index.html•7.19 kB
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>BCI-MCP Documentation</title>
<link rel="stylesheet" href="styles.css">
<link rel="icon" href="favicon.svg" type="image/svg+xml">
</head>
<body>
<a href="https://github.com/enkhbold470/bci-mcp" class="github-corner" aria-label="View source on GitHub">
<svg width="80" height="80" viewBox="0 0 250 250" style="fill:var(--primary-color); color:#fff; position: absolute; top: 0; border: 0; right: 0;" aria-hidden="true">
<path d="M0,0 L115,115 L130,115 L142,142 L250,250 L250,0 Z"></path>
<path d="M128.3,109.0 C113.8,99.7 119.0,89.6 119.0,89.6 C122.0,82.7 120.5,78.6 120.5,78.6 C119.2,72.0 123.4,76.3 123.4,76.3 C127.3,80.9 125.5,87.3 125.5,87.3 C122.9,97.6 130.6,101.9 134.4,103.2" fill="currentColor" style="transform-origin: 130px 106px;" class="octo-arm"></path>
<path d="M115.0,115.0 C114.9,115.1 118.7,116.5 119.8,115.4 L133.7,101.6 C136.9,99.2 139.9,98.4 142.2,98.6 C133.8,88.0 127.5,74.4 143.8,58.0 C148.5,53.4 154.0,51.2 159.7,51.0 C160.3,49.4 163.2,43.6 171.4,40.1 C171.4,40.1 176.1,42.5 178.8,56.2 C183.1,58.6 187.2,61.8 190.9,65.4 C194.5,69.0 197.7,73.2 200.1,77.6 C213.8,80.2 216.3,84.9 216.3,84.9 C212.7,93.1 206.9,96.0 205.4,96.6 C205.1,102.4 203.0,107.8 198.3,112.5 C181.9,128.9 168.3,122.5 157.7,114.1 C157.9,116.9 156.7,120.9 152.7,124.9 L141.0,136.5 C139.8,137.7 141.6,141.9 141.8,141.8 Z" fill="currentColor" class="octo-body"></path>
</svg>
</a>
<header>
<h1>BCI-MCP Documentation</h1>
<p>Brain-Computer Interface with Model Context Protocol</p>
</header>
<div class="container">
<nav>
<h3>Contents</h3>
<ul>
<li><a href="#overview">Overview</a></li>
<li><a href="#installation">Installation</a></li>
<li><a href="#features">Features</a></li>
<li><a href="#api">API Reference</a></li>
<li><a href="#contributing">Contributing</a></li>
<li><a href="#changelog">Changelog</a></li>
</ul>
</nav>
<div class="content">
<section id="overview">
<h2>Overview</h2>
<p>The BCI-MCP system provides integration between Brain-Computer Interface (BCI) technology and large language models through the Model Context Protocol (MCP). This enables AI systems to receive and process brain activity data as additional context, creating more intuitive human-AI interaction.</p>
</section>
<section id="installation">
<h2>Installation</h2>
<h3>Prerequisites</h3>
<p>Before installing the BCI-MCP system, ensure you have the following:</p>
<ul>
<li>Python 3.8 or higher</li>
<li>Git</li>
<li>Docker and Docker Compose (for containerized deployment)</li>
<li>4GB RAM minimum (8GB recommended)</li>
</ul>
<h3>Method 1: Direct Installation</h3>
<pre><code>git clone https://github.com/enkhbold470/bci-mcp.git
cd bci-mcp
python -m venv venv
# On Windows
venv\Scripts\activate
# On macOS/Linux
source venv/bin/activate
pip install -r requirements.txt</code></pre>
<h3>Method 2: Docker Installation</h3>
<pre><code>git clone https://github.com/enkhbold470/bci-mcp.git
cd bci-mcp
docker-compose up -d</code></pre>
</section>
<section id="features">
<h2>Features</h2>
<h3>BCI Capabilities</h3>
<ul>
<li>Support for multiple BCI devices (OpenBCI, Emotiv, NeuroSky)</li>
<li>Real-time signal processing and visualization</li>
<li>Feature extraction for various EEG paradigms</li>
<li>Artifact removal and signal cleaning</li>
</ul>
<h3>MCP Integration</h3>
<ul>
<li>Conversion of neural signals to context data for LLMs</li>
<li>Real-time streaming of brain activity features</li>
<li>Cognitive state estimation and adaptation</li>
<li>Secure and private data handling</li>
</ul>
</section>
<section id="api">
<h2>API Reference</h2>
<h3>BCI Module</h3>
<p>The BCI module provides classes and functions for interfacing with brain-computer interface devices and processing neural signals.</p>
<pre><code>from bci_mcp.devices import OpenBciDevice
from bci_mcp.processing import FeatureExtractor
# Initialize BCI device
device = OpenBciDevice(port="/dev/ttyUSB0")
device.connect()
device.start_stream()
# Extract features from BCI data
extractor = FeatureExtractor()
bci_data = device.get_data(seconds=5)
features = extractor.process(bci_data)</code></pre>
<h3>MCP Module</h3>
<p>The MCP module facilitates integration between BCI data and large language models through the Model Context Protocol.</p>
<pre><code>from bci_mcp.mcp import McpClient
# Create MCP client and send query with BCI context
client = McpClient(api_key="your_api_key")
response = client.query(
prompt="How should I modify my meditation practice based on my current state?",
context={"bci_data": features}
)
print(response.text)</code></pre>
</section>
<section id="contributing">
<h2>Contributing</h2>
<p>We welcome contributions to the BCI-MCP project! Please follow these steps:</p>
<ol>
<li>Fork the repository</li>
<li>Create a feature branch</li>
<li>Make your changes</li>
<li>Run tests</li>
<li>Submit a pull request</li>
</ol>
<p>For more details, see the <a href="https://github.com/enkhbold470/bci-mcp/blob/main/CONTRIBUTING.md">contributing guidelines</a>.</p>
</section>
<section id="changelog">
<h2>Changelog</h2>
<h3>Unreleased</h3>
<ul>
<li>Initial documentation structure</li>
<li>GitHub Pages deployment workflow</li>
<li>Basic project structure and dependencies</li>
</ul>
<h3>v0.1.0 - 2023-03-23</h3>
<ul>
<li>Initial repository setup</li>
<li>Basic BCI device interface</li>
<li>Simple MCP client implementation</li>
<li>Project documentation</li>
<li>Docker configuration</li>
</ul>
</section>
</div>
</div>
<footer>
<p>© 2023-2024 BCI-MCP Project. Released under the MIT License.</p>
</footer>
</body>
</html>
