# BrainFlow Biosensing Boards

Connect an AI agent to BrainFlow-compatible biosensing boards to stream, record, and inspect signals. Try the simulated mode before connecting a board.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 23
- Author: K-Dense-AI
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/K-Dense-AI/lab-instrument-mcps/tree/HEAD/servers/health/brainflow-biosensors
- Updated: 2026-09-26
- HTML: https://affpapa.org/en/nevibecode/mcp/brainflow-biosensing-boards

## What it does

The server works with boards supported by BrainFlow, including OpenBCI, Muse, Neurosity, Unicorn, and BrainBit. An agent can collect a stream, record it with event markers, inspect EEG band powers, and check signal quality by electrode. Simulation lets you test the connection without a physical device.

To connect hardware, choose a board and provide its address or other connection details when needed. Testing has covered BrainFlow’s synthetic board and a built-in simulation, but not physical hardware. Verify the connection with your board before relying on its output. The project describes this as a research tool, not equipment for medical decisions.

Add it to Claude Code with `claude mcp add labmcp-brainflow -- uvx labmcp-brainflow`. Close any other app using the device first. On Linux, serial-port access may require membership in the `dialout` group.

## Requirements
- Needs: Python and uv (commands run via uvx)
- Environment variables: `LABMCP_ADDRESS`, `LABMCP_SIMULATE`, `LABMCP_READ_ONLY`, `LABMCP_LIMITS` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add --env LABMCP_ADDRESS=<LABMCP_ADDRESS> --env LABMCP_SIMULATE=<LABMCP_SIMULATE> --env LABMCP_READ_ONLY=<LABMCP_READ_ONLY> --env LABMCP_LIMITS=<LABMCP_LIMITS> --transport stdio brainflow-biosensors -- uvx labmcp-brainflow
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from labmcp-brainflow <command>

### Codex

**Platform CLI**
```bash
codex mcp add brainflow-biosensors --env LABMCP_ADDRESS=<LABMCP_ADDRESS> --env LABMCP_SIMULATE=<LABMCP_SIMULATE> --env LABMCP_READ_ONLY=<LABMCP_READ_ONLY> --env LABMCP_LIMITS=<LABMCP_LIMITS> -- uvx labmcp-brainflow
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from labmcp-brainflow <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "brainflow-biosensors": {
            "command": "uvx",
            "args": [
                "labmcp-brainflow"
            ],
            "env": {
                "LABMCP_ADDRESS": "<LABMCP_ADDRESS>",
                "LABMCP_SIMULATE": "<LABMCP_SIMULATE>",
                "LABMCP_READ_ONLY": "<LABMCP_READ_ONLY>",
                "LABMCP_LIMITS": "<LABMCP_LIMITS>"
            }
        }
    }
}
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from labmcp-brainflow <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "brainflow-biosensors": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "labmcp-brainflow"
            ],
            "env": {
                "LABMCP_ADDRESS": "<LABMCP_ADDRESS>",
                "LABMCP_SIMULATE": "<LABMCP_SIMULATE>",
                "LABMCP_READ_ONLY": "<LABMCP_READ_ONLY>",
                "LABMCP_LIMITS": "<LABMCP_LIMITS>"
            }
        }
    }
}
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from labmcp-brainflow <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e LABMCP_ADDRESS=<LABMCP_ADDRESS> -e LABMCP_SIMULATE=<LABMCP_SIMULATE> -e LABMCP_READ_ONLY=<LABMCP_READ_ONLY> -e LABMCP_LIMITS=<LABMCP_LIMITS> brainflow-biosensors uvx labmcp-brainflow
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from labmcp-brainflow <command>

## When to use it
- stream biosignals from a BrainFlow board
- record data with event markers
- inspect EEG band powers over a recording window
- check signal quality for individual electrodes
- test the MCP connection in simulation

## Example prompts
- Check the connection to the `cyton` board at `/dev/cu.usbserial-DM00Q0QN`.
- Record data from the connected board and add an event marker.
- Show the EEG band powers and electrode signal quality.

## Similar
- [Zotero MCP](https://affpapa.org/en/nevibecode/mcp/zotero-mcp.md) — MCP server · ★ 5585
- [arxiv-mcp-server](https://affpapa.org/en/nevibecode/mcp/arxiv-mcp-server.md) — MCP server · ★ 3235
- [PaperBanana](https://affpapa.org/en/nevibecode/mcp/paperbanana.md) — MCP server · ★ 2418
- [MATLAB MCP Server](https://affpapa.org/en/nevibecode/mcp/matlab-mcp-server.md) — MCP server · ★ 1723
- [Hex Research](https://affpapa.org/en/nevibecode/mcp/hex-research.md) — MCP server · ★ 584
- [DocsAgent — Zotero, Obsidian & Apple Notes MCP Server](https://affpapa.org/en/nevibecode/mcp/docsagent-zotero-obsidian-apple-notes-mcp-server.md) — MCP server · ★ 578

From the same set: [k-dense-ai/lab-instrument-mcps](https://affpapa.org/en/nevibecode/by/k-dense-ai/lab-instrument-mcps.md) — 15 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md