vle-mcp

An educational Model Context Protocol server for the vle and stages-thermo scientific libraries.

The first tool calculates the boiling temperature of water at an absolute pressure using vle-steam's IAPWS-IF97 implementation. The chatbot interprets and explains the request; tested scientific software supplies the number.

Status

M0 (repository foundation) and M1 (minimum stdio server) are implemented and locally verified. The suite contains 19 tests, including an in-memory MCP round trip, a real stdio subprocess handshake, and the vle-steam standard atmosphere acceptance case. See PLAN.md for architecture and TODO.md for verified status.

Related MCP server: Agentic-AI-Planning-And-Reasoning-MCP

Why MCP?

MCP gives AI clients a standard way to discover and call typed tools. It separates natural-language reasoning from authoritative programs and data:

• the model determines intent;

• the MCP client controls connections and tool use;

• this server validates a typed request;

• vle-steam performs the scientific calculation.

See docs/mcp-primer.md for the protocol path and docs/architecture.md for the component architecture. PLAN.md records the Python and API-granularity decisions.

Development setup

Python 3.11 or newer is required.

python3 -m venv .venv
.venv/bin/python -m pip install --upgrade pip
.venv/bin/python -m pip install -e '.[dev]'
.venv/bin/vle-mcp

The last command starts a stdio MCP server and waits for a client. It is not an interactive shell; use an MCP client or the protocol tests.

For development against a local vle checkout, install its Python package into the virtual environment according to that repository's build instructions. Do not commit a machine-specific path.

Tool

water_saturation_temperature

Inputs:

• pressure: positive finite number;

• pressure_unit: Pa, kPa, MPa, bar, or atm;

• all pressure is absolute.

Example arguments:

{"pressure": 101.325, "pressure_unit": "kPa"}

The result is approximately 373.1243 K or 99.9743 °C. It includes the normalized pressure and IAPWS-IF97 provenance.

Verification

.venv/bin/python scripts/check_public_data.py
.venv/bin/ruff check .
.venv/bin/ruff format --check .
.venv/bin/pytest

Security

M1 is local, read-only, deterministic, and uses stdio. No credentials are required. Read SECURITY.md and docs/security-model.md before adding a tool or remote transport.

Authorship

Miguel Jackson owns and directs the project. M0 and M1 were implemented collaboratively by OpenAI Codex using the GPT-5.6 Sol model, following Miguel's instructions and approved plan. See AUTHORS.md for the precise human/AI attribution and limitations.

License

MIT