Skip to main content
Glama
Corrosion Engineering MCP Server

Corrosion Engineering MCP Server

by puran-water

corrosion-engineering-mcp

Corrosion chemistry and explicit screening calculations, with unsupported predictions identified in results.

Experimental release series; v0.1.0 is the initial pinned release and main follows current development. These tools return calculations and structured evidence; the calling LLM supplies explanations and reporting. Engineering review remains necessary.

Use it in an engineering workflow

A corrosion-screening question. Supply material, water chemistry, temperature and relevant gas or flow conditions. Inspect the selected method, validity limits and unsupported-prediction flags.

A screening result is not a remaining-life prediction or a material warranty.

This is a public calculation component of Puran Water's engineering toolchain. The working system connects these tools to sizing-to-balance, proposal and BEP procedures and retained Studio review publications. Those internal workflows and project records are separate from this standalone package.

Have a project that needs engineering interpretation or an independent review? Work with Puran Water. To report a software defect, open a repository issue with a minimal synthetic or redacted input, package revision, expected result and actual result.

Related MCP server: CalcsLive MCP Server

Quick start

Install uv and run with Python 3.12:

uvx --python 3.12 --with 'puran-mcp-support @ git+https://github.com/puran-water/fluids-mcp.git@v0.1.0#subdirectory=support/puran-mcp-support' --from 'git+https://github.com/puran-water/corrosion-engineering-mcp.git@v0.1.0' corrosion-engineering-mcp

The server uses local MCP stdio. It requires no Puran account or private package. uv shares its dependency cache between isolated tool environments. PyPI publishing has not been configured; the pinned public Git release is the installation path.

MCP client configuration

Use this configuration in a client supporting local stdio MCP servers:

{
  "mcpServers": {
    "corrosion-engineering-mcp": {
      "command": "uvx",
      "args": [
        "--python",
        "3.12",
        "--with",
        "puran-mcp-support @ git+https://github.com/puran-water/fluids-mcp.git@v0.1.0#subdirectory=support/puran-mcp-support",
        "--from",
        "git+https://github.com/puran-water/corrosion-engineering-mcp.git@v0.1.0",
        "corrosion-engineering-mcp"
      ]
    }
  }
}

Run the server in a user-owned working directory. Local input and result files belong to that user. Hosted HTTP authentication and managed employee access are outside this release.

Known issues

  • Restore data-backed tools using cleared redistributable data. Material, handbook and thermodynamic tables without fully cleared redistribution provenance are omitted. The public material catalog is empty. Tools requiring these tables cannot provide material-specific results; this release supplies no invented replacement values.

  • Validate suppressed and experimental corrosion models. Several historical rate and suitability outputs are withdrawn or suppressed. Broader regression failures, untested correlations and incomplete numerical qualification remain; do not interpret a screening result as a validated service-life or material-selection guarantee.

  • Complete native runtime and competitor qualification. Native PHREEQC platforms and alternative public implementations need further qualification.

  • Resolve remaining installed-artifact qualification findings. The v0.1.0 source/wheel qualification completed MCP startup but retained these failed checks:

See known issue details, test results, content scan, and licensing inventory. These limitations are disclosed for early feedback.

License and attribution

See LICENSE, NOTICE and THIRD-PARTY-NOTICES for the wrapper and retained upstream material. External dependencies retain their own licenses.

Built by Puran Water.

Historical source-suite snapshot: 1551 passed. These counts predate the cleaned standalone export; they are not its qualification result. Later repairs covered selected subsets only. See historical quality scope.

Following current development

The main branch receives approved development fixes through a one-way source mirror. Publication still checks secrets, private content, redistribution rights and package boundaries. Version tags such as v0.1.0 remain immutable. Installed copies do not update automatically. To upgrade the server and its public support package together from the current branches in your existing environment:

uv pip install --upgrade --reinstall \
  "puran-mcp-support @ git+https://github.com/puran-water/fluids-mcp.git@main#subdirectory=support/puran-mcp-support" \
  "corrosion-engineering-mcp @ git+https://github.com/puran-water/corrosion-engineering-mcp.git@main"

Pin both Git commits when repeatability is more important than following changes. The mirror records the source commit in .puran-mirror.json.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Enables AI assistants to perform petroleum engineering calculations including PVT analysis, well performance modeling, and reservoir simulation support using industry-standard correlations and field units.
      45
      47
      GPL 3.0
    • A
      license
      A
      quality
      D
      maintenance
      Enables AI agents to perform unit-aware engineering calculations with automatic unit conversion, dependency resolution, and access to 500+ units across 75+ categories through the CalcsLive calculation engine.
      3
      15 npm
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to look up thermophysical properties — density, viscosity, thermal conductivity, speed of sound, enthalpy, entropy, Cv/Cp and phase — for roughly 76 reference fluids at a given temperature and pressure, or along the liquid/vapor saturation curve, plus fluid listing and name resolution. Each returned value is accompanied by its unit, and out-of-range conditions surface as clear errors.
      81 npm
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables AI agents to run deterministic data-center engineering calculations and commissioning audits, including liquid-cooling hydraulics, pipe friction and flow checks, corrosion severity classification, protocol search, and defect-code lookup.
      6
      2
      MIT