Skip to main content
Glama

prockill

Kill, suspend, or resume a process by PID or port. Supports tree kill, signal selection, and zombie process handling. Preview with dry_run.

Instructions

Kills, suspends, or resumes a process by PID or port number. Supports tree kill (process + all children), signal selection (kill/term/hup/int/stop/cont). Use signal=stop to suspend and signal=cont to resume a process. On Linux, can detect and handle zombie processes by signaling their parent. Use dry_run=true to preview which processes would be affected. Safety: refuses to target PID 0/1 or the agent-tool process itself.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pidNoProcess ID to kill
portNoKill process(es) using this port number
signalNoSignal to send: kill (default), term, hup, int, stop (suspend), cont (resume). Windows uses NtSuspendProcess/NtResumeProcess for stop/cont
treeNoKill the process and all its child processes (tree kill): true or false. Default: false
include_zombiesNoLinux only: send SIGCHLD to parent of zombie processes to trigger reaping: true or false. Default: false
dry_runNoPreview which processes would be killed without actually killing them: true or false. Default: false
Behavior4/5

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

No annotations exist, so the description bears full burden. It discloses safety (refuses PID 0/1 or itself), OS-specific behavior (Windows stop/cont), zombie handling, and dry run preview. Missing permission requirements and error behavior details.

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

Conciseness5/5

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

The description is concise, front-loaded with the main action, and every sentence adds value without redundancy. Essential details about safety, signal usage, and special features are efficiently packed.

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?

No output schema exists, but description omits return value format (e.g., success message, list of killed PIDs). It mentions dry run previews but doesn't specify output. Missing error handling details. Adequate but incomplete for a complex tool.

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

Parameters4/5

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

Schema coverage is 100%, baseline 3. The description adds meaning: explains signal values (stop/cont for suspend/resume), tree kill, zombie handling, and dry run. It clarifies that port can be used as alternative to pid.

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 clearly states the tool kills, suspends, or resumes processes by PID or port. It distinguishes from siblings like proclist (list) and procexec (execute) through specific action verbs and resource identification.

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

Usage Guidelines4/5

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

The description provides clear usage context: options like tree kill, signal selection, suspend/resume via stop/cont, and dry run. It covers when to use features like zombie handling and safety restrictions, but doesn't explicitly compare with alternatives or state when not to use this tool.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/knewstimek/agent-tool'

If you have feedback or need assistance with the MCP directory API, please join our Discord server