Monitor multiple tasks until all complete.
AI agents call watch_tasks to retrieve information from Code Graph Knowledge System 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 task completion status without side effects. Monitoring/watching operations are read-only by nature. Even in the context of a code graph system with potentially sensitive repository data, the tool itself performs no operations on that data—it merely observes task progress.
From the tool's definition Tool name 'watch_tasks' and description 'Monitor multiple tasks until all complete' indicate passive observation of task status with no modification, creation, deletion, or execution capability.
Documented attack patterns abuse exactly the kind of access watch_tasks gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Code Graph Knowledge System, and nothing reaches the server without passing your rules. This is the rule we recommend for watch_tasks:
{
"version": "1",
"default": "deny",
"tools": {
"watch_tasks": {}
}
}watch_tasks is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Monitor multiple tasks until all complete. It is categorised as a Read tool in the Code Graph Knowledge System MCP Server, which means it retrieves data without modifying state.
Register the Code Graph Knowledge System MCP server in PolicyLayer and add a rule for watch_tasks: 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 Code Graph Knowledge System. Nothing to install.
watch_tasks 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 watch_tasks 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 watch_tasks. 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.
watch_tasks is provided by the Code Graph Knowledge System MCP server (royisme/codebase-rag). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Code Graph Knowledge System, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
30 Code Graph Knowledge System tools catalogued and risk-classified — across an index of 43,000+ MCP servers.