Corrosion Engineering

Provides physics-based corrosion data sources and actions via an MCP server (dual-tier pitting, mechanistic models).

python

0

GitHub Stars

python

Language

6 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "puran-water-corrosion-engineering-mcp": {
      "command": "python",
      "args": [
        "/path/to/corrosion-engineering-mcp/server.py"
      ]
    }
  }
}

Corrosion Engineering MCP Server is a FastMCP-based toolkit that gives AI agents access to physics-based corrosion calculations, ranging from rapid handbook lookups to mechanistic electrochemical models with dual-tier pitting assessment. It is designed to help you quickly screen materials for compatibility, predict corrosion behavior, and assess localized corrosion risks under realistic environmental conditions.

How to use

You run the server locally and connect to it from your MCP client. The server exposes a set of tools under a consistent prefix corrosion_ that you can call to obtain central estimates, uncertainty bounds, and provenance for corrosion predictions. For dual-tier pitting, you can request Tier 1 (empirical PREN/CPT screening) and Tier 2 (mechanistic E_pit vs E_mix) calculations, with automatic tier-disagreement warnings when they diverge.

How to install

Prerequisites: you need Python and a supported shell. Ensure Python and pip are available on your system.

# Clone the MCP server repository
git clone git@github.com:puran-water/corrosion-engineering-mcp.git
cd corrosion-engineering-mcp

# Create and activate a virtual environment
python -m venv venv312
# Linux/macOS
source venv312/bin/activate
# Windows
venv312\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Run tests (optional but recommended during setup)
pytest tests/test_phase3_pitting_integration.py -v

Additional content

Configuration for the MCP client is shown below. It defines a local (stdio) MCP server that runs a Python script implementing the server logic.

{
  "mcpServers": {
    "corrosion-engineering": {
      "command": "python",
      "args": ["/path/to/corrosion-engineering-mcp/server.py"]
    }
  }
}

Available tools

corrosion_screen_materials

Tier 0 handbook lookup: material-environment compatibility via semantic search.

corrosion_query_typical_rates

Tier 0 handbook lookup: empirical corrosion rate queries.

corrosion_identify_mechanism

Tier 0 handbook lookup: mechanism identification and mitigation guidance.

corrosion_langelier_index

Tier 1 chemistry tool: calculates the Langelier saturation index for water scaling tendency.

corrosion_predict_scaling

Tier 1 chemistry tool: predicts mineral scale formation.

corrosion_predict_co2_h2s

Tier 2 mechanistic tool: CO2/H2S corrosion predictions.

corrosion_predict_aerated_chloride

Tier 2 mechanistic tool: predictions under aerated chlorine conditions and DO limitations.

corrosion_assess_galvanic

Tier 2 mechanistic tool: mixed-potential galvanic corrosion assessment.

corrosion_generate_pourbaix

Tier 2 mechanistic tool: Pourbaix diagrams (E-pH stability) lookups.

corrosion_get_material_properties

Tier 2 mechanistic tool: alloy database access (18+ materials).

corrosion_estimate_service_life

Tier 2 mechanistic tool: remaining service life estimates.

corrosion_assess_localized

Tier 3 localized corrosion: dual-tier pitting and crevice assessment.

corrosion_calculate_pren

Tier 3 localized corrosion: PREN calculation.

get_server_info

Returns server information and status.