Skip to main content
Glama
Claude Free Code MCP

Claude Free Code MCP

by ImIpscanning

run_command

Destructive

Execute approved developer commands such as npm, git, or python with argument arrays, workspace-relative cwd, and timeouts for controlled coding workflows.

Instructions

Run a chosen developer executable using argument-array (no implicit shell), workspace cwd, timeout and human approval.

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>",
      "args": "<args>",
      "reason": "<reason>"
    },
    "name": "run_command"
  }
}

Input Schema

NameRequiredDescriptionDefault
cwdNoRelative working directory.
argsYesArgument strings
reasonYesExplain why this command is necessary
commandYesExecutable from command_catalog
timeoutSecondsNo1..180 seconds

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and a closed world, but the description adds important behavior the annotations do not: invocation uses an argument array with no implicit shell, cwd is the workspace, timeouts apply, and human approval is involved. That is meaningful context for a destructive execution tool, though the consequences of timeout or non-zero exit are not described.

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?

A single front-loaded sentence that packs the key behavioral facts -- no implicit shell, workspace cwd, timeout, approval -- with no filler or redundant restatement of the schema.

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?

For a destructive, closed-world command execution tool with no output schema, the description covers the critical safety and invocation facts: argument-array form, working directory, timeout, and human approval. It leaves minor gaps around failure behavior and return values, but nothing essential for calling it safely is missing.

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 all five parameters, including the command enum and timeout bounds, are already documented. The description reinforces the argument-array and cwd semantics and ties 'human approval' to the required reason, but adds little syntax or meaning beyond the schema, so the baseline of 3 applies.

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?

States a specific verb and resource: 'Run a chosen developer executable,' scoped to argument-array invocation, workspace cwd, timeout, and approval. It is clearly distinct from read-only siblings like command_catalog, though it never names an alternative such as run_task, so the differentiation is inferable rather than explicit.

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 'Run a chosen developer executable' and the mention of human approval, which signals a guarded execution path. There is no explicit when-to-use versus run_task or command_catalog, no when-not-to-use, and no stated prerequisite for obtaining approval before calling.

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