Skip to main content
Glama
Sign In
agent-mcp

agent-mcp

by uukelele
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Shell

shell
Destructive

Run commands in the host environment with configurable timeouts or background execution; long-running processes return a PID and log path.

Instructions

Run a command in the host shell. timeout is in milliseconds (0 disables it). Set background=true to start a long-running process; the result contains its PID and log path.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "command": "<command>"
    },
    "name": "shell"
  }
}

Input Schema

NameRequiredDescriptionDefault
commandYes
timeoutNo
workdirNo
backgroundNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already flag destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the danger profile is partly covered by structured data. The description adds genuinely useful behavior for background mode (returns PID and log path) and the timeout unit, but says nothing about output truncation, permission requirements, or the consequences of an unconstrained destructive command, which is the most important thing to warn about here.

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?

Two tight sentences, front-loaded with the core action and followed immediately by the two non-obvious parameters. No filler, no restatement of the tool name.

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?

An output schema exists, so return values need no exhaustive treatment, and the background-mode return note is a reasonable extra. The gaps are workdir and any hint about safety or limits on an arbitrary host-shell executor, which keeps it below complete.

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 0%, so the description must carry all parameter meaning; it does well on timeout (milliseconds, 0 disables) and background (long-running, PID plus log path returned), which the bare schema does not convey. However workdir is never mentioned and command is left self-evident, so half the parameters remain undocumented.

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

Purpose4/5

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

"Run a command in the host shell" gives a specific verb (run) plus resource (host shell), which is enough to separate it from file-oriented siblings like read, write, edit, and grep. It stops short of explicitly naming those siblings as alternatives, so it lands just under the top mark.

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

Usage Guidelines2/5

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

The description explains how to use timeout and background but never says when to reach for shell versus read/grep/edit for the same job — the single most common routing decision for this tool. A long-running-process hint is present, yet there is no when-not guidance or mention of preferring dedicated tools for file inspection.

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

Deploy Server

Other Tools