Find and kill orphaned SLM processes. Detects SLM embedding workers and other subprocesses whose parent has died (orphans). Safely terminates them with SIGTERM. Run with dry_run=True first to preview what would be killed. Args: dry_run: If True, report orphans but don't kill them.
AI agents invoke reap_processes to trigger actions in Qualixar/superlocalmemory. 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.
This tool executes external operations (process termination via SIGTERM signals) whose effects depend on runtime arguments and system state. While not permanently destructive in the data sense, killing processes can interrupt running workloads, corrupt in-memory state, and cause service disruption. This makes it Execute rather than Destructive, but with high severity due to potential system impact.
From the tool's definition Tool description explicitly states it "kill[s] orphaned SLM processes" and "terminates them with SIGTERM". The dry_run parameter confirms the tool performs process termination as its primary function.
Documented attack patterns abuse exactly the kind of access reap_processes gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Qualixar/superlocalmemory, and nothing reaches the server without passing your rules. This is the rule we recommend for reap_processes:
{
"version": "1",
"default": "deny",
"tools": {
"reap_processes": {
"limits": [
{
"counter": "reap_processes_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}reap_processes 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.
Free to start. No card required.
Find and kill orphaned SLM processes. Detects SLM embedding workers and other subprocesses whose parent has died (orphans). Safely terminates them with SIGTERM. Run with dry_run=True first to preview what would be killed. Args: dry_run: If True, report orphans but don't kill them. It is categorised as a Execute tool in the Qualixar/superlocalmemory MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Qualixar/superlocalmemory MCP server in PolicyLayer and add a rule for reap_processes: 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 Qualixar/superlocalmemory. Nothing to install.
reap_processes is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the reap_processes 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 reap_processes. 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.
reap_processes is provided by the Qualixar/superlocalmemory MCP server (qualixar/superlocalmemory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 59 Qualixar/superlocalmemory tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
59 Qualixar/superlocalmemory tools catalogued and risk-classified — across an index of 42,500+ MCP servers.