Roblox Studio MCP

Overview Schema Source Related Servers Discussions Admin

Find instances

find

Read-onlyIdempotent

Search an open Roblox Studio place for instances by name, class, property value, ancestor path, or CollectionService tag; multiple filters combine in one call.

Instructions

Searches the data model by name, class, property value and/or tag. Every filter you supply must match, so one call answers questions that would otherwise take several: "anchored BaseParts under Workspace.Map whose name contains door" is a single request.

This replaces separate name / class / property / tag search tools. Prefer it over tree whenever you know what you are looking for.

Tag searches are answered from CollectionService's index rather than by walking the tree, so they stay fast on large places. Narrow with path if a search reports TOO_BROAD.

op="tags" lists which tags the place actually USES, with counts and a few example paths. Call it before filtering by tag on a place you do not know: a tag search that returns nothing looks the same whether you spelled it wrong or nothing carries it, and the tag names are often the clearest description of how a game is organised (Enemy, Checkpoint, Interactable say more than the folder layout does).

selector is the engine's own query language and is the fastest option of all — the matching happens in C++ and only survivors come back. Reach for it when the shape of the tree is part of the question (Model > Part) or when one call should answer two (Part, Model); the filters above still apply on top of it.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`op`	No	'find' searches for instances. 'tags' lists which CollectionService tags exist in the place, with counts — use it when you do not know the tag names yet.	find
`tag`	No	CollectionService tag the instance must carry.
`path`	No	Limit the search to this subtree, e.g. "Workspace.Map". Omit for everything.
`limit`	No	Maximum items to return (1-500).
`cursor`	No	Opaque cursor from a previous call's `nextCursor`. Omit for the first page.
`detail`	No	concise: compact identity. standard: selected facts. full: all readable properties for inspect; tree/find use the same columns as standard.	standard
`selector`	No	Engine query selector, matched inside Studio. Supports a class name ("Part", superclasses included), "#ExactName", "[Anchored=true]", either-or with "Part, Model", direct children with "Model > Part" and descendants with "Model >> Part". No substring names and no < > comparisons — use nameContains and propertyValue for those. Combines with the other filters.
`studioId`	No	Target Studio; omit for the active one.
`className`	No	Class or superclass, e.g. "BasePart", "Script".
`properties`	No	Project just these properties on matching rows, avoiding a second inspect call. Unreadable names are reported.
`nameContains`	No	Substring of the instance name, case-insensitive.
`propertyName`	No	Property that must exist, e.g. "Anchored". Combine with propertyValue.
`propertyValue`	No	Required value of `propertyName`, compared as text — "true", "0, 5, 0", "Enum.Material.Neon". Omit to match any instance that has the property.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.8.6Sep 30, 2026

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."

addedInput schema / properties / properties

Added value: +{
+  "description": "Project just these properties on matching rows, avoiding a second inspect call. Unreadable names are reported.",
+  "items": {
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 16,
+  "type": "array"
+}

Changed2 schema fields changedv0.6.5Sep 12, 2026

addedInput schema / properties / op

Added value: +{
+  "default": "find",
+  "description": "'find' searches for instances. 'tags' lists which CollectionService tags exist in the place, with counts — use it when you do not know the tag names yet.",
+  "enum": [
+    "find",
+    "tags"
+  ],
+  "type": "string"
+}

addedInput schema / properties / selector

Added value: +{
+  "description": "Engine query selector, matched inside Studio. Supports a class name (\"Part\", superclasses included), \"#ExactName\", \"[Anchored=true]\", either-or with \"Part, Model\", direct children with \"Model > Part\" and descendants with \"Model >> Part\". No substring names and no < > comparisons — use nameContains and propertyValue for those. Combines with the other filters.",
+  "type": "string"
+}

First observedv0.1.8Aug 22, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld). The description still adds non-obvious behavior: tag searches are served from CollectionService's index rather than a tree walk (fast on large places), selector matching runs in C++ with only survivors returned, and results can come back TOO_BROAD. It does not discuss result shape or pagination beyond what the schema's cursor implies.

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 purpose, then layered paragraphs each carrying distinct operational advice. It is long for a description but nearly every sentence provides selection or invocation value, with no boilerplate.

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 a 13-parameter, no-output-schema search tool, the description covers the conceptually hard parts: filter composition, the tag-discovery workflow, and selector's syntax boundaries. The remaining parameters (limit, cursor, detail, studioId) are fully specified in the schema, so the definition is sufficient to call correctly.

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 baseline is 3, but the description meaningfully extends it: it explains that all supplied filters are ANDed, that selector has no substring or < > comparisons (pushing those to nameContains/propertyValue), and why op="tags" exists. It does not add semantics for limit, cursor, detail, or studioId, but those are already fully documented.

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 (searches) and resource (the data model) with the exact filter axes (name, class, property value, tag), and explicitly names the sibling it replaces and the one it supersedes (`tree`). An agent can select it without opening the schema.

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?

Gives explicit routing rules: prefer over `tree` when you know what you are looking for, call op="tags" before filtering by tag on an unfamiliar place, and reach for `selector` when tree shape is the question. It also names the fallback (nameContains/propertyValue) when selector cannot express the query.

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

Deploy Server

Find instances

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools