{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"github-boshyxd--robloxstudio-mcp","slug":"boshyxd--robloxstudio-mcp","name":"robloxstudio-mcp","type":"mcp","url":"https://github.com/boshyxd/robloxstudio-mcp","page_url":"https://unfragile.ai/boshyxd--robloxstudio-mcp","categories":["mcp-servers"],"tags":["ai","ai-agents","ai-tool","ai-tools","game-development","mcp","mcp-server","roblox","roblox-studio","robloxstudio"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"github-boshyxd--robloxstudio-mcp__cap_0","uri":"capability://tool.use.integration.mcp.based.ai.tool.registration.and.schema.exposure.for.roblox.studio","name":"mcp-based ai tool registration and schema exposure for roblox studio","description":"Implements a Model Context Protocol (MCP) server that registers 39 distinct tools (or 21 in inspector mode) as callable endpoints with JSON schemas, exposing them over stdio to AI assistants like Claude and Gemini. The RobloxStudioMCPServer class in packages/core/src/server.ts handles ListToolsRequestSchema and CallToolRequestSchema requests, dynamically loading tool definitions from TOOL_DEFINITIONS array and dispatching calls through a StudioHttpClient bridge. Tools are filtered at startup via getAllTools() or getReadOnlyTools() to enforce read-only vs read-write access policies.","intents":["Connect Claude or Gemini to Roblox Studio so the AI can read and modify game structure","Expose a curated set of Studio capabilities as callable functions to an AI agent","Provide safe read-only inspection mode that prevents accidental mutations via AI","Register tool schemas that match MCP spec so any MCP-compatible client can discover available actions"],"best_for":["Game developers using Claude or Gemini who want AI-assisted Roblox development","Teams building agentic workflows that need to manipulate Roblox game structure programmatically","Non-technical creators who want AI to handle repetitive Studio tasks"],"limitations":["Requires Roblox Studio running locally — no cloud-based Studio support","MCP protocol overhead adds latency per tool call (HTTP round-trip through polling mechanism)","Tool set is fixed at startup — cannot dynamically add new tools without restarting the MCP server","Inspector mode (read-only) is all-or-nothing — no fine-grained permission control per tool"],"requires":["Roblox Studio installed and running","Node.js 16+ with npm","AI assistant with MCP support (Claude, Gemini CLI, Codex CLI, or JSON-configured MCP client)","HTTP requests enabled in Roblox Studio settings (localhost:58741)"],"input_types":["MCP tool call requests (JSON with tool name and arguments)","Studio API parameters (instance paths, property names, script source code)"],"output_types":["MCP tool response (JSON with result or error)","Studio API responses (instance hierarchies, property values, script execution results)"],"categories":["tool-use-integration","mcp-server"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-boshyxd--robloxstudio-mcp__cap_1","uri":"capability://tool.use.integration.http.bridge.with.uuid.tracked.request.queuing.and.polling.based.response.correlation","name":"http bridge with uuid-tracked request queuing and polling-based response correlation","description":"Implements a localhost HTTP server (createHttpServer / BridgeService in packages/core/src/http-server.ts) on port 58741 that maintains an in-memory request queue and response map, keyed by UUID. When an MCP tool is called, the server enqueues the request; the Studio plugin polls /poll endpoint to fetch pending requests, executes them via Studio APIs, and posts results to /response endpoint. UUID tracking ensures responses are correctly correlated to requests even when multiple concurrent AI calls are in flight, enabling asynchronous coordination without WebSocket or persistent connections.","intents":["Enable the Studio plugin to pull work from the MCP server without maintaining a persistent connection","Handle multiple concurrent AI requests without blocking or losing response correlation","Provide a simple HTTP interface that the Lua-based Studio plugin can implement with minimal dependencies","Maintain request state across the air-gap between the MCP server process and the Studio plugin process"],"best_for":["Developers building MCP servers that need to coordinate with desktop applications (Studio, Unreal, etc.)","Teams that want to avoid WebSocket complexity or persistent connection management","Scenarios where the client (Studio plugin) is stateless and pulls work on-demand"],"limitations":["Polling introduces latency — default poll interval means requests may wait 100-500ms before execution","In-memory queue is not persistent — if the MCP server crashes, pending requests are lost","No built-in rate limiting or backpressure — a flood of concurrent AI requests could exhaust memory","UUID collision risk is negligible but