pyrestoolbox-mcpby Mark W. Burgoyne
The pyResToolbox author's own MCP server: a few meta-tools that describe and call any public library function.
pyResToolbox has two MCP servers. Its author, Mark Burgoyne, ships a small meta-tool server in the library's own repository that can describe and call any public function. A community server by Gabriel Serrão wraps 108 calculations as separate tools and bundles a skill with their exact parameters. Both run the GPL-licensed Python library locally on any OS, with no simulator or commercial licence needed.
The pyResToolbox author's own MCP server: a few meta-tools that describe and call any public library function.
Wraps the pyResToolbox library as 108 typed MCP tools for PVT, IPR, nodal analysis, decline curves and simulator tables.
A SKILL.md and parameter reference that teach the agent the exact arguments and method codes of the pyResToolbox MCP tools.
Listings are sorted by origin, then by recent activity. GitHub data is refreshed nightly. Nothing here is ranked.
An MCP server or skill can only do what pyResToolbox lets programs do. pyResToolbox exposes 2 automation interfaces:
The library's author publishes an MCP server himself, in the mcp folder of the pyResToolbox repository (server version 0.1.0, GPL-3.0-or-later). It wasn't yet on PyPI on 4 November 2026, so you install it from the repository. There is no hosted service or company behind pyResToolbox; it is an open-source project.
Checked 4 Nov 2026. Sources: pyResToolbox mcp/README.md
Taken from the listings' own documentation. Check each listing for exactly what it supports.
The listings here document setup for Claude Code and Claude Desktop. Install steps, copied from each project's own documentation, are on each listing's page. Most pyResToolbox integrations run on your own computer next to pyResToolbox, so you need pyResToolbox installed and licensed on the same machine unless the listing says otherwise.
Yes. Mark Burgoyne, who maintains pyResToolbox, publishes pyrestoolbox-mcp in the library's repository. It exposes a few meta-tools (list, describe, call) plus one-shot wrappers, rather than one tool per function.
The author's server tracks the current library (3.8.2 or later) and can call any public function. The community server pins pyResToolbox 3.0.4 but gives every calculation its own validated tool and comes with a skill listing exact argument names, which some clients handle more reliably.
No. They compute correlations, tables and forecasts. To run a deck, pair them with a simulator server such as opm-mcp for OPM Flow.
No. pyResToolbox and both servers are GPL-licensed open source and need only Python.
AI-generated models, drawings and results must be checked by a qualified engineer before use.
Sources (checked 4 Nov 2026): mwburgoyne/pyResToolbox README · pyrestoolbox on PyPI · pyResToolbox mcp/README.md · gabrielserrao/pyrestoolbox-mcp README · pyResToolbox product page
pyResToolbox is developed by its own project (Open source). Tresca is independent and not affiliated with or endorsed by the pyResToolbox project.