Skip to main content
Glama

Roblox Open Cloud

cloud
Destructive

Manage Roblox Open Cloud from Studio: access datastores, publish places, run Luau scripts, upload assets, enforce restrictions, and notify users.

Instructions

Roblox Open Cloud for the place open in Studio. IDs default to the connected session (universe = game.GameId, place = game.PlaceId, creator = the place owner); pass universe_id / place_id / id / creator only to override. Needs an API key: env ROBLOX_OPEN_CLOUD_KEY or /opencloud.json {"key":"…"}, re-read every call and never returned. A 403 names the exact Creator Hub permission to add — or call info what:"key" first: it probes the key and reports allowed | denied | unknown per action. action (ops in parens; arg help is on each field):

  • datastore (list_stores|list_entries|get|set|delete|increment), ordered (list|get|set|delete|increment): persistent entries; etag makes a set conditional.

  • memory (map_list|map_get|map_set|map_delete|queue_add|queue_read|queue_discard): MemoryStore sorted maps + queues, fast cross-server state with a ttl.

  • message: topic + message (≤1 KB) → MessagingService in live servers, not playtests.

  • info (universe|place|group|user|me|key|memberships|roles|inventory|subscription): reads. key = the capability probe.

  • publish: uploads a local .rbxl/.rbxlx as the place's new live version. Do this before luau / instance, which read the PUBLISHED place, never the Studio session.

  • asset_upload: file + asset_type (Model|Decal|Audio|Video|Animation|Mesh|Image) → asset_id + moderation. asset (get|update|versions|rollback|archive|restore): the rest of the lifecycle; update puts a new .fbx behind an existing Model asset_id.

  • luau: runs a script in a fresh server copy of the published place; returns results + logs.

  • instance (get|update|children): read/edit instances of the published place ("root" = the DataModel). For the OPEN place use the run tool.

  • restriction (list|get|ban|unban|logs): ban a user from the experience or one place.