not cryptographically guaranteed (uses standard UUID v4)"],"requires":["Node.js 16+ with http module","Roblox Studio with HTTP requests enabled (localhost:58741 must be accessible)","Studio plugin running and polling at regular intervals"],"input_types":["HTTP POST to /poll (Studio plugin requests pending work)","HTTP POST to /response (Studio plugin returns execution results with UUID and response body)"],"output_types":["JSON queue entry with UUID, tool name, and arguments","JSON response with UUID, result, and error status"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-boshyxd--robloxstudio-mcp__cap_10","uri":"capability://safety.moderation.dual.mode.tool.filtering.with.read.only.inspector.package","name":"dual-mode tool filtering with read-only inspector package","description":"The robloxstudio-mcp-inspector package exposes only 21 read-only tools (vs 39 in the full package) by filtering TOOL_DEFINITIONS at startup using getReadOnlyTools(). Tools are tagged with category: 'read' or category: 'write' in the TOOL_DEFINITIONS array; the inspector package loads only 'read' tools, preventing any mutations (script edits, instance creation/deletion, property changes). This enables safe, read-only inspection of games without risk of accidental or malicious modifications.","intents":["Inspect game structure and properties without risk of accidental mutations","Enable code review or debugging workflows where AI should only read, not modify","Provide a safe mode for untrusted AI clients or experimental prompts","Allow non-developers to use AI for game analysis without risk of breaking the game"],"best_for":["Game developers who want AI to analyze their game without risk of mutations","Teams using AI for code review or debugging (read-only inspection)","Non-technical creators who want AI to understand their game without modifying it","Experimental or untrusted AI workflows that should be sandboxed"],"limitations":["All-or-nothing filtering — no fine-grained permission control per tool or per instance","Read-only mode is enforced at startup — cannot switch between modes without restarting the MCP server","No audit logging — cannot track which read-only tools were called or what data was accessed","Read-only tools can still consume resources (large queries, many API calls) — no rate limiting"],"requires":["robloxstudio-mcp-inspector package (instead of robloxstudio-mcp)","Roblox Studio running with the MCP plugin installed","No special configuration — filtering is automatic at startup"],"input_types":["Same as full package (instance paths, property names, etc.)"],"output_types":["Same as full package (instance metadata, property values, etc.)"],"categories":["safety-moderation","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-boshyxd--robloxstudio-mcp__cap_11","uri":"capability://data.processing.analysis.metadata.and.type.introspection.for.roblox.classes.and.properties","name":"metadata and type introspection for roblox classes and properties","description":"Provides tools like GetClassMetadata and GetPropertyMetadata that return information about Roblox classes (Part, Model, Script, etc.) and their properties (type, default value, read-only status, etc.). These tools query the Studio's DataModel API to introspect class definitions and return structured JSON describing available properties, their types, and constraints. This enables AI to understand what properties are available on instances and what values are valid, reducing errors when setting properties or creating instances.","intents":["Understand what properties are available on a given class (e.g., Part has Position, Size, Color, etc.)","Determine valid property types and ranges before setting properties","Discover what classes are available in Roblox and what they are used for","Enable AI to make informed decisions about instance creation and property modification"],"best_for":["Game developers who want AI to understand Roblox class definitions","Teams building agentic workflows that need to validate property types before setting them","Creators using AI for rapid development who want to avoid property-related errors"],"limitations":["Metadata is read-only — cannot be used to modify class definitions or add custom properties","Metadata may be incomplete or outdated if Studio version is not current","Complex property types (Connections, Signals, custom types) may not be fully described","No documentation or examples — metadata includes type information but not usage guidance"],"requires":["Roblox Studio running with the MCP plugin installed","Valid class names (e.g., 'Part', 'Model', 'LocalScript')"],"input_types":["Class name (string, e.g., 'Part')","Property name (optional, for GetPropertyMetadata)"],"output_types":["Class metadata (JSON with property list, inheritance, default values)","Property metadata (JSON with type, default value, read-only status, constraints)"],"categories":["data-processing-analysis","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-boshyxd--robloxstudio-mcp__cap_12","uri":"capability://tool.use.integration.asynchronous.request.coordination.with.uuid.tracking.and.concurrent.request.handling","name":"asynchronous request coordination with uuid tracking and concurrent request handling","description":"The HTTP bridge maintains UUID-keyed request and response maps that enable the MCP server to handle multiple concurrent AI requests without blocking or losing response correlation. When an MCP tool is called, the server generates a UUID, enqueues the request, and returns immediately; the Studio plugin polls /poll, fetches the request by UUID, executes it, and posts the result to /response with the same UUID. The MCP server retrieves the response by UUID and returns it to the AI. This architecture allows the MCP server to be stateless and the Studio plugin to be event-driven, with no persistent connections required.","intents":["Handle multiple concurrent AI requests without blocking the MCP server or Studio plugin","Maintain request state across the air-gap between the MCP server and Studio plugin","Enable the Studio plugin to pull work on-demand without maintaining a persistent connection","Support agentic workflows that may issue multiple concurrent tool calls"],"best_for":["Developers building MCP servers that need to coordinate with desktop applications","Teams that want to avoid WebSocket complexity or persistent connection management","Scenarios where the client (Studio plugin) is stateless and pulls work on-demand"],"limitations":["UUID collision risk is negligible but not cryptographically guaranteed","In-memory maps are not persistent — if the MCP server crashes, pending requests are lost","No built-in rate limiting or backpressure — a flood of concurrent requests could exhaust memory","Polling introduces latency — requests may wait 100-500ms before execution","No timeout mechanism — if the Studio plugin crashes, requests will hang indefinitely"],"requires":["Node.js 16+ with uuid module (or equivalent UUID generation)","HTTP server with /poll and /response endpoints","Studio plugin that polls /poll at regular intervals"],"input_types":["MCP tool call requests (JSON with tool name and arguments)"],"output_types":["MCP tool responses (JSON with result or error)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-boshyxd--robloxstudio-mcp__cap_2","uri":"capability://automation.workflow.lua.based.studio.plugin.with.http.polling.and.routemap.based.tool.dispatch","name":"lua-based studio plugin with http polling and routemap-based tool dispatch","description":"The MCPPlugin.rbxmx Studio plugin (Lua code running inside Roblox Studio) implements a polling loop that periodically calls the /poll HTTP endpoint on localhost:58741, receives pending tool requests, dispatches them via a routeMap (a table mapping tool names to handler functions), executes the corresponding Studio API calls, and posts results back to /response. The plugin is stateless and event-driven, with no persistent connection to the MCP server, making it resilient to MCP server restarts.","intents":["Execute Studio API calls on behalf of the AI assistant without requiring the AI to have direct Studio access","Translate MCP tool requests into Roblox Lua API calls (e.g., finding instances, editing scripts, setting properties)","Provide a bridge between the MCP server and Studio's internal object model and scripting engine","Handle concurrent requests from multiple AI calls without blocking the Studio UI"],"best_for":["Roblox developers who want to automate Studio workflows via AI","Game teams building agentic development pipelines that need to modify game structure programmatically","Creators who want AI to handle bulk edits, script generation, or property manipulation"],"limitations":["Polling introduces latency — tool execution is not instantaneous, typically 100-500ms per request","Plugin runs inside Studio process — heavy operations (large script edits, bulk instance creation) can freeze the UI","Lua-based implementation limits error handling and debugging compared to TypeScript/Node.js","No built-in undo/redo integration — AI-driven changes are not easily reversible via Studio's undo system"],"requires":["Roblox Studio installed and running","MCPPlugin.rbxmx installed in Studio's plugins folder","HTTP requests enabled in Studio settings (localhost:58741)","MCP server running and accessible on localhost:58741"],"input_types":["HTTP response from /poll endpoint (JSON with tool name, arguments, UUID)"],"output_types":["HTTP POST to /response endpoint (JSON with UUID, result, error status)"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-boshyxd--robloxstudio-mcp__cap_3","uri":"capability://data.processing.analysis.hierarchical.instance.querying.and.inspection.with.path.based.traversal","name":"hierarchical