Generate a unified AI spend report aggregating subscription fees, API token costs, and local model compute across all detected AI tools. Returns per-vendor breakdown, daily spend trend, and total for the period.
AI agents call cost_report to retrieve information from Scan Your Ai Toolkit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a reporting and analytics tool that reads cost/billing data from detected AI tools and presents summaries (per-vendor breakdown, spend trends, totals). It has no side effects: it neither modifies data, executes operations, deletes records, nor moves money. The blast radius of misuse is minimal—an agent could generate spurious reports, but cannot alter actual spend or charge accounts.
From the tool's definition The tool 'Generate a unified AI spend report aggregating subscription fees, API token costs, and local model compute' performs data retrieval and aggregation. Key verbs: 'Generate' (report), 'aggregating', 'Returns' metrics.
Attacks that exploit this kind of access
Generate a unified AI spend report aggregating subscription fees, API token costs, and local model compute across all detected AI tools. Returns per-vendor breakdown, daily spend trend, and total for the period. It is categorised as a Read tool in the Scan Your Ai Toolkit MCP Server, which means it retrieves data without modifying state.
Register the Scan Your Ai Toolkit MCP server in PolicyLayer and add a rule for cost_report: 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 Scan Your Ai Toolkit. Nothing to install.
cost_report 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_report 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_report. 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_report is provided by the Scan Your Ai Toolkit MCP server (sakthivelchan89/scan_your_ai_toolkit). 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 →