BrainFlow Biosensing Boards MCP Server

tec Unicorn, BrainBit and many more. It covers recording with event markers, EEG band powers and per-electrode signal-quality checks. Its 12 documented tools cover board, streaming.

People who work with board and streaming and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

One of 32 MCP servers published from k-dense-ai/lab-instrument-mcps. Stars and repository activity are shared across all of them. See all 32 →

VERIFIED ACTIVE

LAST COMMIT 2026-09-26 · VERIFIED 2026-09-30

Apache-2.0 · Python servers · how we verify → /methodology

01 · Install BrainFlow Biosensing Boards

Claude Code

claude mcp add k-dense-ai-lab-instrument-mcps-servers-h -- uvx labmcp-brainflow

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "k-dense-ai-lab-instrument-mcps-servers-h": {
      "command": "uvx",
      "args": [
        "labmcp-brainflow"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

repo age created 2026-09-25 - young repo, little track record yet

license Apache-2.0 - declared in the repository

pypi package labmcp-brainflow - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.K-Dense-AI is GitHub-verified and matches the repo owner

03 · What BrainFlow Biosensing Boards can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

g. after it was power cycled or a cable was re-plugged), and start continuous acquisition into BrainFlow's ring buffer (the board's radio/LEDs switch on.

Capability map

Tools grouped from the project's README - what BrainFlow Biosensing Boards lets an agent do.

read & search

6 tools - e.g. EEG 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 powe; Describe the connected board: channel…

get_band_powers · get_board_info · get_command_log · get_connection_info · get_signal_quality · list_supported_boards

run & execute

2 tools - e.g. Start continuous acquisition into BrainFlow's ring buffer (the board's radio/LEDs switch on; nothing is applied to the participant). Needed for insert_marker; r; Stop acquisition (saves battery). A record…

start_streaming · stop_streaming

Configure

1 tool - e.g. Send a raw board-specific command to the firmware through BrainFlow's config_board (e.g. OpenBCI channel settings 'x1060110X', test signals, or Muse presets 'p5

configure_board

create & write

1 tool - e.g. Write an event marker into the data stream at the current sample (for event-related experiments: stimulus onsets, condition changes). Requires start_streaming;

insert_marker

Reconnect

1 tool - e.g. Close and re-open the connection to the instrument (e.g. after it was power cycled or a cable was re-plugged).

reconnect

Record

1 tool - e.g. Record duration_s seconds and return per-channel statistics, event markers and downsampled traces. Uses the live stream if one is running, otherwise starts a te

record

Limitations (from the README)

- 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), foll

04 · Who maintains BrainFlow Biosensing Boards

BrainFlow Biosensing Boards is maintained by k-dense-ai. We track 32 MCP servers from k-dense-ai - 32 actively maintained, 9 combined GitHub stars, oldest repo from Sep 2026. Full record: all servers from k-dense-ai.

  1. Tecan Cavro Syringe Pump MCP server for Tecan Cavro syringe pumps (XLP 6000, XMP 6000, XCalibur) over the DT protocol. ★ 9
  2. Micro-Manager Microscope MCP server for microscopes controlled by Micro-Manager (pymmcore-plus). ★ 9
  3. Opentrons OT-2 / Flex MCP server for Opentrons OT-2 and Flex liquid-handling robots (HTTP API). ★ 9
  4. Atlas Scientific EZO Sensors MCP server for Atlas Scientific EZO sensor circuits (pH, ORP, DO, EC, RTD, HUM, CO2, PRS) over UART. ★ 9
  5. New Era Syringe Pump MCP server for New Era Pump Systems syringe pumps (NE-1000 family, RS-232). ★ 9
  6. Alicat Mass Flow & Pressure Controller MCP server for Alicat mass flow and pressure meters/controllers. ★ 9

05 · Facts

category
other - actively maintained as of 2026-09-30.
registry
io.github.K-Dense-AI/labmcp-brainflow (active, first published 2026-09-26 · 3 versions)
packages
pypi:labmcp-brainflow

06 · BrainFlow Biosensing Boards FAQ

Is BrainFlow Biosensing Boards still maintained?

Yes - as of 2026-09-30, its last commit was 2026-09-26. We re-verify nightly.

What can BrainFlow Biosensing Boards do?

g. after it was power cycled or a cable was re-plugged), and start continuous acquisition into BrainFlow's ring buffer (the board's radio/LEDs switch on.

How do I install BrainFlow Biosensing Boards?

Run `uvx labmcp-brainflow`. You can also paste the ready-made client config above.

Does BrainFlow Biosensing Boards run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to BrainFlow Biosensing Boards