roblox-mcp

roblox-mcp is a skill for Claude Code, Codex from Difz25x/roblox-mcp-difz. It costs 76 tokens per session (4,220 once invoked), scanned A, original, MIT.

A tool suite for connecting an agent to Roblox clients, the game-running programs used by players, through the roblox-mcp protocol. It supports inspecting games, running Luau scripts, automating input, and collecting telemetry.

In plain words
What is it for?
It is for Roblox game analysis, instance inspection, Luau execution, reverse engineering, RemoteEvent inspection, input simulation, and telemetry collection.
Why use it?
It provides a way to inspect and test Roblox sessions from an agent instead of relying only on manual play. It can target particular client processes or connected sessions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit It is for Roblox game analysis, instance inspection, Luau execution, reverse engineering, RemoteEvent inspection, input simulation, and telemetry collection.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/difz25x/roblox-mcp-difz/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 Difz25x/roblox-mcp-difz --skill roblox-mcp
Clone the repo
git clone --depth 1 https://github.com/Difz25x/roblox-mcp-difz

Made for: Claude Code, 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/difz25x/roblox-mcp-difz/roblox-mcp/github.svg)](https://agentmods.dev/skills/difz25x/roblox-mcp-difz/roblox-mcp)
Your own site
<a href="https://agentmods.dev/skills/difz25x/roblox-mcp-difz/roblox-mcp"><img src="https://agentmods.dev/badge/skills/difz25x/roblox-mcp-difz/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/difz25x/roblox-mcp-difz/roblox-mcp"><img src="https://agentmods.dev/badge/skills/difz25x/roblox-mcp-difz/roblox-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,220 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 $0.00076 $0.04220
Opus 5.5 $0.00030 $0.01688
Sonnet 5.5 $0.00015 $0.00844
Haiku 4.5 $0.00008 $0.00422

Measured 4d ago against content hash e63f5eb0dc77, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-06, 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 4d 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 · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Roblox MCP — Agent Engineering & Mastery Skill

This skill guides AI agents (Claude Code, Cursor, Windsurf, Copilot, etc.) on how, when, and why to use the roblox-mcp tool suite to automate, reverse-engineer, inspect, and test Roblox games across single or multiple Windows processes.


1. System Architecture & Session Routing

Roblox MCP operates as a bidirectional bridge connecting AI agents to in-game Roblox executor clients over WebSocket (ws://localhost:28429) with automatic long-polling HTTP Stream fallback. A background Discovery Router (http://127.0.0.1:58295) automatically resolves custom server ports.

Universal Session Targeting (workerId & pid)

Every tool accepts two universal, optional session routing arguments as its first properties:

  • workerId?: string: Target a specific client session by ID, username, or session name (e.g. "Worker_14388", "Player1").
  • pid?: number: Target a specific Roblox client window by operating system Process ID (e.g. 14388).
  • If omitted: The tool automatically executes across ALL active connected sessions or defaults to the primary active session.

2. Universal Argument Normalization (AI Error Tolerance)

The server features automatic bidirectional argument normalization. You do not need to worry about rigid schema mismatches:

  • Path & Instance Aliases: target_path, script_path, instance_path, target_part, part_path, path, target, and instance are completely interchangeable.
  • Casing: Both camelCase (e.g. targetPath, placeId, jobId) and snake_case (e.g. target_path, place_id, job_id) are accepted everywhere.
  • Code & Content: code, script, source, content, and lua are interchangeable.
  • Property Maps: property_map and properties accept either a stringified JSON string ('{"Transparency":0.5}') or a direct JSON object ({ "Transparency": 0.5 }).
  • Player Targets: player, player_name, username, and target_player are interchangeable.
  • Coordinates & Teleport: Accepts coordinates: { x, y, z }, flat x, y, z, player: "Name", or target_part: "workspace.Part".

Read the full file on GitHub · 207 lines

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. 4d ago First seen · 207 lines · 76 tokens per session scan A e63f5eb0dc77

Subscribe to this mod's changes

roblox-mcp is a skill published in the GitHub repository Difz25x/roblox-mcp-difz (12 stars, last pushed 5d ago), licensed MIT. It adds 76 tokens to every session and 4,220 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-02.

Related

Other skills, from other repositories

playtest-report

Structured playtest report template, or turn existing playtest notes into structured feedback.

Donchitos/Claude-Code-Game-Studios · 20 tokens

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

Reconstruct a skeleton from calibrated mesh projections and sequential VLM joint annotations, then fit joints and skin weights. Generate motion from joint-position trajectories, rhythm and contact constraints through IK; refine bone orientation against the action, then export, retarget and validate on the target mesh.

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