WaterTAP Engine MCP
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
watertap-engine-mcp
Build and solve steady-state process flowsheets using WaterTAP, IDAES and Pyomo, with structured solver diagnostics.
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 steady-state process question. Define a supported flowsheet, feed basis, equipment specification and operating conditions. Inspect solver diagnostics, constraints and stream results.
A successful solve is specific to its model and assumptions; unavailable solver capabilities and infeasibility must be resolved explicitly.
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: AspenPlus 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/watertap-engine-mcp.git@v0.1.0' watertap-engine-mcpThe 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": {
"watertap-engine-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/watertap-engine-mcp.git@v0.1.0",
"watertap-engine-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
Complete solver and flowsheet regression qualification. Broader source tests retained failures, errors, skips and timeouts. Solver binaries and model initialization remain environment-dependent; representative smoke cases do not qualify all flowsheets.
Qualify generic replacements for excluded application workflows. Private site presets, vendor-fitted application workflows, product-bound membrane catalogs and database publication are excluded. Use general unit APIs with explicit inputs; no proprietary calibration parameters are bundled.
Complete resource-bound and comparative benchmarks. Full graph/job resource coverage, cross-platform solvers and a common benchmark against competing wrappers remain open.
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: 1926 passed, 53 failed, 6 skipped, 2 error. These counts predate the cleaned standalone export; they are not its qualification result. Later repairs covered selected subsets only. See historical quality scope.
Bundled feedstock input presets are excluded. Supply a complete influent basis; classification names alone do not provide a design input dataset.
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[simulation] @ git+https://github.com/puran-water/fluids-mcp.git@main#subdirectory=support/puran-mcp-support" \
"watertap-engine-mcp @ git+https://github.com/puran-water/watertap-engine-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…
This server cannot be deployed
Maintenance
Related MCP Connectors
Build and run AI workflows, agents, data tables and 1000+ API integrations from any MCP client.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
OCR, transcription, file extraction, and image generation for AI agents via MCP.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables natural language control of anaerobic digestion modeling using the internationally recognized ADM1 standard. Supports wastewater treatment simulation for process design and optimization with AI-powered feedstock analysis, multi-reactor configurations, and professional report generation.2MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with Aspen Plus process simulations through a standardized MCP interface, supporting simulation control, data access, and flowsheet manipulation.37MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to simulate wastewater treatment processes using natural language, with dual MCP and CLI adapters for flexible integration.MIT
- AlicenseNot gradedqualityCmaintenanceEnables building, running, and optimizing cheminformatics pipelines via composable blocks, with an MCP agent interface for natural language interaction.2MIT