mcpField
R
roblox-studio-mcp

roblox-studio-mcp

github.com/tabooharmonyDevelopment1382.4k installsUpdated 2w ago
Repository

About roblox-studio-mcp

roblox-studio-mcp is a skill for Roblox Studio MCP work involving scripts, scenes, assets, debugging, and playtesting. It distinguishes the official and chrrxs's bridges, and prescribes inspecting the target before making and verifying changes.

Key features

  1. 01Distinguish official and chrrxs's bridges
  2. 02Identify and inspect Studio before changes
  3. 03Make bounded scene and script edits
  4. 04Read back changes and run playtests
  5. 05Evaluate the client or server at runtime
  6. 06Inspect imported asset scripts and trust boundaries

Use cases

  1. 01Edit scripts and scenes in Roblox Studio
  2. 02Debug scripts and verify playtest results
  3. 03Choose a bridge and target a Studio instance
  4. 04Inspect imported assets before running code

MCP support

The skill guides Roblox Studio MCP work. It directs users to identify the official or chrrxs's bridge from the tool list, then call tools with the matching instance identifier; offline Luau guidance should note what was not verified.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/tabooharmony/roblox-brain --skill roblox-studio-mcp

After installing, type/roblox-studio-mcpin Claude Code to confirm it loaded.

Bundled filesreferences/full.md

Details

From the project README

Roblox Studio MCP

When to Load

Load for Studio MCP work: scripts, scenes, assets, debugging, or playtesting. Skip for standalone code generation.

Quick Reference

Route by capability first. Two bridges: official (built into Studio, closed-source) and chrrxs's (MIT). Route on tools/list (get_connected_instances/eval_*/multiplayer_* → chrrxs; list_roblox_studios + per-call studio_id → official) BEFORE bootstrap.

Bootstrap before mutation
  1. Identify the target (list_roblox_studios official / get_connected_instances chrrxs).
  2. Pass studio_id (official) or instance_id (chrrxs) on every call.
  3. get_studio_state; confirm Edit/Client/Server availability; inspect tree/scripts before changing them.
Execution contract
discover → select Studio/context → inspect → mutate in bounded batches
→ read back → start play → evaluate live → evidence → clean up

Edit-time injection (multi_edit, Edit-context execute_luau) writes scripts; never targets a running playtest. Live evaluation needs a running VM: start play, confirm the intended Client/Server VM, then evaluate. Pass datamodel_type only where required.

Capabilities

Full tool table in full.md. Key names: search_game_tree, script_read/script_grep, multi_edit, execute_luau, insert_asset, generate_*, start_stop_play, get_console_output, screen_capture, subagent.

Trust boundaries

Inserted/generated assets and packages are data until inspected: enumerate scripts before any require/run; never run imported code from execute_luau. Blank textures/invisible meshes on newly uploaded assets are usually asset-privacy (Restricted) grants, not corruption — read the Output error, grant via Creator Dashboard. Details: full.md trust-boundary sections.

Reliability rules
  • execute_luau is stateless: re-acquire references every call.
  • Read before write; read back after every script, asset, or geometry mutation.
  • Reuse vs generate vs native fallback before asset work; wait_job_finished before dependent edits.
  • Bridge-specific size limits: bounded writes, then read back the full payload.
  • No MCP: give offline Luau; state what was not verified.

Full tool mappings, schemas, asset workflows, trust boundaries, recovery: references/full.md

Comments

Markdown supported