instance querying and inspection with path-based traversal","description":"Exposes tools like GetInstance, GetInstanceChildren, GetInstanceProperties, and DescribeInstance that allow AI to navigate the Roblox game hierarchy by path (e.g., 'Workspace/Baseplate/Part1') and inspect instance metadata, properties, and children. These tools use the Studio's DataModel API to traverse the object tree and return structured JSON describing instances, their properties, and their relationships. Path-based querying enables AI to understand game structure without loading the entire hierarchy into memory.","intents":["Understand the structure of a Roblox game (what instances exist, how they are organized, what properties they have)","Find specific instances by name or path so the AI can target edits or queries","Inspect instance properties (Position, Size, Color, etc.) to understand current state before making changes","Enable AI to reason about game structure and make informed decisions about where to place new objects or modify existing ones"],"best_for":["Game developers who want AI to analyze and understand their game structure","Teams using AI for code review or debugging (inspecting what instances exist and their properties)","Creators building agentic workflows that need to query game state before making changes"],"limitations":["Path-based queries are linear — querying deep hierarchies requires multiple round-trips","No built-in filtering or search — AI must traverse the tree manually to find instances by property","Large games with thousands of instances may return large JSON responses, increasing latency","Read-only in inspector mode — cannot be used to discover instances for subsequent mutations"],"requires":["Roblox Studio running with the MCP plugin installed","Target instances must exist in the open game file","Valid instance paths (e.g., 'Workspace/Part1' or 'ReplicatedStorage/Modules/MyModule')"],"input_types":["Instance path (string, e.g., 'Workspace/Baseplate')","Property names (optional, to filter which properties are returned)"],"output_types":["JSON object with instance metadata (Name, ClassName, Parent path, Children list, Properties dict)"],"categories":["data-processing-analysis","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-boshyxd--robloxstudio-mcp__cap_4","uri":"capability://code.generation.editing.script.editing.and.code.generation.with.source.replacement","name":"script editing and code generation with source replacement","description":"Provides tools like GetScript, SetScript, and InsertScript that allow AI to read Lua script source code from instances (LocalScripts, Scripts, ModuleScripts) and replace or insert new code. The SetScript tool takes an instance path and new source code, replacing the entire script source via the Studio API. InsertScript creates a new script instance at a given path with initial source code. This enables AI to generate, refactor, or debug Lua code directly within the game structure.","intents":["Generate new Lua scripts for game logic, UI, or utilities based on AI understanding of game structure","Refactor or debug existing scripts by reading current source and replacing with improved code","Create boilerplate scripts (event handlers, module templates) to accelerate development","Enable AI to understand and modify game behavior by reading and editing the code that drives it"],"best_for":["Game developers who want AI to generate or refactor Lua code","Teams building agentic development pipelines that need to modify game logic programmatically","Creators using AI for rapid prototyping or boilerplate generation"],"limitations":["Full script replacement — no line-by-line editing or merge conflict resolution","No syntax validation — AI can generate invalid Lua code that will only fail at runtime","No undo integration — replaced scripts cannot be easily reverted via Studio's undo system","Lua-specific — does not support other Roblox script types (e.g., animation scripts, plugin scripts)","No built-in testing — AI-generated code is not validated before insertion"],"requires":["Roblox Studio running with the MCP plugin installed","Target script instance must exist (for GetScript/SetScript) or parent instance must exist (for InsertScript)","Write access enabled (full robloxstudio-mcp package, not inspector mode)"],"input_types":["Instance path (string, e.g., 'Workspace/Part1/LocalScript')","Lua source code (string, for SetScript and InsertScript)"],"output_types":["Lua source code (string, for GetScript)","Confirmation message (for SetScript and InsertScript)"],"categories":["code-generation-editing"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-boshyxd--robloxstudio-mcp__cap_5","uri":"capability://automation.workflow.instance.creation.and.deletion.with.property.initialization","name":"instance creation