  • notify: send an experience notification to a user (message_id = a Creator Hub template). Results are JSON ≤ 20 KB; long calls return pending: true + a re-poll handle after timeout_ms.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idNoinfo group/user/inventory/subscription: id; restriction: the player’s user id; notify: the user to notify
opNodatastore: list_stores|list_entries|get|set|delete|increment; ordered: list|get|set|delete|increment; memory: map_list|map_get|map_set|map_delete|queue_add|queue_read|queue_discard; asset: get|update|versions|rollback|archive|restore; restriction: list|get|ban|unban|logs; instance: get|update|children
keyNodatastore/ordered/memory map: entry or item key
deepNoinfo key: also probe writes that a delete against a reserved name can settle (nothing real is deleted)
etagNodatastore set: write only if the entry still has this etag (from get)
fileNoasset_upload / asset update (.fbx Models only) / publish: absolute path of the file
nameNoasset_upload / asset update: display name
taskNoluau: re-poll an earlier task path instead of creating one
whatNoinfo: universe | place | group | user | me (owner of the open place) | key (what this API key may do) | memberships | roles | inventory | subscription
countNomemory queue_read: how many items to read (default 1, max 200)
levelNorestriction: "universe" (default, the whole experience) or "place" (one place only)
scopeNodatastore: scope (omit = global); ordered: scope (default global)
storeNodatastore/ordered: data store name; memory: the sorted map or queue name (created by its first write)
topicNomessage: MessagingService topic (≤ 80 chars)
ttl_sNomemory map_set / queue_add: how long the item lives, in seconds
usersNodatastore set/increment: user ids the value belongs to
valueNoset ops: JSON value (ordered: integer; memory queue_add: the item payload)
actionYes
amountNoincrement: integer amount to add (negative allowed)
filterNolist_entries: id.startsWith("prefix"); ordered list: entry >= 10 && entry <= 30; memory map_list: sortKey > 100 (NOT numericSortKey); restriction logs: user == "users/156"; info memberships/inventory: see the reference
reasonNorestriction ban: the private moderation note (not shown to the player)
scriptNoluau: Luau source run server-side in a fresh copy of the published place
creatorNoasset_upload: owner (default: owner of the open place)
messageNomessage: string or JSON (≤ 1 KB)
read_idNomemory queue_discard: the read_id from queue_read — a whole read batch is acknowledged at once
versionNoasset rollback: the version number to restore (from asset versions)
asset_idNoasset ops: the asset to act on
order_byNoordered list: "value desc" (default ascending); memory map_list: only "id" / "id desc"
place_idNooverride: place (default game.PlaceId of the open place)
priorityNomemory queue_add: higher runs closer to the front (equal priorities keep insertion order)
sort_keyNomemory map_set: sort key — a number sorts numerically, a string alphabetically
page_sizeNolist ops: page size (memory and restrictions cap at 100, asset versions at 50)
read_maskNoasset get: comma-separated extra metadata fields to return
asset_typeNoasset_upload: Model | Decal | Audio | Video | Animation | Mesh (also Image)
attributesNodatastore set/increment: metadata object
class_nameNoinstance update: Folder | Script | LocalScript | ModuleScript — the only classes this API can write
duration_sNorestriction ban: length in seconds; omit entirely for a permanent ban
message_idNonotify: the notification string id from Creator Hub
page_tokenNolist ops: nextPageToken from the previous page
parametersNonotify: values for the {placeholders} in the notification string (string or integer each)
product_idNoinfo subscription: the subscription product id
propertiesNoinstance update: PascalCase properties, e.g. {"Source":"print(1)"} or {"Enabled":false}
timeout_msNolong calls: how long to wait (default 60000, max 300000)
descriptionNoasset_upload / asset update: description
instance_idNoinstance: the instance to act on; "root" (default) is the DataModel
launch_dataNonotify: launch data carried into the experience when the player taps (≤ 200 bytes)
universe_idNooverride: universe (default game.GameId of the open place)
exclude_altsNorestriction ban: do not extend the ban to detected alt accounts
operation_idNoasset_upload: re-poll an earlier upload operation instead of uploading
show_deletedNodatastore list ops: include deleted
version_typeNopublish: "Published" (default, goes live) or "Saved" (stored as a version without publishing)
all_or_nothingNomemory queue_read: return nothing (404) unless the full count is available
display_reasonNorestriction ban: the message the banned player sees
invisibility_sNomemory queue_read: seconds the read items stay hidden from other readers before reappearing
analytics_categoryNonotify: analytics category for this notification

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already mark destructive/write behavior to no surprise, and the description adds substantial operational context: API key resolution from env or file, re-read every call and never returned, 403 error messages naming the required permission, a built-in key probe (info what:'key'), return size limits, pending async handles, and the critical distinction that luau/instance read the published place, not the Studio session. These details go far beyond what annotations convey.

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?

The description is long but appropriately dense for a tool with 55 parameters across 12 actions. It front-loads the most critical constraints (defaults, authentication, error behavior) before listing actions, and each action group is compactly summarized. A few sentences could be tightened, but overall the structure aids scanning.

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?

Given the enormous scope and absence of an output schema, the description covers essentials: authentication setup, default scoping, override mechanism, error probing, result size limits, async polling pattern, publishing workflow, and where the tool does not apply (open place → run tool). No critical usage detail appears to be 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 98%, so the baseline is 3; the description adds meaningful cross-cutting semantics: default universe/place/creator resolution with overrides, etag-based conditional writes, memory store TTL behavior, message size limits, and the action-specific op groupings. It also refers users to field-level help ('arg help is on each field'), acknowledging the schema's completeness while clarifying global defaults.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear resource and scope: 'Roblox Open Cloud for the place open in Studio.' It enumerates a dozen distinct actions, making the tool's breadth apparent. However, it does not explicitly contrast with sibling tools like observe/run/playtest, though the name and subtitle imply a cloud API access role.

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 description gives explicit routing guidance: 'For the OPEN place use the run tool,' distinguishing when not to use this tool for instance operations. It also explains sequencing ('Do this before luau / instance, which read the PUBLISHED place, never the Studio session') and environmental caveats ('message … in live servers, not playtests'). While not covering every possible alternative, it provides clear context for major decision points.

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