activitywatch-run-query · ActivityWatch MCP Server MCP

WHAT IT DOES

What activitywatch-run-query does on ActivityWatch MCP Server

AI agents invoke activitywatch-run-query to trigger actions in ActivityWatch MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why activitywatch-run-query needs a policy

This tool executes queries whose effects depend on the query arguments provided by the AI agent. Even though ActivityWatch is a read-heavy time-tracking system, a query engine can extract sensitive temporal data (work patterns, application usage, location history via timestamps).

From the tool's definition Tool name 'activitywatch-run-query' indicates execution of arbitrary queries against ActivityWatch data; description is empty but sibling tools (get-events, get-settings, list-buckets, query-examples) confirm this is a query engine.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

activitywatch-run-query Rate-limited

activitywatch-run-query stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "activitywatch-run-query": {
      "limits": [
        {
          "counter": "activitywatch-run-query_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches ActivityWatch MCP Server, so you can run agents against it safely.

FAQ

Questions about activitywatch-run-query

What does the activitywatch-run-query tool do? +

activitywatch-run-query. It is categorised as a Execute tool in the ActivityWatch MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on activitywatch-run-query? +

Register the ActivityWatch MCP Server MCP server in PolicyLayer and add a rule for activitywatch-run-query: 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.

What risk level is activitywatch-run-query? +

activitywatch-run-query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit activitywatch-run-query? +

Yes. Add a rate_limit block to the activitywatch-run-query 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.

How do I block activitywatch-run-query completely? +

Set action: deny in the PolicyLayer policy for activitywatch-run-query. 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.

What MCP server provides activitywatch-run-query? +

activitywatch-run-query is provided by the ActivityWatch MCP Server MCP server (jelloeater/activitywatch-mcp-server-py). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.