extentosVerifiedFeatured
@Asger mølgaard
About extentos
Extentos is a multi-vendor development platform for adding smart-glasses capabilities to existing iOS and Android apps. The simplest analogy is Stripe for smart glasses:


Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"extentos": {
"command": "npx",
"args": [
"-y",
"@extentos/mcp-server@latest"
]
}
}
}Tools
No tools detected
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Overview
What is Extentos?
Extentos is an MCP server that lets AI coding agents — Claude Code, Cursor, Cline — add smart-glasses capabilities to Android and iOS apps: camera capture, voice triggers, live transcription, and audio playback. The tools are deterministic: the agent discovers the SDK surface, scaffolds the integration, validates it, and tests it end-to-end in a browser simulator before touching hardware.
It works with Meta smart glasses today (Ray-Ban Meta, Oakley Meta, Meta Ray-Ban Display), with a multi-vendor architecture by design. Think Stripe for smart glasses: your app integrates once, Extentos handles the vendor SDKs, credentials, permissions, and hardware connections underneath.
How to use Extentos
With Claude Code:
claude mcp add extentos -- npx -y @extentos/mcp-server@latest
Or add to any MCP client config:
{
"mcpServers": {
"extentos": {
"command": "npx",
"args": ["-y", "@extentos/mcp-server@latest"]
}
}
}
Then ask your agent to add glasses features to your app. Requires Node 20+.
Key features
- Discovery — the SDK capability catalog, per-feature call shapes in Kotlin and Swift, and canonical end-to-end code patterns
- Scaffolding — generates the connection UI, manifest, and platform config for your app
- Validation — deterministic checks of the integration in your repo
- Browser simulator — runs the same SDK code as production with only the transport swapped, so the agent can verify behavior end-to-end with no hardware
- Production guidance — checklist and credential guide for the path from simulator to real glasses
Use cases
- Add voice commands or a voice assistant to an existing mobile app, running on the wearer's glasses
- Capture photos or video from glasses and process them in your app
- Build and test a complete glasses integration without owning the hardware, then ship it to real devices
FAQ
Do I need smart glasses to use it?
No — the browser simulator runs the same SDK code as production, so agents build and verify the full loop without hardware. Real Meta smart glasses are the production target.
Does it need an account?
Discovery, validation, and guidance tools work anonymously. Creating simulator sessions and scaffolding use a free account — the server walks you through a device-code sign-in when needed.
Which glasses are supported?
Meta smart glasses today: Ray-Ban Meta, Ray-Ban Meta Optics, Oakley Meta HSTN, Oakley Meta Vanguard, and Meta Ray-Ban Display. The architecture is multi-vendor by design.
Where are the docs?
Full documentation at extentos.com/docs, including the MCP tools reference and the [smart-glasses ecosystem reference](https://extentos.com/docs/ecosystem
Frequently asked questions
Do I need smart glasses to use it?
No — the browser simulator runs the same SDK code as production, so agents build and verify the full loop without hardware. Real Meta smart glasses are the production target.
Does it need an account?
Discovery, validation, and guidance tools work anonymously. Creating simulator sessions and scaffolding use a free account — the server walks you through a device-code sign-in when needed.
Which glasses are supported?
Meta smart glasses today: Ray-Ban Meta, Ray-Ban Meta Optics, Oakley Meta HSTN, Oakley Meta Vanguard, and Meta Ray-Ban Display. The architecture is multi-vendor by design.
Where are the docs?
Full documentation at [extentos.com/docs](https://extentos.com/docs), including the [MCP tools reference](https://extentos.com/docs/reference/mcp-tools) and the [smart-glasses ecosystem reference](https://extentos.com/docs/ecosystem
Basic information
More Developer Tools MCP servers
AptiBuild AI — Career Intelligence
ParklandBuildsAptiBuild AI — Career Intelligence MCP Server Structured career decision scaffolding for AI agents. Provides personality-conditioned business idea generation, official BLS OEWS wage data, FRED labor market signals, and

endoflife.ai
endoflife.aiFree MCP server for software end-of-life intelligence: EOL dates, support status, and the 0-100 EOL Risk Score across 480+ tracked products. Agents can check a single version, pull a product's full lifecycle schedule, or

Termany
thinkany-aiAgent-Native Terminal
OpenSumi
opensumiA framework helps you quickly build AI Native IDE products. MCP Client, supports Model Context Protocol (MCP) tools via MCP server.
MCP Server By TestMu AI
TestMu AITestMu AI MCP Server lets developers run, debug, and triage tests through natural language directly from their IDE (Cursor, Claude, GitHub Copilot, and other MCP clients). It exposes five tools — HyperExecute (test orche
Comments