Onsense

io.github.hufirst由 GitHub 帳號 hufirst 發布v0.3.20更新於 Oct 24, 2026

Android phone camera, sensors & files for any MCP client — local, no cloud, no ADB.

概覽

AI 產生的概覽

讓 AI 助理透過本機 Wi-Fi 查看已配對 Android 手機的相機、讀取感測器,並在手機與電腦之間傳送照片、檔案與剪貼簿內容。

可以做什麼
Onsense 是 onSense Android 應用程式在電腦端的 stdio MCP 代理。工具包括 get_live_frame(取得目前相機畫面)、read_sensors(讀取電量、環境光、加速度計)、recent_photos 與 get_photo(瀏覽與取得手機照片)、rename_photo(重新命名已取得的檔案)、get_reference(取得手機指定的相機畫面、照片或任意檔案),以及 get_cam_fps/set_cam_fps(讀取與設定相機影格率)。選用的 clip 橋接常駐程式監聽 8770 埠,可將手機上的圖片、檔案與剪貼簿內容推送到電腦,啟用後也可拉取電腦剪貼簿。
適用情境
當電腦上的助理需要來自附近 Android 手機的即時畫面或感測器資料,或需要在手機與電腦之間傳送照片、檔案與剪貼簿內容時使用。適合不希望使用雲端中轉與 ADB 的本機隱私情境。
執行需求
透過 uvx 在本機執行(uv 會自動下載受管理的 Python)。需要手機安裝 onSense Android 應用程式並與電腦處於同一本機 Wi-Fi 網路,需要相容 MCP 的 stdio 用戶端,並需一次性配對,將手機位址與權杖儲存到 ~/.onsense/pair.json。選用環境變數包括 PHONE_BASE、PHONE_TOKEN、ONSENSE_CLIP_DIR、ONSENSE_CLIP_MAX_MB、ONSENSE_CLIP_ALLOW_PULL、ONSENSE_CLIP_SET_CLIPBOARD 與 ONSENSE_TEST_FRAME。
安裝前請注意
配對權杖是儲存在 ~/.onsense/pair.json 的憑證,用於 HMAC 簽章與 AES-256-GCM 加密請求,應妥善保管。clip 常駐程式綁定所有網路介面,並在應用層拒絕非私有 IP 連線,不要將其暴露到網際網路。剪貼簿注入與電腦到手機的剪貼簿拉取預設關閉,啟用後手機可讀取或覆寫電腦剪貼簿。取得的照片與檔案會寫入磁碟,大型傳輸會在記憶體中緩衝。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Onsense,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

onsense — Phone Camera, Sensors & Files for PC AI Agents

Don't describe it. Let your AI see it. onsense is the PC-side MCP broker for the onSense Android app: run uvx onsense pair on your PC, and any MCP-capable AI — Claude Code, Claude Desktop, Codex, or your own agent — can see through your phone's camera, read its sensors, and move files & clipboard both ways. No cloud relay. No ADB.

[onSense demo — Claude Code reads the phone's sensors and camera through onSense]

Claude Code, running on the PC, reads the phone's sensors and looks through its camera to answer — live, over local Wi-Fi.

[onSense demo — Codex does the same through onSense]

…and the same with Codex. onSense is a standard MCP server, so any MCP client works.


Architecture

text
Android phone (onSense app)           PC (this package)           AI client  HTTP provider :8080        ←→    stdio MCP broker          Claude / Codex / …  camera frames, photos,           onsense serve               natural-language or  sensors, QR pairing              onsense clip :8770          /onsense tool calls
  • The phone runs an HTTP provider on port 8080. It exposes camera frames, recent photos, and sensor readings, all gated by a pairing token.
  • The PC package (onsense) is a stdio MCP broker. It translates MCP tool calls from your AI client into HTTP requests to the phone.
  • Discovery uses mDNS (_onsense._tcp.local.). If the phone's IP changes, the broker rediscovers it automatically — no manual reconfiguration needed.
  • An optional clip bridge daemon on port 8770 lets the phone push camera frames, files, and clipboard content to the PC (and, if enabled, lets the phone pull from the PC clipboard).

Requirements

  • uv (provides uvx; downloads a managed Python automatically — no separate Python install needed)
  • The onSense Android app installed on a phone on the same local Wi-Fi network as your PC
  • An MCP-compatible AI client such as Claude Code, Codex, or any stdio MCP client

Quick Start

0. Fresh PC without uv? Use the app's setup helper (recommended)

On a clean PC, uvx doesn't exist yet and the command below will fail with "'uvx' is not recognized". The easiest fix: install the onSense app first, tap "Start PC setup helper", and open the shown address on your PC. It gives you a one-line command that installs uv, pairs, and registers the MCP server in one go — and because the PC connects out to the phone, it also sidesteps the Windows firewall entirely.

