Skip to main content
Glama
okenjioxx

Roblox Executor MCP Server

by okenjioxx
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Snapshot an instance subtree and diff what an action changed

diff-instance-snapshot
Read-onlyIdempotent

Capture a baseline of a Roblox instance subtree, run an in-game action, then diff before and after to see which instances were added, removed, or changed.

Instructions

Answer 'what did clicking this button / firing this remote / opening this menu actually change in the game tree?' by snapshotting an instance subtree, performing the action in-game, then diffing the before/after. Workflow: (1) call action='snapshot' on a root (default game.Workspace) to capture a baseline; (2) do the thing in-game (click, fire a remote, walk somewhere, wait for a wave to spawn); (3) call action='compare' with the SAME name to see exactly which instances were ADDED, REMOVED, or CHANGED. How it works: it walks root:GetDescendants() (capped at maxInstances) and builds a per-instance signature from a handful of cheap properties (ClassName, Name, Parent, and whichever of Position/Transparency/Value/Text/Visible/Anchored/Health/Enabled exist). 'changed' entries report the before and after signatures so you can see precisely which property moved (a part teleported, a value bumped, a label retexted, a GUI shown). State is stored CLIENT-SIDE in getgenv().__mcp_snapshots[name], so baselines persist across tool calls and are naturally isolated per game / per session. Use distinct names to keep several independent baselines. snapshot returns: { action='snapshot', name, root, captured, truncated }. compare returns: { action='compare', name, root, counts={ added, removed, changed }, added=[paths], removed=[paths], changed=[{ path, before, after }], truncated=bool }. Non-mutating and fully pcall-guarded (locked/destroyed instances are skipped, never aborting the scan). Each detail list is capped at 200 entries; the exact counts are always reported. Signature: { action: "snapshot" | "compare", root: any?, name: any?, maxInstances: any?, threadContext: number? }. Phase: verify; cost=medium; idempotency=read-only. Requires: active-client. Produces: structured-result. Safety: read-only. On failure: inspect tool-schema for exact fields, defaults, constraints, and an invocation example.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoSlot/name for the snapshot (default 'default'). compare diffs against the baseline stored under this same name. Use distinct names to keep several independent before/after pairs around at once.default
rootNoLuau expression for the root instance of the subtree to snapshot/diff (default 'game.Workspace'). Examples: 'game.Workspace', 'game.Players.LocalPlayer.PlayerGui', 'game.Workspace:FindFirstChild("Map")'. Evaluated as `return <root>`. Pick the smallest subtree that contains what you expect to change — a tighter root means a faster, less noisy diff.game.Workspace
actionYes'snapshot' captures a baseline signature map of the subtree under `name`. 'compare' re-walks the subtree now and diffs it against the stored baseline of that `name`, reporting added/removed/changed instances.
maxInstancesNoMax descendants to walk per pass (default 4000). The walk stops at this many and flags `truncated`; a truncated baseline plus a truncated compare can produce spurious added/removed near the cap, so prefer a tighter root over a huge cap.
threadContextNoOptional Roblox thread identity for this call; omit it to use the server default.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0-spies.2

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial non-obvious behavior: state lives client-side in getgenv().__mcp_snapshots[name] and persists across calls, per-game/per-session isolation, the maxInstances cap and its truncation risk, pcall-guarding that skips locked/destroyed instances, and the 200-entry detail cap with exact counts always reported.

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 the driving question, then the numbered workflow, then mechanics, then return shapes; nearly every sentence carries information. Minor redundancy appears in the tail ('Non-mutating', 'idempotency=read-only', 'Safety: read-only' restate the same trait) and the signature/phase line duplicates schema content.

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 compensates fully by spelling out both return payloads (snapshot's {action,name,root,captured,truncated} and compare's counts/added/removed/changed shapes). For a 5-param verify-phase tool, an agent has everything needed to call and interpret it.

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 baseline is 3, but the description contributes extra meaning: it clarifies that 'name' is the pairing key shared by snapshot and compare, that 'root' is an evaluated Luau expression with examples, and that a tighter root yields a faster/less noisy diff and mitigates truncation near maxInstances.

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 ('snapshotting an instance subtree, performing the action in-game, then diffing') framed around a concrete question the agent would ask. It is clearly separable from siblings like compare-instances, watch-value, and get-instance-tree because it pairs a pre/post snapshot around an in-game action rather than a live subscription or a static tree dump.

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?

Gives an explicit three-step workflow (snapshot → do the thing in-game → compare with the SAME name) and advises picking the smallest root and distinct names for independent baselines. It stops short of naming alternative sibling tools or stating when this approach is the wrong choice, so it is clear context but not full when/when-not routing.

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