Get AI feature usage for the organization showing current consumption vs maximum allowed. Tracks AI credits used across all workspaces. Useful for monitoring AI quota before heavy AI operations.
AI agents call get_ai_usage to retrieve information from Fusebase MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query of usage statistics and quota information. It has no side effects on data or systems. While the information retrieved could be sensitive (usage patterns), the tool itself creates no risk of data modification, deletion, or unauthorized operations. Severity is low because misuse would only expose organizational usage metrics without enabling further harmful actions.
From the tool's definition Tool name 'get_ai_usage' and description indicate it retrieves AI feature usage data and credit consumption metrics ('Get AI feature usage', 'Tracks AI credits used', 'monitoring AI quota').
Attacks that exploit this kind of access
Get AI feature usage for the organization showing current consumption vs maximum allowed. Tracks AI credits used across all workspaces. Useful for monitoring AI quota before heavy AI operations. It is categorised as a Read tool in the Fusebase MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Fusebase MCP Server MCP server in PolicyLayer and add a rule for get_ai_usage: 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 Fusebase MCP Server. Nothing to install.
get_ai_usage 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_ai_usage 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_ai_usage. 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_ai_usage is provided by the Fusebase MCP Server MCP server (ryan-haver/fusebase-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 →