Physbound
About
PhysBound is a specialized "Physics Linter" for AI that deterministically validates RF and thermodynamic claims against hard physical limits, preventing hallucinations in engineering workflows.
Details
- Author
- JonesRobM
- Downloads
- 319
- Categories
- Productivity, Other
Jump to
- Validates RF link budgets via the Friis transmission equation
- Computes Shannon-Hartley channel capacity and flags impossible throughput claims
- Calculates thermal noise floor and cascaded noise figures
- Checks antenna gains against physical aperture limits
- Returns structured PhysicalViolationError with LaTeX explanations
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
PhysboundCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install with pip install physbound, then add Physbound to any MCP-compatible client (e.g., Claude Desktop, Cursor, Windsurf) using the JSON configuration: "command": "uv", "args": ["run", "--from", "physbound", "physbound"]. Your AI assistant can then call tools like rf_link_budget, shannon_hartley, and noise_floor.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"physbound": {
"physbound": {
"command": "uvx",
"args": [
"physbound"
]
}
}
}
}McpServers
{
"physbound": {
"command": "uvx",
"args": [
"physbound"
]
}
}PhysBound
Physical Layer Linter — An MCP server that validates RF and physics calculations against hard physical limits. Catches AI hallucinations in engineering workflows.
[
]()
---
What LLMs Get Wrong
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 bypytest tests/test_marketing.py -s
---
Quick Start
Install
``bash
pip install physbound
`
MCP Client Configuration
Add PhysBound to any MCP-compatible client. For example, in Claude Desktop (claude_desktop_config.json), Cursor, or Windsurf:
`json
{
"mcpServers": {
"physbound": {
"command": "uv",
"args": ["run", "--from", "physbound", "physbound"]
}
}
}
`
Your AI assistant now has access to physics-validated RF calculations.
---
Tools
rf_link_budget
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.
shannon_hartley
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.
noise_floor
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.
---
Physics Guarantees
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/Hz at 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.
---
Development
``bashSign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
