h iniciam novo bloco — pattern ccusage). Retorna blocks[] com started_at, ended_at, total_usd, by_model, entry_count, is_active + shape canônico agregado. Triggers:. It is categorised as a Read tool in the Kit MCP Server, which means it retrieves data without modifying state.
Register the Kit MCP server in PolicyLayer and add a rule for cost-blocks: 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 Kit. Nothing to install.
cost-blocks 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-blocks 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-blocks. 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-blocks is provided by the Kit MCP server (luanpdd/kit-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 →