Skip to main content
Glama

Run command on webspace

webspace_exec
Destructive

Run a shell command as the webspace's unprivileged site user. Jailed to /home//. Returns { stdout, stderr, exitCode }, each output limited to 256 KB.

Use timeoutSeconds (default 60, max 300) for the per-command timeout. For longer work, launch in the background with nohup ... & and poll a log file (see vps_exec description for the pattern).

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": {
      "id": "<id>",
      "command": "<command>"
    },
    "name": "webspace_exec"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesThe webspace ID
commandYes
timeoutNoDEPRECATED: use `timeoutSeconds`. Same semantics (seconds).
timeoutSecondsNoPer-command timeout in seconds. Default 60, max 300.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description adds real substance on top: the sandbox boundary (unprivileged site user, jailed to home), the exact return shape { stdout, stderr, exitCode }, and a 256 KB truncation limit on each stream. The main gap is that it does not say whether truncated output is signaled, nor what happens to processes that outlive the command.

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?

Front-loaded with the identity and jail constraint, then return shape, then timeout guidance, then the long-running pattern. Three tight paragraphs with no filler; the timeout sentence largely duplicates the schema's own description of timeoutSeconds, which is the only wasted line.

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 no output schema, the description correctly supplies the return shape and output-size cap, plus timeout behavior and a workaround for long jobs, which is what an agent needs to call this safely. The one omission is a note on the deprecated `timeout` parameter or on privileged-operation limits relative to vps_exec.

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 75% and the schema itself documents id, timeoutSeconds, and the deprecated timeout. The description only restates timeoutSeconds' default and max, adding no new semantics, and it never mentions the deprecated `timeout` alias that the schema exposes, which is the one place an agent could pick the wrong parameter.

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 plus the execution context that makes it distinct: 'Run a shell command as the webspace's unprivileged site user' and 'Jailed to /home/<user>/'. That execution scope implicitly separates it from vps_exec, though it never names the boundary explicitly ('for host-level commands use vps_exec').

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?

Gives clear operational guidance: per-command timeout defaults and ceilings, and a concrete pattern for long-running work (nohup ... & plus polling a log file), pointing to vps_exec for the full pattern. It lacks an explicit when-not statement, e.g. that this cannot do privileged/system-level operations and those must go to vps_exec.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.