Get time spent by category.
AI agents call get_category_breakdown to retrieve information from RescueTime 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 existing productivity analytics data without side effects. It falls squarely into the Read category as it fetches time-tracking summaries organized by category, similar to other sibling tools (get_activity_data, get_today_summary, etc.).
From the tool's definition Tool name 'get_category_breakdown' and description 'Get time spent by category' indicate a retrieval operation. The server description confirms this is about 'access to RescueTime productivity data' including 'category breakdowns' for analysis purposes.
Attacks that exploit this kind of access
Get time spent by category. It is categorised as a Read tool in the RescueTime MCP Server MCP Server, which means it retrieves data without modifying state.
Register the RescueTime MCP Server MCP server in PolicyLayer and add a rule for get_category_breakdown: 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 RescueTime MCP Server. Nothing to install.
get_category_breakdown 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_category_breakdown 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_category_breakdown. 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_category_breakdown is provided by the RescueTime MCP Server MCP server (jasonbates/rescuetime-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 →