and deletion with property initialization","description":"Provides tools like CreateInstance and DeleteInstance that allow AI to create new instances (Parts, Models, Scripts, etc.) at specified parent paths with optional initial properties, and delete instances by path. CreateInstance takes a parent path, class name (e.g., 'Part', 'Model', 'LocalScript'), and optional property dict (e.g., {Position: [0, 5, 0], Color: [1, 0, 0]}), and returns the path of the newly created instance. DeleteInstance removes an instance and its descendants by path. These tools enable AI to build game structure programmatically.","intents":["Create new game objects (parts, models, scripts) based on AI understanding of game design","Bulk-create instances with initial properties to accelerate level design or prototyping","Clean up or reorganize game structure by deleting instances that are no longer needed","Enable AI to build game structure from scratch or modify existing structure programmatically"],"best_for":["Game developers using AI for rapid level design or prototyping","Teams building agentic workflows that need to generate game structure programmatically","Creators who want AI to handle repetitive instance creation tasks"],"limitations":["No validation of property values — AI can set invalid properties that cause runtime errors","No undo integration — deleted instances cannot be easily recovered via Studio's undo system","Property initialization is limited to simple types (numbers, strings, booleans, vectors) — complex properties (Connections, Signals) cannot be set","No bulk operations — creating many instances requires multiple tool calls, each with HTTP latency","No parent validation — AI can create instances under invalid parents, causing errors"],"requires":["Roblox Studio running with the MCP plugin installed","Parent instance must exist (for CreateInstance)","Write access enabled (full robloxstudio-mcp package, not inspector mode)","Valid class names (e.g., 'Part', 'Model', 'LocalScript', 'RemoteEvent')"],"input_types":["Parent path (string, e.g., 'Workspace')","Class name (string, e.g., 'Part')","Property dict (optional, e.g., {Position: [0, 5, 0], Color: [1, 0, 0]})"],"output_types":["New instance path (string, e.g., 'Workspace/Part1')","Confirmation message (for DeleteInstance)"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-boshyxd--robloxstudio-mcp__cap_6","uri":"capability://data.processing.analysis.property.reading.and.writing.with.type.coercion.and.validation","name":"property reading and writing with type coercion and validation","description":"Provides tools like GetProperty and SetProperty that allow AI to read and write instance properties (Position, Color, Size, Transparency, etc.) by instance path and property name. GetProperty returns the current value as JSON; SetProperty takes a path, property name, and new value, and updates the property via the Studio API. The tools handle type coercion (e.g., converting JSON arrays to Vector3) and basic validation (e.g., ensuring Transparency is between 0 and 1). This enables AI to modify instance appearance and behavior without creating or deleting instances.","intents":["Modify instance appearance (color, size, position, transparency) based on AI decisions","Read current property values to understand instance state before making changes","Batch-update properties across multiple instances to implement design changes","Enable AI to reason about and modify game behavior by adjusting instance properties"],"best_for":["Game developers who want AI to adjust instance properties (color, position, size, etc.)","Teams building agentic workflows that need to modify game appearance or behavior","Creators using AI for rapid iteration on level design or visual polish"],"limitations":["Type coercion is limited — complex property types (Connections, Signals, Enums) may not be supported","No validation of property ranges — AI can set invalid values (e.g., Transparency > 1) that cause errors","No undo integration — property changes are not easily reversible via Studio's undo system","Property names are case-sensitive — AI must use exact property names (e.g., 'Position', not 'position')","Some properties are read-only — attempting to set them will fail silently or with an error"],"requires":["Roblox Studio running with the MCP plugin installed","Target instance must exist","Write access enabled for SetProperty (full robloxstudio-mcp package, not inspector mode)","Valid property names (e.g., 'Position', 'Color', 'Size', 'Transparency')"],"input_types":["Instance path (string, e.g., 'Workspace/Part1')","Property name (string, e.g., 'Position')","Property value (JSON, e.g., [0, 5, 0] for Vector3, or 0.5 for Transparency)"],"output_types":["Property value (JSON, for GetProperty)","Confirmation message (for