roblox-mcp

roblox-mcp is a skill for Codex from amyyzing/ai-mcp. It costs 78 tokens per session (909 once invoked), scanned A, original, MIT.

A guide for using an MCP connection to inspect and intentionally modify a live Roblox client with Luau, Roblox’s scripting language. It covers finding instances, inspecting scripts and runtime data, and choosing tools for reads or side effects.

In plain words
What is it for?
Use it to search live Roblox instances, inspect scripts and remote data, query runtime objects, run Luau that returns values, or execute and verify an intentional client-side change.
Why use it?
It helps an agent inspect only the relevant parts of a running Roblox game and avoid broad, inefficient scans. It also defines when to verify a change after deliberately modifying the client.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to search live Roblox instances, inspect scripts and remote data, query runtime objects, run Luau that returns values, or execute and verify an intentional client-side change.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/amyyzing/ai-mcp/roblox-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add amyyzing/ai-mcp --skill roblox-mcp
Clone the repo
git clone --depth 1 https://github.com/amyyzing/ai-mcp

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for roblox-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/amyyzing/ai-mcp/roblox-mcp/github.svg)](https://agentmods.dev/skills/amyyzing/ai-mcp/roblox-mcp)
Your own site
<a href="https://agentmods.dev/skills/amyyzing/ai-mcp/roblox-mcp"><img src="https://agentmods.dev/badge/skills/amyyzing/ai-mcp/roblox-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for roblox-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/amyyzing/ai-mcp/roblox-mcp"><img src="https://agentmods.dev/badge/skills/amyyzing/ai-mcp/roblox-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 909 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.00909
Opus 5 $0.00039 $0.00454
Sonnet 5 $0.00016 $0.00182
Haiku 4.5 $0.00008 $0.00091

Measured 11d ago against content hash 76aacee7aa69, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

roblox-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/roblox-mcp/SKILL.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Roblox MCP

Use the connected MCP server's live tool schemas as the source of truth for names, parameters, defaults, and limits.

Core decision rules

Apply these defaults unless the task meets an exception in references/runtime-patterns.md:

  1. Prefer a specialized read tool over arbitrary Luau.
  2. Use search-instances for filtered instance discovery. It runs QueryDescendants; do not fetch every descendant and filter it manually.
  3. In custom Luau, use QueryDescendants for selector-expressible instance filters instead of a GetDescendants() scan.
  4. Use search-gc for one compact first match. Use gc-snapshot + gc-query when the task needs reusable handles, pages, diffs, statistics, or reference traversal. Use raw filtergc only when neither structured query surface can express the predicate.
  5. Use get-data-by-code when the task needs values returned from Luau. Return compact raw Lua values; do not print data through execute or JSON-encode it manually.
  6. Use execute or execute-file only for intentional side effects or code that does not need to return data. Verify the effect with a focused read.

Operating workflow

  1. Select the client. Call list-clients when the target is unclear or multiple clients may exist, then call set-active-client if needed.
    • If connection, capability, mapping, or decompiler health is uncertain, call runtime-status.
  2. Narrow with the cheapest specialized tool:
    • One known instance: inspect-instance; discovery: search-instances, or get-descendants-tree with summaryOnly=true.
    • Script metadata: script-index-status, then script-index-start if needed, followed by list-scripts.
    • Known text or identifier: script-grep.
    • Unknown implementation with known behavior: semantic-search-scripts. Confirm remote embedding upload only when the configured endpoint is trusted; local Ollama stays local.
    • Source: get-script-content with a focused line range.
    • Luraph-protected source: use operation=run for an indexed script or operation=run-source for raw source already in hand. Raw source does not require a Roblox client. Start with captureMode=strict, page with operation=read, release when finished, and retry with sandboxed only if strict mode stops at an intermediate tree.
    • Arbitrary compact values: get-data-by-code.
    • One GC function/table: search-gc. Deeper runtime investigation: executor-capabilities, then gc-snapshot, gc-query, and runtime-inspect/runtime-references.
  3. Reduce the root, selector, range, filters, and limit before increasing any output budget.
  4. For GC or custom instance probes, follow references/runtime-patterns.md.
  5. Mutate only when the user's request authorizes mutation. Use execute or execute-file, then verify the resulting state with a specialized read, a targeted get-data-by-code probe, or a small console read.
  6. For remotes, call remote-spy with operation=list, a small limit, and summaryOnly=true before requesting arguments or changing capture state.
  7. Report the observed result. Top-level execution acknowledgement is not proof that the intended in-game state changed; verify that state separately.
  8. Use wait-for-event cursors for console and non-selector instance journals instead of repeatedly polling snapshots. Selector, attribute, and remote waits observe from call start (or current state with includeExisting).

Read the full file on GitHub · 42 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 42 lines · 78 tokens per session scan A 76aacee7aa69

Subscribe to this mod's changes

roblox-mcp is a skill published in the GitHub repository amyyzing/ai-mcp (0 stars, last pushed 8d ago), licensed MIT. It adds 78 tokens to every session and 909 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

gameobject-component-destroy

Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.

IvanMurzak/Unity-MCP · 49 tokens

unity-version-split

Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).

IvanMurzak/Unity-MCP · 59 tokens

godot-signals-groups

Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…

gamedev-skills/awesome-gamedev-agent-skills · 95 tokens

motion

How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.

OpenDCAI/GameFactory-3A · 0 tokens

unity-addressables

Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).

Besty0728/Unity-Skills · 25 tokens

threejs-exposure-color-grading

Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.

scottstts/Threejs-Awesome-Graphics-Agent-Skills · 60 tokens