Prefer installing uv yourself? One line:

powershell
# Windows (PowerShell)irm https://astral.sh/uv/install.ps1 | iex$env:Path = "$env:USERPROFILE\.local\bin;$env:Path"   # make uvx visible in this same shell
bash
# macOS / Linuxcurl -LsSf https://astral.sh/uv/install.sh | shexport PATH="$HOME/.local/bin:$PATH"

1. Pair your phone

Run this once. The PC prints a QR code; scan it from the onSense app ("Scan PC QR"). The phone pushes its address and token to the PC, which registers the MCP server automatically.

bash
uvx onsense pair

After pairing, restart your AI client once so it picks up the new onsense MCP server.

2. Use it

Ask your AI client naturally:

"Take a photo of what's in front of my phone." "What are the current sensor readings?" "Show me the last 5 photos on my phone."

The MCP tools are called automatically. In Claude Code you can also use the bundled /onsense slash command (installed during pairing).

3. Diagnose problems

bash
uvx onsense doctor           # checks Python, uv, MCP, Claude registration, mDNS, phone reachabilityuvx onsense doctor --base http://192.168.1.5:8080 --token YOUR_PAIRING_TOKEN

Windows: QR scan times out?

The #1 cause is the Windows firewall dropping the phone's inbound connection:

  • If your Wi-Fi network profile is Public, inbound traffic is blocked hard. Switch it to Private (Settings → Network → your Wi-Fi → Network profile), or just use the app's PC setup helper, which needs no inbound port at all.

  • On a Private network, add a durable allow rule once (run as administrator):

    powershell
    uvx onsense pair --fix-firewall

    The first-run firewall popup is program-path-scoped and uvx's ephemeral paths silently invalidate it — the port-scoped rule above (TCP 8765–8774, Private) is what actually sticks.

  • If port 8765 is taken, pair automatically falls back to the next free port (up to 8774) and the QR reflects the real port — no action needed.


Subcommands

CommandWhat it does
uvx onsense pairDisplay a QR code on the PC; phone scans it and pushes {base, token}; registers MCP automatically
uvx onsense pair "onsense://pair?base=...&token=..."Parse a pairing URI directly (phone-displayed QR → manual copy)
uvx onsense pair --img screenshot.pngDecode a pairing QR from a screenshot file (requires opencv)
uvx onsense serveRun the MCP server (stdio). Also starts the clip daemon automatically unless --no-clip is passed
uvx onsense serve --no-clipRun the MCP server only, without starting the clip daemon
uvx onsense clipRun the clip bridge daemon standalone (port 8770)
uvx onsense clip --allow-pullEnable phone→pull: phone can GET /clip to retrieve the PC clipboard
uvx onsense clip --set-clipboardAuto-inject received content into the PC OS clipboard (off by default)
uvx onsense pair --fix-firewall(Windows, admin) Add the durable port-scoped firewall rule, then pair as usual
uvx onsense doctorDiagnose installation, connectivity, and phone reachability
uvx onsense statsShow local-only activation stats (--json, --reset). Nothing is uploaded automatically

Other MCP clients (Claude Desktop, Codex, …)

uvx onsense pair auto-registers the server with Claude Code (via claude mcp add) — this one-line auto-setup is Claude Code-specific. The MCP server itself is standard stdio MCP, so any MCP-compatible client works once you add it manually. Run uvx onsense pair once first: it saves your phone's address and token to ~/.onsense/pair.json, which the server reads at request time — so you don't put the token in each client's config, and the phone's IP is auto-tracked via mDNS.

Claude Desktop — add to claude_desktop_config.json:

json
{ "mcpServers": { "onsense": { "command": "uvx", "args": ["onsense", "serve"] } } }

Codex — register via the CLI (verified with Codex CLI 0.142.5):

bash
codex mcp add onsense -- uvx onsense serve

Codex sandbox note: Codex's default sandbox blocks network access, so the MCP server can't reach your phone and tool calls fail silently. Run Codex with network access enabled (e.g. --sandbox danger-full-access, or a sandbox policy that permits network) so onsense can talk to the phone on your LAN.

or add to ~/.codex/config.toml:

toml
[mcp_servers.onsense]command = "uvx"args = ["onsense", "serve"]

Restart the client once after adding the server. Any other stdio MCP client works the same way — point it at uvx onsense serve.


