Skip to main content
Glama

datastore

Destructive

Inspect and edit saved data for published Roblox games via Open Cloud, supporting read queries and confirmed writes for offline players only.

Instructions

Inspect/edit a PUBLISHED game's saved data via the Open Cloud DataStore API (server-side HTTP, no Studio runtime). READ actions: list_datastores, list_keys, get, list_ordered, get_ordered. WRITE actions (gated — need confirm:true and are blocked in read-only mode): set, delete, increment. ⚠ SESSION-LOCK WARNING: a live game server owns the keys of ONLINE players (ProfileStore session lock); the REST write path ignores that lock, so writing such a key either gets overwritten by the server's autosave or corrupts the live session. Only write keys for OFFLINE players. ⚠ SHARED BUDGET: since 2026-07-29 Open Cloud DataStore calls count against the SAME unified per-experience request budget as the live game's in-game DataStore calls (base 300 + CCU × multiplier per request type/minute) — heavy MCP-driven reads/writes can starve a running game; watch the quota: line when the API returns rate-limit headers. Needs an Open Cloud key with universe-datastores scopes (TUFAN_OPENCLOUD_KEY) and a published universe (auto-detected from game.GameId, or TUFAN_UNIVERSE_ID).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "datastore"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNomax results per page
orderNosort for list_ordered (default asc; desc = top-first leaderboard)
placeNoTarget place (PlaceId or project name). Defaults to the bound/sole connected place.
scopeNoDataStore scope (default "global")
valueNothe JSON value to store (set)
actionYesWhat to do. Reads: list_datastores, list_keys, get, list_ordered, get_ordered. Writes (need confirm true): set, delete, increment.
cursorNopagination cursor / page token from a previous call
prefixNoname/key prefix filter (list actions)
confirmNoREQUIRED for write actions (set/delete/increment) — acknowledges the session-lock risk
userIdsNoassociated user ids to tag on the entry (set)
entryKeyNothe entry key (required for get/set/delete/increment/get_ordered)
allScopesNolist keys across all scopes (list_keys) — mutually exclusive with scope
attributesNoentry metadata (set)
incrementByNoamount to add (increment)
matchVersionNoonly write if the current version matches (set)
datastoreNameNothe DataStore name (required for standard entry actions)
exclusiveCreateNoonly create if the key doesn't exist yet (set)
orderedDataStoreNoordered datastore name (list_ordered / get_ordered)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.1
    • addedInput schema / properties / action / description
      Added value: +"What to do. Reads: list_datastores, list_keys, get, list_ordered, get_ordered. Writes (need confirm true): set, delete, increment."
  2. First observedv0.1.0

TDQS

A4.1/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false, openWorldHint=true and non-idempotent, but the description adds genuinely non-derivable behavior: writes ignore the ProfileStore session lock and can be overwritten by autosave or corrupt a live session, and calls share a unified per-experience request budget with the live game (base 300 + CCU × multiplier). That is strong beyond-annotation disclosure. It does not describe the shape of responses or how pagination cursors terminate, which keeps it below the top band.

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-loaded with purpose, then the action taxonomy, then the risk warnings — a sensible order with no filler sentences. It is dense and long, with two stacked ⚠ blocks, but each warning guards against a destructive, hard-to-notice failure mode, so the length is largely earned.

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

Completeness4/5

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

For an 18-parameter, destructive, multi-action tool with no output schema it covers the essentials: auth/env requirements, universe auto-detection, write gating, concurrency hazards, and rate-limit budget. The main gap is return-shape and pagination guidance (cursor reuse, page size), which matters here because there is no output schema to fall back on.

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

Parameters3/5

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

Schema description coverage is 100% across 18 parameters, so the schema already carries the per-parameter semantics and the baseline is 3. The description adds rationale rather than new parameter meaning — it explains why confirm exists (acknowledging the session-lock risk) and that writes are gated, but does not clarify ambiguous combinations such as scope vs allScopes or matchVersion/exclusiveCreate semantics.

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?

Opens with a specific verb pair and resource — "Inspect/edit a PUBLISHED game's saved data via the Open Cloud DataStore API (server-side HTTP, no Studio runtime)" — and then enumerates the exact action set (list_datastores, list_keys, get, set, delete, increment, list_ordered, get_ordered). It also implicitly distinguishes itself from the Studio-runtime siblings by stating the HTTP/no-runtime path, so an agent knows this is not a Studio-bound tool.

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 splits READ vs WRITE actions, states that writes require confirm:true and are blocked in read-only mode, and gives a hard condition on when writes are permissible: "Only write keys for OFFLINE players." It also names the prerequisite environment (published universe, Open Cloud key with universe-datastores scopes), which is the practical when-to-use gate.

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