local-vitals-mcp

clean_orphan_processes

Detect and terminate orphaned background processes left by AI agents, such as headless browsers, zombie test workers, and stray Node daemons. Use dry run mode to preview candidates and potential RAM savings first.

Instructions

Scans and cleans orphaned/zombie background processes commonly abandoned by AI agents (e.g. headless Playwright/Chrome instances, zombie test workers, orphaned Vite/Node daemons).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "clean_orphan_processes"
  }
}

Input Schema

Name	Required	Description	Default
`dryRun`	No	If true, only lists identified orphan candidates and potential RAM savings without terminating them. Defaults to false.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Nov 10, 2026

TDQS

B3.4/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must fully disclose behavior. While it hints at termination by saying "cleans," it never explicitly states that processes are killed, whether termination is irreversible, what signals are sent, or whether permissions/confirmation are required. This is a significant gap for a potentially destructive cleanup tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single front-loaded sentence that states the action and scope before listing examples. It is efficient with no redundant wording, though a slightly clearer separation of scan-vs-clean phases might improve structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations and no output schema, the description carries the full burden of behavioral disclosure. It identifies targets well but omits critical safety context such as irreversibility, termination method, and expected output format, leaving the agent under-informed about side effects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the single dryRun parameter is fully documented in the schema with its default and effect (list vs terminate). The description adds no additional parameter meaning beyond what the schema already provides, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb pair ("Scans and cleans") with a precise resource ("orphaned/zombie background processes") and concrete examples (Playwright/Chrome, test workers, Vite/Node daemons). This clearly distinguishes it from siblings like kill_port_process or inspect_port, which target specific ports rather than orphaned processes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase "commonly abandoned by AI agents" implies a usage context, but the description does not explicitly state when to use this tool versus alternatives such as kill_port_process or inspect_port. No exclusion conditions or direct routing to siblings are provided, leaving the agent to infer applicability.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server