getPlatformInfo
SDK capability catalog, version/artifact info, and platform constraints
How to use it
Project documentation lists getPlatformInfo for the MCP Server MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), then check which tools your installed version makes available. Tool availability can depend on configuration and credentials. A server handshake does not verify this tool’s behavior. See the full listing for setup details.
Install MCP Server
npx -y @extentos/mcp-server@latestOther tools in MCP Server (37)
upload a custom sound (earcons, wake sounds) to the project
bring an existing connection-page file under managed configuration
wait for an assistant tool-call event matching name/args (agent E2E loop)
finish the device-code sign-in flow
mint a browser-simulator session for end-to-end testing
open/attach the simulator browser tab for the session
scaffold the connection UI, manifest, and platform config into your app
read the managed voice-assistant configuration (model, voice, memory, wake sound)
per-feature call shapes in Kotlin + Swift with gotchas
canonical end-to-end patterns (voice Q&A, photo-describe, live transcription UI, …)
read the managed connection-page configuration
how to obtain and configure Meta DAT credentials
which credentials (Meta DAT, AI provider) are configured
read the rendered display tree and interactive element ids (Ray-Ban Display)
read the session event log (transport, audio, camera, speak, toggle, stream, system)
AI-gateway usage and metering for the project
mapping table and cutover plan from Meta DAT direct usage to Extentos
the exact permission set the integration needs per platform
the path from simulator to real glasses
usage analytics for the project's glasses integration
live session state: phase, roles, open streams, freshness, test videos
implementation guidance for voice triggers and wake phrases
drive the voice assistant with an utterance end-to-end (real provider session)
simulate the hardware capture button
drive display input: select/navigate/back, like Neural Band gestures
inject a voice transcript into the running app, as if the wearer spoke
read the current state of the integration in your repo
list custom sounds uploaded for the project
regenerate a managed connection-page file after config changes
search the bundled, versioned documentation topics
update the managed voice-assistant configuration
update the managed connection-page configuration
store a credential for the project
switch the simulated glasses model
pipe a test video into the simulated camera
trigger a camera shutter in the active simulator session
deterministic checks of the integration (manifest, config, wiring)