SetProperty)"],"categories":["data-processing-analysis","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-boshyxd--robloxstudio-mcp__cap_7","uri":"capability://search.retrieval.creator.store.asset.search.and.insertion.via.open.cloud.api","name":"creator store asset search and insertion via open cloud api","description":"Integrates with the Roblox Open Cloud API (OpenCloudClient in packages/core/src/open-cloud-client.ts) to enable AI to search the Creator Store for assets (models, decals, audio, etc.) by keyword and insert them into the game. The SearchCreatorStoreAssets tool queries the Open Cloud API with a search term and returns matching assets with metadata (ID, name, description, thumbnail). The InsertCreatorStoreAsset tool inserts a selected asset into the game at a specified parent path. This enables AI to populate games with community-created assets without manual browsing.","intents":["Search the Creator Store for assets (models, decals, audio) by keyword","Insert Creator Store assets into the game programmatically without manual browsing","Enable AI to populate games with appropriate assets based on game design or theme","Accelerate game development by automating asset discovery and insertion"],"best_for":["Game developers who want AI to find and insert Creator Store assets","Teams building agentic workflows that need to populate games with community assets","Creators using AI for rapid prototyping or asset-heavy game development"],"limitations":["Requires valid Open Cloud API credentials (API key with Creator Store access)","Search results are limited to the Creator Store — cannot search user-created assets or private libraries","Asset insertion may fail if the asset is incompatible with the game or if the parent instance is invalid","No preview or validation — AI cannot verify that an asset is appropriate before insertion","Creator Store availability varies by region and account type"],"requires":["Roblox Studio running with the MCP plugin installed","Valid Open Cloud API key with Creator Store access","Internet connection to query the Creator Store","Write access enabled (full robloxstudio-mcp package, not inspector mode)"],"input_types":["Search term (string, e.g., 'tree', 'sword', 'ambient music')","Asset ID (string, for InsertCreatorStoreAsset)","Parent path (string, e.g., 'Workspace')"],"output_types":["Asset list (JSON array with ID, name, description, thumbnail URL)","Confirmation message (for InsertCreatorStoreAsset)"],"categories":["search-retrieval","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-boshyxd--robloxstudio-mcp__cap_8","uri":"capability://automation.workflow.playtest.execution.and.result.collection.with.output.capture","name":"playtest execution and result collection with output capture","description":"Provides a PlaytestGame tool that launches a Studio playtest session, waits for completion, and collects output (print statements, errors, warnings) from the game's execution. The tool captures console output from the running game and returns it as structured JSON, enabling AI to understand game behavior and debug issues without manually reading the Output window. This enables AI to test game logic and iterate based on playtest results.","intents":["Test game logic by running a playtest and capturing output","Debug game behavior by analyzing print statements and error messages from playtests","Iterate on game design based on playtest results (e.g., adjust difficulty, fix bugs)","Enable AI to validate that changes work correctly before committing them"],"best_for":["Game developers who want AI to test and debug game logic","Teams building agentic workflows that need to validate changes via playtesting","Creators using AI for rapid iteration on game mechanics"],"limitations":["Playtest execution is synchronous — the MCP server blocks while the playtest runs, potentially for minutes","Output capture is limited to console output (print statements) — visual or gameplay issues are not captured","No timeout mechanism — a game that hangs or runs indefinitely will block the MCP server","Playtest results are not deterministic — the same game may produce different output on different runs","No access to game state after playtest — AI cannot inspect instance properties or memory after execution"],"requires":["Roblox Studio running with the MCP plugin installed","Game file must be valid and runnable (no syntax errors or missing dependencies)","Write access enabled (full robloxstudio-mcp package, not inspector mode)"],"input_types":["Playtest duration (optional, in seconds; defaults to a reasonable timeout)"],"output_types":["Playtest output (JSON with console output, errors, warnings, execution time)"],"categories":["automation-workflow","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-boshyxd--robloxstudio-mcp__cap_9","uri":"capability://memory.knowledge.build.library.asset.management.with.metadata.and.versioning","name":"build library