Skip to main content
Glama
EL4CTEO

Roblox Studio MCP

by EL4CTEO
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

Run, pause and stop the simulation

playtest
Destructive

Start, run, or stop Studio simulation sessions and read their state, so scripts execute and can be observed without the user pressing anything.

Instructions

Starts and stops playtests, so scripts can be made to run and then observed without asking the user to press anything.

play is the Play button: a character spawns and Players.PlayerAdded fires. run is Run mode, which executes scripts with no player at all. multiplayer starts a test with several players for testing replication. addPlayers joins more players to a running multiplayer test, for late joins and lobby fill-up. state reports without changing anything.

Play and multiplayer return the playtest server's studioId once it connects. Use that ID directly for console, performance and execute_luau; the editor session has a separate log. If connection takes too long, the reply says so and list_studios can find it later.

A test does not block this call: it starts and the reply reports the state reached. Studio only ends it when something inside calls StudioTestService:EndTest(value) or when stop is used here; whatever EndTest passed comes back as lastResult on a later state. That makes a scripted check possible end to end: args is readable inside the test via StudioTestService:GetTestArgs(), so a test can be told what to do and report back what happened.

Stopping discards everything the playtest changed, exactly as pressing Stop does. Build in edit mode, then play — not the other way round.

The reply says whether the mode actually moved, not merely that Studio accepted the request.

The panel's playtests on grants permission, never a requirement: obey AGENTS.md, CLAUDE.md, user instructions and project guidance that prohibit playtesting even when ON. playtests off is a hard MCP lock: play, run, multiplayer and addPlayers are refused regardless of instructions to test; state and stop remain available. The lock only blocks starting simulation: screenshots, tree, inspect, script reads, edit-mode execute_luau and UI inspection stay available. Continue using edit-mode tools and static inspection where possible. Only the user can re-enable it with playtests on in the panel. Do not bypass the lock through execute_luau, Studio APIs or another operation. Manual Studio Play is unaffected.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
opYes'play' starts a playtest with a character, 'run' runs scripts with no player, 'multiplayer' starts a several-player test, 'addPlayers' joins more to a running multiplayer test, 'stop' ends it and discards its changes, 'state' only reports.
argsNoValue handed to the test, readable inside it with `StudioTestService:GetTestArgs()`. Use it to tell a test which case to exercise.
playersNomultiplayer: how many players to start (default 2). addPlayers: how many to add (default 1).
studioIdNoTarget Studio; omit for the active one.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.8.6
    • changedInput schema / properties / op / description
      Previous value: -"'play' starts a playtest with a character, 'run' runs scripts with no player, 'multiplayer' starts a several-player test, 'stop' ends it and discards its changes, 'state' only reports."New value: +"'play' starts a playtest with a character, 'run' runs scripts with no player, 'multiplayer' starts a several-player test, 'addPlayers' joins more to a running multiplayer test, 'stop' ends it and discards its changes, 'state' only reports."
    • changedInput schema / properties / op / enum
      Previous value: -[
-  "play",
-  "run",
-  "multiplayer",
-  "stop",
-  "state"
-]New value: +[
+  "play",
+  "run",
+  "multiplayer",
+  "addPlayers",
+  "stop",
+  "state"
+]
    • removedInput schema / properties / players / default
      Removed value: -2
    • changedInput schema / properties / players / description
      Previous value: -"multiplayer only: how many players to start."New value: +"multiplayer: how many players to start (default 2). addPlayers: how many to add (default 1)."
  2. First observedv0.1.8

TDQS

A4.8/5.0
Behavior5/5

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

Far exceeds the annotations (destructiveHint, idempotentHint, openWorldHint): it discloses that stopping discards all playtest changes, that the call is non-blocking, that EndTest's value surfaces as lastResult, that play/multiplayer return a studioId, connection-timeout behavior, and the permission/lock model including an explicit anti-bypass warning.

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-loads the op semantics, then behavior, then permission rules, and every section is functional. It is on the long side (~300 words), but the tool has six ops plus a permission lock, so the length is largely justified rather than padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries return-value disclosure itself: studioId on connect, the state reached, and lastResult on a later state call. Nothing an agent needs to call this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% so the schema already documents each param, but the description adds meaning beyond it: the returned studioId is linked to downstream tools (console, performance, execute_luau), and args is framed as the way to tell a test which case to exercise.

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?

States a specific verb+resource (starts/stops playtests) and enumerates each op's distinct effect (play spawns a character, run executes scripts with no player, multiplayer/addPlayers manage multi-player tests, state reports only). It is clearly distinguishable from siblings like execute_luau and list_studios.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly describes when each op applies and when not: build in edit mode then play, use studioId for console/performance/execute_luau, and use edit-mode tools when `playtests off` locks starting simulation. Names the alternative behaviors (state/stop remain available) and exclusions (lock only blocks starting simulation).

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

Deploy Server

Other Tools