BrainFlow Biosensing Boards

io.github.K-Dense-AI由 GitHub 帳號 K-Dense-AI 發布v0.1.2更新於 Oct 24, 2026

MCP server for EEG/EMG/ECG/PPG boards via BrainFlow (OpenBCI, Muse, Neurosity, Unicorn, BrainBit).

發布方自己的服務:BrainDog

概覽

AI 產生的概覽

本機 MCP 伺服器,讓助理透過 BrainFlow 支援的生物感測板擷取、錄製並分析 EEG、EMG、ECG 與 PPG 資料。

可以做什麼
列出支援的板卡,並回報連線資訊、板卡資訊與指令日誌,包括目前是模擬或實機、是否唯讀以及生效的安全限制。啟動與停止連續擷取,在斷電或重新插線後重新連線,並向資料流插入事件標記。依指定時長錄製並回傳各通道統計、標記與降取樣波形,可選擇將全取樣率資料另存為新的 CSV 或 BrainFlow 檔案。計算 EEG 頻段功率與峰值頻率,並檢查每個電極是否斷線、飽和、受市電干擾或振幅過高。向板卡韌體送出原始專用指令,例如通道設定或預設。
適用情境
適合使用 OpenBCI、Muse、Neurosity、Unicorn、BrainBit 等板卡進行研究或嗜好級生物訊號工作,例如讓助理檢查電極接觸、帶事件標記錄製短片段或比較頻段功率。也可在沒有硬體的模擬模式下先行試用。
執行需求
以 Python 套件(uvx labmcp-brainflow)透過 stdio 在本機執行,僅限桌面。需要受支援的板卡,並透過 LABMCP_ADDRESS 或選項提供連線資訊(序列埠、藍牙 MAC、IP 位址或序號),還需要 BrainFlow;藍牙連線需本機適配器或 BLED112 加密狗。可選 LABMCP_LIMITS、LABMCP_READ_ONLY、LABMCP_SIMULATE。Linux 下序列埠存取可能需要加入 dialout 群組。
安裝前請注意
僅供研究使用,不是醫療器材。configure_board 會把原始字串未經檢查直接送給韌體,可能開啟導聯脫落阻抗電流等輸出;設定會保留到變更或斷電為止。啟動串流與錄製會控制真實硬體,record 可將檔案寫入指定路徑。使用前先關閉佔用裝置的其他程式。README 顯示尚未在實機上驗證。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 BrainFlow Biosensing Boards,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

BrainFlow Biosensing Boards — MCP Server

Let an AI agent stream, record and analyse EEG, EMG, ECG, EOG, PPG and EDA from the biosensing boards supported by the open-source BrainFlow SDK: OpenBCI, Muse, Neurosity, g.tec Unicorn, BrainBit and many more. It covers recording with event markers, EEG band powers and per-electrode signal-quality checks.

Research use only. This is not a medical device. Do not use it to diagnose, monitor or treat anyone. Follow the board manufacturer's safety instructions (battery operation, electrical isolation, skin preparation). This server does not change any of them.

Packagelabmcp-brainflow
InstrumentsOpenBCI Cyton, Cyton+Daisy, Ganglion, Galea (USB dongle, BLE, WiFi Shield) · Muse 2 / S / S Athena / 2016 · Neurosity Crown / Notion · g.tec Unicorn · BrainBit · Callibri · Enophone · Mentalab Explore · EmotiBit · FreeEEG32/128 · NeuroPawn Knight · Shimmer3 · any other board in BrainFlow's BoardIds
InterfacesUSB serial dongle, Bluetooth LE (native or BLED112 dongle), WiFi, vendor SDKs (all through BrainFlow)
ProtocolBrainFlow SDK ≥ 5.21: BoardShim, BrainFlowInputParams, DataFilter (User API, Supported Boards, Data Format)
Status🧪 simulated: tested against BrainFlow's own synthetic board and a built-in fake, not yet verified on hardware. Report a hardware test

Try it without hardware

bash
uvx labmcp-brainflow --simulate --check

--simulate runs BrainFlow's own SYNTHETIC_BOARD, so the real BrainFlow code path runs: 16 EXG channels at 250 Hz with sine waves at 5, 10, 15 … 80 Hz plus accelerometer, gyro, PPG, EDA and temperature rows. On platforms where BrainFlow's native library can't load, or with --option simulator=fake, a pure-numpy stand-in is used instead. It simulates an 8-channel, 250 Hz EEG headset with 1/f background, posterior alpha at 10 Hz and one badly attached electrode (Fp2, heavy 50 Hz pickup), so the signal-quality check has something to find.