MCP Tools

These tools are exposed to your AI client after pairing:

ToolDescription
get_live_frame()Capture the current camera frame from the phone (returns JPEG image)
read_sensors()Return phone sensor readings as JSON: battery level/charging state, ambient light (lux), accelerometer (x/y/z)
recent_photos(limit=10)List recent photos on the phone: id, name, date_added, size, width, height
get_photo(id, max_width=1024, save_original=False)Fetch a specific photo by id (downscaled to max_width); use ids from recent_photos. Also saves it to the same Downloads folder as get_reference and returns the path, so the image survives the conversation. save_original=True archives full resolution instead of the downscaled copy
rename_photo(path, name)Rename a fetched file to describe what the image actually shows (photo_1000024531.jpg → whiteboard_sprint_plan.jpg). The AI calls this right after viewing, so it costs no extra tokens
get_reference()Fetch whatever the phone has designated as its reference source — a live camera frame, a captured photo, or an arbitrary file (incl. non-images) — saved to disk with path + metadata. The core of the file/capture bridge
get_cam_fps()Read the phone's current camera FPS setting (15 = high-performance, 2 = balanced, 0 = on-demand)
set_cam_fps(fps)Set the phone's camera FPS: 15 (high-performance), 2 (balanced, recommended), or 0 (power-saving / on-demand)

If the phone's IP changes, the broker retries using mDNS autodiscovery before surfacing an error.


Clip Bridge (Phone ↔ PC File & Clipboard)

onsense serve automatically starts a clip daemon on port 8770. You can also run it standalone with onsense clip.

Phone → PC push (POST /clip)

The onSense Android app can push content to the PC:

  • Images are saved to disk as latest.jpg (in ONSENSE_CLIP_DIR, default <tempdir>/onsense/).
  • Text files are saved to disk.
  • Other files (video, PDF, etc.) are saved to disk by filename.
  • If --set-clipboard is active, images and text are also injected into the PC OS clipboard so you can paste with Ctrl+V immediately.

By default, --set-clipboard is off — files are saved to disk but the clipboard is not touched.

PC → Phone pull (GET /clip)

Off by default. Enable with:

bash
uvx onsense clip --allow-pull

When enabled, the phone can GET /clip to retrieve the current PC clipboard content (copied files first, then images, then text). Returns 204 if the clipboard is empty.

Ports and environment variables

VariableDefaultPurpose
PHONE_BASE(from pairing)Phone HTTP base URL, e.g. http://192.168.1.5:8080
PHONE_TOKEN(from pairing)Pairing auth token
ONSENSE_CLIP_DIR<tempdir>/onsenseDirectory where pushed files are saved
ONSENSE_CLIP_MAX_MB200Maximum incoming file size in MB (0 = unlimited)
ONSENSE_CLIP_ALLOW_PULL0Set to 1 to enable PC→phone pull without the CLI flag
ONSENSE_CLIP_SET_CLIPBOARD0Set to 1 to auto-inject into OS clipboard without the CLI flag
ONSENSE_TEST_FRAME(unset)Local JPEG path returned by get_live_frame when phone is unreachable

Security

Local network only. The PC-side services bind to all interfaces but reject connections from non-private IP addresses at the application layer. They are not intended to be exposed to the internet.

HMAC request signing. The pairing token is never sent in cleartext. Every authenticated request is signed with HMAC-SHA256 over METHOD\npath\ntimestamp\nnonce\nalgorithm, keyed by a signing key derived from the pairing token via HKDF-SHA256 (a key separate from the encryption key), and carries X-Ts / X-Nonce / X-Sig / X-Enc headers. Servers verify in constant time, reject timestamps outside a ±300 s window, and reject reused nonces — so a sniffed request cannot be replayed and the token cannot be stolen off the wire. New Android installs generate a 128-bit random token, stored on the phone and in ~/.onsense/pair.json (chmod 600) after pairing. (The /health endpoint is unauthenticated.) See PROTOCOL.md for the exact wire format.

Pull and clipboard injection are off by default. GET /clip (phone pulls PC clipboard) and OS clipboard auto-injection (phone push → Ctrl+V) are disabled unless you explicitly pass --allow-pull or --set-clipboard.

Encrypted bodies (AES-256-GCM). Sensitive payloads — camera frames, photos, sensor data, files, and clipboard content — are encrypted between the phone and your PC with AES-256-GCM (no cloud in between, so there is no third party to decrypt them). The key is derived from the pairing token via HKDF-SHA256 (a key separate from the signing key); each message uses a fresh 96-bit nonce, and the GCM tag authenticates the body and binds it to its request (so tampering or response substitution is rejected). A passive sniffer on the same Wi-Fi sees only ciphertext. Low-sensitivity metadata stays plaintext: the open /version and /health endpoints, HTTP error responses, and the saved-file path returned after a push. (Note: large transfers currently buffer the body in memory while encrypting/decrypting — chunked streaming for very large files is a future step. Transport-level TLS is also a possible future hardening.)

File size cap. Incoming pushes are rejected if they exceed ONSENSE_CLIP_MAX_MB (default 200 MB). Set to 0 to remove the cap.

Reporting a vulnerability. Please report security issues privately — see SECURITY.md. Do not open a public issue for security reports.


License

MIT. See LICENSE.

來源:README.md,提交 8027d37

工具

0
SourceWeft 尚未在沙箱中啟動過該軟體包,因此其工具未知。

版本歷史

1
  1. v0.3.20最新Sep 16, 2026

評分

已滿足適用檢查項的 50%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分

    請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。

  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分