asset management with metadata and versioning","description":"Provides tools like GetBuildLibraryAssets and InsertBuildLibraryAsset that allow AI to browse and insert pre-built game components (buildings, terrain, UI templates) from a local build library. The build library is a collection of .rbxm files with metadata (name, description, tags, version) stored in a JSON manifest. GetBuildLibraryAssets returns the list of available assets with metadata; InsertBuildLibraryAsset loads a selected asset file and inserts it into the game at a specified parent path. This enables AI to reuse pre-built components without creating them from scratch.","intents":["Browse available pre-built game components (buildings, terrain, UI) in the build library","Insert pre-built components into the game to accelerate development","Reuse tested, validated components instead of creating new ones from scratch","Enable AI to understand what components are available and choose appropriate ones for the game design"],"best_for":["Game developers with a library of pre-built components they want to reuse","Teams building agentic workflows that need to assemble games from pre-built parts","Creators using AI for rapid prototyping with a component library"],"limitations":["Build library must be manually maintained — no automatic indexing or discovery","Asset metadata is stored in JSON — no rich versioning or dependency management","Asset insertion may fail if the asset is incompatible with the game or if the parent instance is invalid","No preview or validation — AI cannot verify that an asset is appropriate before insertion","Build library is local-only — cannot share assets across teams without manual file transfer"],"requires":["Roblox Studio running with the MCP plugin installed","Build library folder with .rbxm files and metadata.json manifest","Write access enabled (full robloxstudio-mcp package, not inspector mode)","Valid asset paths and parent instances"],"input_types":["Asset ID or name (string, e.g., 'house_v2', 'terrain_forest')","Parent path (string, e.g., 'Workspace')"],"output_types":["Asset list (JSON array with ID, name, description, tags, version)","Confirmation message (for InsertBuildLibraryAsset)"],"categories":["memory-knowledge","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":43,"verified":false,"data_access_risk":"high","permissions":["Roblox Studio installed and running","Node.js 16+ with npm","AI assistant with MCP support (Claude, Gemini CLI, Codex CLI, or JSON-configured MCP client)","HTTP requests enabled in Roblox Studio settings (localhost:58741)","Node.js 16+ with http module","Roblox Studio with HTTP requests enabled (localhost:58741 must be accessible)","Studio plugin running and polling at regular intervals","robloxstudio-mcp-inspector package (instead of robloxstudio-mcp)","Roblox Studio running with the MCP plugin installed","No special configuration — filtering is automatic at startup"],"failure_modes":["Requires Roblox Studio running locally — no cloud-based Studio support","MCP protocol overhead adds latency per tool call (HTTP round-trip through polling mechanism)","Tool set is fixed at startup — cannot dynamically add new tools without restarting the MCP server","Inspector mode (read-only) is all-or-nothing — no fine-grained permission control per tool","Polling introduces latency — default poll interval means requests may wait 100-500ms before execution","In-memory queue is not persistent — if the MCP server crashes, pending requests are lost","No built-in rate limiting or backpressure — a flood of concurrent AI requests could exhaust memory","UUID collision risk is negligible but not cryptographically guaranteed (uses standard UUID v4)","All-or-nothing filtering — no fine-grained permission control per tool or per instance","Read-only mode is enforced at startup — cannot switch between modes without restarting the MCP server","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.3499073294610682,"quality":0.35,"ecosystem":0.6000000000000001,"match_graph":0.25,"freshness":0.9,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.15,"match_graph":0.23,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:21.549Z","last_scraped_at":"2026-05-03T13:57:13.678Z","last_commit":"2026-04-29T12:36:48Z"},"community":{"stars":408,"forks":74,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=boshyxd--robloxstudio-mcp","compare_url":"https://unfragile.ai/compare?artifact=boshyxd--robloxstudio-mcp"}},"signature":"9wsfrdipDVuedVJgV34p2nHHGm0WqZ8HOQdI9Kor3ETm+vJOE2wYyf6LZyQSFUG0yaDVhgn8VnPWIlw88Zr/AQ==","signedAt":"2026-06-16T01:51:46.655Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/boshyxd--robloxstudio-mcp","artifact":"https://unfragile.ai/boshyxd--robloxstudio-mcp","verify":"https://unfragile.ai/api/v1/verify?slug=boshyxd--robloxstudio-mcp","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}