Connect your board

  1. Pick the board with --option board=<alias> (or any BrainFlow BoardIds name such as ANT_NEURO_EE_411_BOARD, or a numeric id). The list_supported_boards tool prints this table too.
  2. Give the connection detail with --address. Depending on the board, BrainFlow expects a different BrainFlowInputParams field, and the server fills in the right one:
Board (--option board=)--address isRequired?Notes
cyton, cyton_daisyserial port of the USB dongleyesmacOS: use /dev/cu.usbserial-*, not /dev/tty.*
ganglion (native BLE)Bluetooth MACno (auto-discovery)FW 2 boards: --option other_info=fw:2
ganglion_dongleserial port of the BLED112 dongleyesoptional --option mac_address=
cyton_wifi, cyton_daisy_wifi, ganglion_wifiWiFi Shield IP (192.168.4.1 in direct mode)no (SSDP)--option ip_port= (default 6789)
muse_2, muse_s, muse_s_athena, muse_2016Bluetooth MACno--option serial_number=Muse-XXXX; PPG: --option other_info=p50 (Muse 2) / p61 (Muse S)
muse_2_bled, muse_s_bledserial port of the BLED112 dongleyes
crown, notion_1, notion_2device serial numbernosame network, broadcast must be allowed
unicorn, brainbitdevice serial numbernoUnicorn: pair with the supplied dongle
enophone, explore_4, explore_8Bluetooth MACLinux only
emotibitnetwork broadcast addressno
freeeeg32, freeeeg128, neuropawn_knight, shimmer3, ironbci_32serial portyes
playbackpath of a file saved in BrainFlow formatyes--option master_board=<board it was recorded with>
syntheticnothingBrainFlow's synthetic board

For a board that isn't listed, the server infers the field from the address format: COM3 or /dev/… becomes a serial port, AA:BB:… a MAC address, a.b.c.d an IP address, and anything else a serial number. You can also set any field directly with --option serial_port=… / mac_address=… / ip_address=… / serial_number=… / other_info=… / timeout=….

  1. Test the connection:
    bash
    uvx labmcp-brainflow --option board=cyton --address /dev/cu.usbserial-DM00Q0QN --check   # macOSuvx labmcp-brainflow --option board=cyton_daisy --address COM3 --check                  # Windowsuvx labmcp-brainflow --option board=muse_2 --option serial_number=Muse-1A2B --checkuvx labmcp-brainflow --option board=unicorn --check
    Close other programs that hold the device (OpenBCI GUI, Muse app) first. On Linux, add yourself to the dialout group for serial ports.

Add to your MCP client

Claude Code

bash
claude mcp add eeg -- uvx labmcp-brainflow --option board=cyton --address /dev/ttyUSB0

Claude Desktop / Cursor / Windsurf (claude_desktop_config.json, .cursor/mcp.json, …)

json
{  "mcpServers": {    "eeg": {      "command": "uvx",      "args": ["labmcp-brainflow", "--option", "board=cyton", "--address", "/dev/ttyUSB0"]    }  }}

With --read-only, the agent can still record and analyse data (a temporary stream is started for each recording) but cannot leave the stream running, insert markers or send configure_board commands. stop_streaming stays available.

Tools

ToolKindDescription
configure_board⚠️ hazardSend a raw board-specific command to the firmware through BrainFlow's config_board (e.g. OpenBCI channel settings 'x1060110X', test signals, or Muse presets 'p50'/'p61' to enable PPG).
get_band_powers👁 readEEG band powers (delta 1-4, theta 4-8, alpha 8-13, beta 13-30, gamma 30-50 Hz) over the most recent window_s seconds: BrainFlow's channel-averaged relative powers plus per-channel absolute (uV^2) and relative powers and the peak frequency. Records a fresh window if not streaming.
get_board_info👁 readDescribe the connected board: channel names by type (EEG/EMG/ECG/EOG share the EXG rows on most boards), sampling rate, available presets (data buffers) and streaming state.
get_command_log👁 readReturn the most recent raw commands sent to / replies received from the instrument (newest last). Useful for debugging and for recording what was done.
get_connection_info👁 readReport which instrument is connected (identity, address, simulated or real), whether the server is read-only, and the active safety limits. Call this first.
get_signal_quality👁 readCheck every EXG channel for common electrode problems: flat line (disconnected), railed (amplifier saturated, OpenBCI Cyton boards), strong 50/60 Hz mains noise (poor contact or missing reference), and implausibly high amplitude (movement, muscle, loose electrode).
insert_marker🎛 controlWrite an event marker into the data stream at the current sample (for event-related experiments: stimulus onsets, condition changes). Requires start_streaming; markers appear in record results and saved files.
list_supported_boards👁 readList common BrainFlow boards: the --option board= alias, BrainFlow board id, and which connection detail --address must hold (serial port, Bluetooth MAC, IP address or serial number). Any other BrainFlow BoardIds name or numeric id is accepted too. Does not need a board.
reconnect🛑 safetyClose and re-open the connection to the instrument (e.g. after it was power cycled or a cable was re-plugged).
record👁 readRecord duration_s seconds and return per-channel statistics, event markers and downsampled traces. Uses the live stream if one is running, otherwise starts a temporary one. The full data (every row, full sampling rate) can be written to save_path. stop_streaming ends a recording early.
start_streaming🎛 controlStart continuous acquisition into BrainFlow's ring buffer (the board's radio/LEDs switch on; nothing is applied to the participant). Needed for insert_marker; record then reads from the live stream. Call stop_streaming when finished.
stop_streaming🛑 safetyStop acquisition (saves battery). A record in progress ends at once with the data acquired so far. Data already in the buffer is kept until the next stream starts or the session is released (reconnect).

