Enable AI tools with HzOS Developer MCP

Updated: Dec 9, 2025

Meta Quest Developer Hub (MQDH) integrates a dedicated Model Context Protocol (MCP) server, engineered to support AI assistant workflows. The MCP server is a self-contained executable. This design ensures easy portability and simplifies deployment, allowing you to integrate the MCP server into other applications or environments with minimal setup.

Enabling the MCP server within MQDH unlocks a suite of tools that:

Streamline documentation access for faster information retrieval

Enhance debugging with advanced troubleshooting tools

Accelerate content creation and prototyping by leveraging Meta’s extensive 3D asset library

This integration is designed to deliver a seamless, productive experience for developers working with Meta’s platforms. By centralizing essential tooling and resources, the MCP server helps you work faster, debug smarter, and build more effectively, whether you’re extending MQDH or embedding AI assistant capabilities in your own projects.

Connect your LLM

MCP for Meta Horizon OS developers uses STDIO to connect to your LLM agent. It provides several ways for you to connect the LLM agent of your choice.

Download MQDH

The latest version (v6.2.1) of Meta Quest Developer Hub (MQDH) includes a new AI Tools setting tab which helps you connect the MCP for Meta Horizon OS developers to the LLM agent of your choice.

To check your version of MQDH, navigate to Settings > About. Validate the currently installed version of MQDH is v6.2.1. If you do not have MQDH installed or need to update to the latest version, you can manually install MQDH for Mac or Windows.

Quick install

For VS Code, there is a one-click install link which automatically configures the MCP for Meta Horizon OS developers if VS Code or VS Code Insiders is installed.

Manual install

For the most popular agents listed below, there are guided setup instructions within MQDH.

Android Studio

Augment Code

Claude Code

Claude Desktop

Cline

Cursor

Gemini CLI

JetBrains AI Assistant

OpenAI Codex

Roo Code

Zed

Select the LLM agent from the drop-down of available setup instructions. For any LLM agent not listed, select Other and consult the documentation for your LLM agent.

How MCP server works with your AI assistant

When you submit a query, the client first requests the list of available tools from the MCP server. It then forwards your query, along with tool metadata, to your chosen interface. The interface analyzes your request and determines which tools, if any, are needed to address it. The client invokes these tools through the server, and the resulting outputs are sent back to the interface. Using these results, the interface generates a natural language response, which is then displayed for your review.

This workflow ensures that queries are processed efficiently, leveraging the appropriate tools to deliver clear and actionable answers for developers.

Available tools and capabilities

Once the MCP server is connected, you’ll be able to utilize the following tools.

Tool Name	Description	Key Parameters / Usage	More Details / Links
fetch_meta_quest_doc	Retrieve the full content of a specific documentation page from Meta’s Horizon platforms.	`url` (required): Full URL to the documentation page (should start with https://developers.meta.com/horizon/llmstxt/documentation/)	Use with *_documentation_index tools for specific pages.
get_unity_documentation_index	Get the latest Unity development documentation index for Meta Quest.	None	Use with `fetch_meta_quest_doc` for specific pages.
get_unreal_documentation_index	Get the latest Unreal Engine development documentation index for Meta Quest.	None	Use with `fetch_meta_quest_doc` for specific pages.
get_spatial_sdk_documentation_index	Get the latest Meta Spatial SDK development documentation index for Meta Quest.	None	Use with `fetch_meta_quest_doc` for specific pages.
get_android_apps_documentation_index	Get the latest Android Apps development documentation index for Meta Quest.	None	Use with `fetch_meta_quest_doc` for specific pages.
get_native_documentation_index	Get the latest Native C++ development documentation index for Meta Quest.	None	Use with `fetch_meta_quest_doc` for specific pages.
get_web_documentation_index	Get the latest Web development documentation index for Meta Quest.	None	Use with `fetch_meta_quest_doc` for specific pages.
get_adb_path	Return the preferred ADB binary path for Meta Quest development.	None
get_device_logcat	Retrieve Android logcat logs from a connected Meta Quest device via ADB.	`lines`, `tag`, `level`, `package`, `pid`, `clear`	Useful for debugging app crashes, performance, system events, etc.
stream_device_logcat	Stream real-time Android logcat logs from a connected Meta Quest device via ADB.	`duration_seconds`, `tag`, `level`, `package`, `pid`	Real-time device monitoring.
take_screenshot	Capture a screenshot from a connected Meta Quest device via ADB.	`width`, `height`, `method`	For debugging or documentation.
hex_to_datetime	Convert a hexadecimal timestamp string to a datetime object (UTC).	`hex_str` (required): Hexadecimal string representing a Unix timestamp	Useful for interpreting trace timestamps.
load_trace_for_analysis	Load the content of a Perfetto trace or processed JSON for analysis.	`session_id` (required): The file name of the trace	For in-depth performance session analysis.
trace_thread_state	Retrieve thread state information from a parfait trace for performance analysis.	`session_id` (required), `utid` (required), `start_ts`, `end_ts`	Diagnose expensive operations or CPU activity.
run_sql_query	Run SQL query on the loaded trace to retrieve information in JSON format.	`session_id` (required), `query` (required)	Flexible trace data interrogation.
get_counter_for_gpu_frames	Return all GPU metric counters for given arrays of GPU frame start/end times.	`session_id` (required), `start_ts` (array, required), `end_ts` (array, required)	At least 20 start/end times recommended for accurate metrics.
get_perfetto_context	Retrieve the context needed for Perfetto or performance analysis workflows.	None	Must be called before most Perfetto-related analysis.
meta-assets-search	Search for existing 3D models in Meta’s asset library using text descriptions.	`prompt` (required), `number_of_models`	Returns download URLs for FBX/GLB and preview images.