Skip to main content
Glama
EL4CTEO

Roblox Studio MCP

by EL4CTEO
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

Inspect instances

inspect
Read-onlyIdempotent

Read properties, attributes, tags, and children of Roblox instances in one batch call. Invalid paths return separately, so valid results still come through.

Instructions

Reads properties, attributes, tags and children of one or more instances. Pass every path you care about in a single call — batching costs one round trip instead of N.

Property selection comes from the live Roblox API dump for each instance's actual class, so it stays correct across engine updates: concise — class and child count only standard — the properties that characterise the class (Part gets Size, Position, CFrame, Anchored, Material...) full — every readable property; expensive, use on one or two instances at most

Bad paths do not fail the call: they come back under failures while the valid ones still return, so one typo does not cost you the whole batch.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathsYesInstance paths, e.g. ["Workspace.Baseplate", "Lighting"].
detailNoconcise: compact identity. standard: selected facts. full: all readable properties for inspect; tree/find use the same columns as standard.standard
physicsNoAlso report mass, density, assembly root and centre of mass for any BasePart. Mass appears nowhere in Studio — it is computed from volume and material — so this is the only way to answer 'why does this fall over', 'why does it sink', or 'why did half the model stay behind when I moved it'.
studioIdNoTarget Studio; omit for the active one.
propertiesNoRead exactly these properties instead of the detail-level default. Use when you want one specific value across many instances.
includeChildrenNoInclude a name/class listing of direct children.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.8.6
    • changedInput schema / properties / detail / description
      Previous value: -"How much to return per item. 'concise' = name + class only, cheapest, use when scanning or counting. 'standard' = the properties that matter for most edits. 'full' = every readable property, expensive — use only after you have narrowed to a handful of instances."New value: +"concise: compact identity. standard: selected facts. full: all readable properties for inspect; tree/find use the same columns as standard."
  2. Changed1 schema field changedv0.6.5
    • addedInput schema / properties / physics
      Added value: +{
+  "default": false,
+  "description": "Also report mass, density, assembly root and centre of mass for any BasePart. Mass appears nowhere in Studio — it is computed from volume and material — so this is the only way to answer 'why does this fall over', 'why does it sink', or 'why did half the model stay behind when I moved it'.",
+  "type": "boolean"
+}
  3. First observedv0.1.8

TDQS

A4.2/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is low, and the description clears it with non-obvious behavior: bad paths do not fail the call, they are returned under `failures` while valid instances still resolve. That partial-success contract plus the cost profile of the 'full' detail level and the live API-dump sourcing are exactly the kind of context an agent cannot get from the annotations.

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 core action, then the batching advice, then a scannable breakdown of the three detail levels, then the failure semantics. Every paragraph carries information, though the API-dump justification sentence is slightly more explanation than the agent strictly needs to make the call.

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?

With six parameters, full schema coverage and a complete annotation set, the description fills the remaining gaps: it covers the detail-level tradeoff, batching strategy, and one failure key in the response. It is nearly complete, but with no output schema it still leaves the overall response shape to inference beyond the mention of `failures` and the child listing.

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 adds meaning beyond the schema: it explains that property selection is derived from the live Roblox API dump for each instance's actual class and stays correct across engine updates, and gives a concrete example of what 'standard' yields for a Part (Size, Position, CFrame, Anchored, Material).

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?

Opens with a specific verb and resource set: 'Reads properties, attributes, tags and children of one or more instances', which tells the agent exactly what comes back. It is clear and self-contained, but it never names or contrasts itself with the read-oriented siblings (tree, find, script_read), so the agent must infer the boundary from the schemas of those tools.

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 real usage context: batch every path into one call because batching costs one round trip instead of N, and warns that 'full' is expensive and should be limited to one or two instances. It stops short of naming an alternative tool or stating an explicit when-not-to-use-this case (e.g. when 'tree' is the better choice).

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