Safety limits

LimitDefaultMeaning
max_record_duration_s60 sLongest recording or analysis window (record, get_band_powers, get_signal_quality) an agent may request

Override at launch: --limit max_record_duration_s=600. BrainFlow boards measure; the only tool that can switch on an output (for example an impedance-test current through the electrodes, or the bias drive on a channel) is configure_board, a raw firmware passthrough that is marked as a hazard so MCP clients ask before running it.

Example prompts

  • "Check the signal quality on all 8 Cyton channels and tell me which electrodes need more gel."
  • "Record 30 s eyes-closed and 30 s eyes-open, save both as CSV in ~/data/sub-01/, and compare occipital alpha power."
  • "Start streaming. I'll run an oddball task: insert marker 1 for standards and 2 for targets when I tell you. Then save the session in BrainFlow format."
  • "What's the peak alpha frequency on O1 and O2 over the last 10 seconds?"
  • "Is there 50 or 60 Hz mains noise in this setup, and on which channels?"
  • "List the boards you support and tell me how to connect my Muse S."

Notes

  • How the band powers are computed. average_relative comes from BrainFlow's DataFilter.get_avg_band_powers(apply_filter=True): detrend, 48–52 and 58–62 Hz band-stop, 2–45 Hz band-pass, Welch PSD, then bands of 1–4, 4–8, 8–13, 13–30 and 30–50 Hz averaged over channels and normalised to sum to 1. Per-channel values use detrend, a 50/60 Hz notch and a 1–45 Hz 4th-order zero-phase Butterworth (BrainFlow DataFilter), followed by a Welch PSD (Hann window, 50 % overlap, ≈0.5 Hz bins). Absolute band power is the integrated PSD in µV², and gamma is effectively 30–45 Hz.
  • Signal-quality verdicts (EEG-oriented thresholds): flat means the raw SD is below 0.5 µV (disconnected); railed means at least 90 % of the ADS1299 input range is used (OpenBCI Cyton family only, using BrainFlow's formula with gain 24, set by --option exg_gain=); line_noise means 50 or 60 Hz power exceeds the whole 1–45 Hz power; high_amplitude means the band-passed RMS is above 100 µV. EMG/ECG recordings will naturally be "high amplitude".
  • Units. BrainFlow returns EXG in µV "wherever possible". The OYMotion gForce armbands return ADC counts. Accelerometer, PPG and similar channels use board-specific units. Timestamps are Unix seconds.
  • Presets. Some boards stream several buffers with different sampling rates, for example Muse EEG (default), IMU (auxiliary) and PPG (ancillary). Pass preset= to get_board_info and record.
  • Markers go into the default preset's marker row and need an active stream (start_streaming). You can insert them while record is running. Value 0 is reserved.
  • Saved files. save_path must be a new file (.csv; .csv, .tsv or .txt for save_format="brainflow"): ~ is expanded, missing folders are created, an existing file is never overwritten, and the path is checked before recording starts. save_format="csv" writes labelled columns for every row. save_format="brainflow" writes DataFilter.write_file output, which you can replay with --option board=playback --address file.csv --option master_board=<board>.
  • configure_board passes a string straight to the board firmware through BrainFlow's config_board, for example OpenBCI channel settings or Muse presets. Nothing is checked: some commands switch on outputs such as the lead-off (impedance-test) current. Settings persist until changed or the board is power-cycled; check the board's SDK documentation for valid commands.
  • Streams. record, get_band_powers and get_signal_quality start a temporary stream when none is running and stop it afterwards, unless start_streaming was called meanwhile (the stream then stays on) or another recording still uses it. stop_streaming ends a running record at once; it returns only the data acquired so far, with stopped_early: true.
  • reconnect (and stopping the server) stops the stream and calls release_session, which frees the serial port or BLE connection.

Hardware verification

ModelFirmwareInterfaceVerified byDate
none yet: be the first

來源:servers/health/brainflow-biosensors/README.md,提交 46545ea

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

2
  1. v0.1.2最新Sep 27, 2026
  2. v0.1.0Sep 26, 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

其他 Brain 整合