Physical Layer Linter — An MCP server that validates RF and physics calculations against hard physical limits. Catches AI hallucinations in engineering workflows.
LLMs routinely hallucinate physics. PhysBound catches it:
| # | Category | LLM Hallucination | PhysBound Truth | Verdict |
|---|---|---|---|---|
| 1 | Shannon-Hartley | "20 MHz 802.11n at 15 dB SNR achieves 500 Mbps" | Shannon limit: 100.6 Mbps | CAUGHT |
| 2 | Shannon-Hartley | "100 MHz 5G channel at 20 dB SNR delivers 2 Gbps" | Shannon limit: 665.8 Mbps | CAUGHT |
| 3 | Antenna Aperture | "30 cm dish at 1 GHz provides 45 dBi gain" | Aperture limit: 7.4 dBi | CAUGHT |
| 4 | Thermal Noise | "Noise floor of -180 dBm/Hz at room temperature" | Actual: -174.0 dBm/Hz at 290K | CAUGHT |
| 5 | Link Budget | "Wi-Fi at 2.4 GHz reaches 10 km at -40 dBm" | Actual RX power: -94.1 dBm | CAUGHT |
| 6 | Link Budget | "1W to GEO with 0 dBi antennas at -80 dBm" | Actual RX power: -175.1 dBm | CAUGHT |
Generated automatically by pytest tests/test_marketing.py -s
pip install physboundAdd PhysBound to any MCP-compatible client. For example, in Claude Desktop (claude_desktop_config.json), Cursor, or Windsurf:
{
"mcpServers": {
"physbound": {
"command": "uv",
"args": ["run", "--from", "physbound", "physbound"]
}
}
}Your AI assistant now has access to physics-validated RF calculations.
Computes a full RF link budget using the Friis transmission equation. Validates antenna gains against aperture limits.
Example: "What's the received power for a 2.4 GHz link at 100 m with 20 dBm TX, 10 dBi TX gain, 3 dBi RX gain?"
Returns: FSPL, received power, wavelength, and optional aperture limit checks. Rejects antenna gains that violate G_max = eta * (pi * D / lambda)^2.
Computes Shannon-Hartley channel capacity C = B * log2(1 + SNR) and validates throughput claims.
Example: "Can a 20 MHz channel with 15 dB SNR support 500 Mbps?"
Returns: Theoretical capacity, spectral efficiency, and whether the claim is physically possible. Flags violations with the exact percentage by which the claim exceeds the Shannon limit.
Computes thermal noise power N = k_B * T * B, cascades noise figures through multi-stage receivers using the Friis noise formula, and calculates receiver sensitivity.
Example: "What's the noise floor for a 1 MHz receiver at 290K with a two-stage LNA chain?"
Returns: Thermal noise in dBm and watts, cascaded noise figure, system noise temperature, and receiver sensitivity.
Every calculation is validated against hard physical limits:
- Speed of light:
c = 299,792,458 m/s— no exceptions - Thermal noise floor:
N = -174 dBm/Hzat 290K — the IEEE standard reference - Shannon limit:
C = B * log2(1 + SNR)— no throughput claim exceeds this - Aperture limit:
G_max = eta * (pi * D / lambda)^2— antenna gain is bounded by physics
Violations return structured PhysicalViolationError responses with LaTeX explanations, not silent failures.
# Clone and install
git clone https://github.com/JonesRobM/physbound.git
cd physbound
uv sync --all-extras
# Run tests
uv run pytest tests/ -v
# Print hallucination delta table
uv run pytest tests/test_marketing.py -s
# Start MCP server locally
uv run physboundAI coding assistants are increasingly used in RF engineering, telecommunications, and signal processing workflows. But LLMs have no intrinsic understanding of physics — they generate plausible-sounding numbers that can violate fundamental laws like Shannon-Hartley, thermodynamic noise limits, and antenna aperture bounds.
PhysBound acts as a physics guardrail for any MCP-compatible AI assistant. Every calculation is checked against CODATA physical constants via SciPy, with dimensional analysis enforced through Pint. Violations return structured errors with LaTeX explanations — not silent failures.
- RF system design review — validate link budgets, receiver sensitivity, and noise cascades
- Telecom proposal vetting — catch impossible throughput claims before they reach a customer
- Educational tools — teach Shannon-Hartley, Friis transmission, and thermal noise with verified calculations
- CI/CD for physics — integrate as a validation step in engineering pipelines
If PhysBound is useful in your work, consider buying me a coffee.
MIT License. See LICENSE.
- Model Context Protocol — the open standard for AI tool integration
- MCP Server Registry — official directory of MCP servers
- FastMCP — Python framework for building MCP servers
