Skip to main content
Glama

Run a Lua file from disk

run_file
Destructive

Reads a local .lua, .luau, or .txt script file and executes it in the connected Roblox executor without pasting code.

Instructions

Read a .lua, .luau or .txt file from this computer and run it in the connected Roblox executor, like execute_lua but without pasting the code. The path is on the computer that runs the Superbase MCP server (absolute, or relative to its working folder; ~ is the home folder). Files up to 500 KB. The code runs with the executor's full permissions, so only run files the user asked for. Requires the connected state.

Input Schema

NameRequiredDescriptionDefault
pathYesPath of the file on this computer.
clientNoClient id from list_clients, for example c2. Defaults to the client that connected last.
timeout_msNoHow long to wait for the code to finish (default 15000).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.4.0

TDQS

A4.2/5.0
Behavior4/5

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

Beyond the annotations (readOnly=false, destructive=true), the description discloses the 500 KB file-size ceiling, that code executes with the executor's full permissions, and the connected-state requirement — all material for a destructive write. It does not say what happens on failure or what the call returns.

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?

Five short sentences, front-loaded with the action and sibling differentiation, then constraints. Nothing is redundant or padded.

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 three parameters, full schema coverage and annotations carrying the safety profile, the description supplies what an agent needs to select and invoke it. The one gap is the absence of any statement about results or error behavior, with no output schema to fill that in.

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%, so the baseline is 3. The description does add the path resolution rules (absolute, relative to the server's working folder, ~ expansion), but client and timeout_ms are left entirely to 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?

"Read a .lua, .luau or .txt file from this computer and run it in the connected Roblox executor" states a specific verb and resource, and the clause "like execute_lua but without pasting the code" explicitly separates it from the sibling execute_lua.

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?

The comparison to execute_lua plus "without pasting the code" tells an agent when this is the right choice, and "Requires the connected state" states a precondition. There is no explicit when-not-to-use clause beyond the caution about user intent, so it falls short of a 5.

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