Skip to main content
Glama
Sign In
local-context

local-context

by JustinA988
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

run_command

Destructive

Execute a single shell command inside an allowed root with capped output and a sanitized environment, so local tasks can run without exposing Anthropic credentials.

Instructions

Run one command inside an allowed root. Output is capped. Anthropic credentials are removed from the child environment.

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": "run_command"
  }
}

Input Schema

NameRequiredDescriptionDefault
cwdNoWorking directory inside a root.
commandYesCommand line.
timeout_secondsNoTimeout, capped by server config.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and openWorldHint=true, so the risk profile is covered. The description adds two genuinely useful facts beyond them: output is capped, and Anthropic credentials are stripped from the child environment. It still omits whether the command runs through a shell, how exit codes/stderr are surfaced, and the actual cap size.

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?

Three short sentences, zero filler, and the two facts that most affect an agent's decision (single command, capped output) are front-loaded. Nothing could be cut without losing information.

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?

For a destructive shell-execution tool the safety framing is adequate, but key operational details are missing: what defines an 'allowed root', whether shell metacharacters/chaining are permitted, and how the result (exit code, stderr, truncation marker) is returned when no output schema exists.

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 description coverage is 100%, so cwd, command, and timeout_seconds are already documented. The description's only related addition is that the working directory must sit inside an allowed root, which the schema's cwd text already conveys, so it adds little beyond the structured fields.

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 one command inside an allowed root" gives a specific verb (run), a bounded resource (a single command line), and a scope constraint (allowed root). It is clear enough to distinguish from siblings such as run_task or query_sql, though it never names an alternative explicitly.

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 states a constraint (must be inside an allowed root) but gives no when-to-use guidance and no comparison against sibling tools like run_task, query_sql, or read_file. An agent must infer that this is the escape hatch for arbitrary shell execution.

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