</>MCP Agents Market
MCP Server

RuView

by ruvnet90.4kRustUpdated 2026-08-17

π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.

Claude CodeCodex

RuView is an MCP server that transforms standard WiFi signals into contactless spatial intelligence and vital sign monitoring without cameras or wearables. Built for ESP32 hardware and compatible smart-home platforms, it detects presence, breathing rate, heart rate, falls, and activity through walls using Channel State Information (CSI). The server provides local edge processing with cryptographic attestation, integrates with Home Assistant, Apple Home, Google Home, and Alexa, and ships pretrained models on Hugging Face for immediate deployment.

Key Features

Contactless vital sign monitoring (breathing 6–30 BPM, heart rate 40–120 BPM) from WiFi CSI with no wearables required
Through-wall presence detection, occupancy counting, and activity recognition using ESP32-S3/C6 sensors ($9–10)
Native integration with Home Assistant (MQTT), Apple HomeKit (HAP bridge), Google Home, and Alexa via Matter endpoints
105 edge intelligence modules (Cogs) for health, security, retail, and industrial applications running on-device
Pretrained contrastive encoder (82.3% temporal-triplet accuracy) and pose model (82.69% torso-PCK@20 on MM-Fi benchmark) published on Hugging Face
Multi-frequency mesh sensing across 6 WiFi channels with cryptographic Ed25519 witness chain for measurement attestation
Quantized models (4-bit, 8 KB) run in microseconds on Raspberry Pi; full system operates offline with no cloud dependency
Python PyPI packages (ruview / wifi-densepose) and Docker images for rapid prototyping and deployment

Use Cases

  • 01Elderly care monitoring with fall detection, inactivity alerts, and contactless vital sign tracking
  • 02Smart home automation triggered by room occupancy, sleep state, or presence detection without privacy-invasive cameras
  • 03Healthcare applications for remote patient monitoring, sleep apnea screening, and overnight respiratory tracking
  • 04Building management with occupancy analytics, queue length monitoring, and multi-room transition tracking
  • 05Security and safety systems detecting distress patterns, bed exits, or elevated fall risk through radio sensing
  • 06Industrial and retail environments for customer flow analysis, clean-room occupancy, and zone-based people counting

Related MCP Servers

View more

RuView — FAQ

What is the RuView MCP server?+

RuView is an MCP server that converts WiFi radio signals into actionable spatial intelligence—presence detection, vital signs (breathing/heart rate), activity recognition, and pose estimation—without cameras or wearables. It processes Channel State Information (CSI) from ESP32 sensors or research NICs locally on edge hardware.

How do I install and run RuView?+

Install via Docker (docker pull ruvnet/wifi-densepose:latest), Python PyPI (pip install ruview), or flash ESP32-S3/C6 firmware for live sensing. Run the MCP server with npx @ruvnet/ruview@0.3.1 mcp start or docker run -p 3000:3000 ruvnet/wifi-densepose:latest for simulated data without hardware.

What hardware and prerequisites are needed?+

Full CSI sensing requires an ESP32-S3 ($9), ESP32-C6 ($6–10), or research NIC (Intel 5300 / Atheros). For evaluation, the Docker image runs with simulated data. Optional Cognitum Seed (~$140) adds persistent storage and witness chain; standard WiFi laptops provide RSSI-only presence detection.

Which smart-home platforms and AI clients does RuView support?+

RuView integrates with Home Assistant (MQTT), Apple Home/HomePod (HAP bridge), Google Home, Amazon Alexa, and Matter endpoints. The MCP server works with Claude Code, Codex, and other MCP-compatible AI clients via the @ruvnet/ruview metaharness.

Is RuView free and open source?+

Yes, RuView is MIT-licensed open source. Pretrained models are freely available on Hugging Face (ruvnet/wifi-densepose-pretrained, ruvnet/wifi-densepose-mmfi-pose). The system runs entirely offline with no cloud fees or subscriptions.

What accuracy can I expect from WiFi-based pose estimation?+

The MM-Fi pose model achieves 82.69% torso-PCK@20 (single model) or 83.59% (ensemble). The on-device ESP32 17-keypoint model is first-cut (3.0% PCK@20) and below production targets. Presence detection reaches 82.3% held-out temporal-triplet accuracy with the published encoder.

How do I install RuView?+

Open the source repository on GitHub and follow its README. RuView is a mcp server — MCP Agents Market links you directly to the official repo.

Is RuView free?+

RuView is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.

Related searches