activitywatch_get_categories
Get all ActivityWatch categories (classification rules). Returns the list of categories with their regex rules used to classify window events.
This record as markdown: /tools/8bitgentleman-activitywatch-mcp-server/activitywatch-get-categories.md
What activitywatch_get_categories does on ActivityWatch MCP Server
AI agents call activitywatch_get_categories to retrieve information from ActivityWatch MCP Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why activitywatch_get_categories is rated Low
This tool retrieves classification rules and category definitions without creating, modifying, or deleting any data. It is a straightforward read operation with minimal risk—the data returned are only category metadata and regex patterns used for event classification, not sensitive user activity logs themselves.
From the tool's definition Tool name and description indicate retrieval of data: 'Get all ActivityWatch categories' and 'Returns the list of categories'. No modification, deletion, or execution is performed.
Attacks that exploit this kind of access
The rule that runs activitywatch_get_categories safely
PolicyLayer is an MCP gateway: it sits between your AI agents and ActivityWatch MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For activitywatch_get_categories, this is the rule to start with:
activitywatch_get_categories is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect ActivityWatch MCP Server, apply this rule, and every activitywatch_get_categories call is checked against it from then on.
Questions about activitywatch_get_categories
Get all ActivityWatch categories (classification rules). Returns the list of categories with their regex rules used to classify window events. It is categorised as a Read tool in the ActivityWatch MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ActivityWatch MCP Server MCP server in PolicyLayer and add a rule for activitywatch_get_categories: 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 ActivityWatch MCP Server. Nothing to install.
activitywatch_get_categories 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 activitywatch_get_categories 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 activitywatch_get_categories. 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.
activitywatch_get_categories is provided by the ActivityWatch MCP Server MCP server (8bitgentleman/activitywatch-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on ActivityWatch MCP Server, and thousands of servers like it.
This server
Across the catalogue