Skip to main content
Glama

Find agents nobody is watching

check_agents
Read-only

Lists coding agents running unattended, idle sessions, scheduled jobs, exported API keys, and leftover dev servers, including billing source and variable names without values; read-only.

Instructions

List coding agents that run without a human on this machine: agent processes (Claude Code, Codex, Gemini, Cursor, Aider...), sessions still working with no human message for hours, scheduled agents (cron, launchd/systemd, GitHub Actions schedules) with the account each one bills (subscription or API key), API keys exported by shell start-up files, and dev servers left running. Prints variable names, never values. Read-only: it never stops anything.

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": "check_agents"
  }
}

Input Schema

NameRequiredDescriptionDefault
idle_hoursNoFlag sessions with no human message for this long. Default 2.
running_hoursNoFlag agent processes running longer than this. Default 12.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is mostly provided. The description nevertheless adds meaningful non-annotation context: it will print variable names but never secret values, it reports the billing account per agent, and it explicitly restates that it stops nothing — useful reassurance for a secrets-adjacent scan. It stops short of describing output shape, ordering, or cost of the scan.

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 purpose is front-loaded in the first clause, and the trailing enumerations plus the two closing sentences each contribute real scope or safety information rather than filler. It is dense and long-ish for a two-parameter read tool, but nearly every clause earns its place by delimiting what is scanned.

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

Completeness4/5

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

With only two optional, fully documented parameters, safety covered by annotations, and no output schema, the description supplies what is missing by indicating the kinds of findings returned (processes, sessions, schedules with billing account, key variable names, dev servers). Only finer output expectations — grouping, counts, ordering — remain unstated.

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 both parameters already carry descriptions plus defaults, so the description owes little here. Its phrasing about sessions 'with no human message for hours' and processes 'left running' loosely maps to idle_hours and running_hours but adds no thresholds, units, or edge-case behavior beyond the schema.

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 opens with a specific verb and resource — 'List coding agents that run without a human on this machine' — then enumerates the exact categories it covers (agent processes, idle sessions, scheduled agents, exported API keys, dev servers). It is unmistakably distinct from the skill/query/scan siblings, so an agent can select it without opening the schema.

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?

Usage is implied by the framing ('agents nobody is watching') and by the closing scope note 'it never stops anything', which tells the agent this is a discovery-only tool. However, no explicit when-to-use trigger, prerequisite, or named alternative is given, so the agent must infer that this is an audit/reconnaissance call.

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