petro-mcp · Free & Open Source · Alpha v0.8.1

Put Petroleum Engineering Inside Your AI Assistant.

70 tested tools for LAS parsing, decline curves, PVT, drilling, and economics. Your team asks questions in plain English; petro-mcp runs deterministic code underneath — not AI-generated math.

MIT licensed Files stay on disk — you choose what reaches the LLM Python 3.10+

The Gap petro-mcp Fills

Large language models are powerful reasoners but have no native way to open an LAS file, fit an Arps decline, or compute a kill mud weight. petro-mcp closes that gap.

Before petro-mcp

  • “Write me a Python script to parse this LAS file”
  • “Now add decline curve fitting with scipy.”
  • “Now handle the missing-data edge case.”
  • “Now fix the bug you introduced.”

With petro-mcp

  • “Read the LAS file at /data/wolfcamp.las and summarize the curves.”
  • “Fit a hyperbolic decline on Well 47’s last 18 months.”
  • “Calculate EUR assuming a 5 bbl/day economic limit.”
  • Tested, deterministic tools run — not AI-generated code.

Install & Configure

Install via pip, Glama, or source. About five minutes end-to-end for a first-time setup.

Recommended

pip install petro-mcp

Then add petro-mcp to your Claude Desktop, Cursor, or VS Code MCP config. Full setup instructions are in the README.

Also listed on mcp.so, the community MCP directory.

What’s Inside

70 tools across 12 petroleum engineering domains. Load only the groups you need to keep context overhead low.

Well Logs

LAS 2.0 parsing, header extraction, curve inspection, depth-range filtering. Built on lasio.

Production Data

Query production CSVs by well and date range. Detect shut-ins, rate jumps, water breakthrough, GOR blowouts.

Decline Curve Analysis

Arps (exp, hyp, harmonic), modified hyperbolic, Duong, PLE, SEPD, THM models. EUR calculation with economic limits.

PVT Correlations

Bubble point, solution GOR, oil FVF, viscosity, gas compressibility — standard industry correlations.

Petrophysics

Shale volume, effective porosity, water saturation (Archie, Simandoux), net pay cutoffs from log curves.

Drilling

Hydraulics, ECD, kill mud weight, kick tolerance, pressure loss across the circulation system.

Reservoir Engineering

Material balance, radial flow, skin, pseudo-steady-state productivity index calculations.

Production Engineering

IPR and TPR curves, nodal analysis, tubing sizing, artificial lift screening.

Well Economics

NPV, IRR, payout, break-even oil price. Configurable price decks, severance tax, and working interest.

Trajectory

Minimum-curvature survey math, dogleg severity, 3D wellpath generation (optional, via welleng).

Calculations & Units

Field-standard unit conversions and quick-look formulas that engineers reach for every day.

Full Tool List

See all 70 tools with signatures and examples.

Browse on GitHub →

Ask in Plain English

These are the prompts engineers actually use. Your AI assistant calls the right petro-mcp tools under the hood.

“Read the LAS file at /data/wells/wolfcamp.las and summarize the curves.”

“Load production data from /data/prod.csv and fit a hyperbolic decline for Wolfcamp A-1H.”

“Calculate EUR with qi=800, Di=0.06, b=1.1 and a 5 bbl/day economic limit.”

“Run a nodal analysis: 3,500 psi reservoir, PI = 4.2, 2.875-inch tubing, 150 psi wellhead.”

“What’s the kill mud weight if SIDP is 500 psi, current MW is 10.5 ppg, TVD 12,000 ft?”

“Calculate PVT properties for 35° API oil at 200 °F and 3,000 psi.”

Works With Your Existing Stack

MCP is an open standard. petro-mcp works with any compliant client.

Claude Desktop

Drop into claude_desktop_config.json.

Cursor

Add to .cursor/mcp.json.

VS Code

MCP extension, same JSON config.

Custom Clients

Any MCP-compatible runtime — the protocol is open.

Who It’s For

Petroleum Engineers

Skip the scripting loop. Ask your AI assistant for the same LAS parse, decline fit, or PVT calc you already run — and get an answer backed by tested code, not hallucinated math.

Data & Platform Teams

A drop-in MCP layer over the petroleum workflows your engineers already trust. Pair with your own tools or extend the codebase — MIT license, no lock-in.

Researchers & Students

Teach, prototype, and publish with a shared, inspectable foundation. Every calculation is transparent source code — not a black-box API.

Who Built This

Groundwork Analytics

petro-mcp is built and maintained by Groundwork Analytics, an AI and data science firm working with upstream operators across the Permian, Eagle Ford, and other major U.S. basins. Led by Dr. Mehrdad Shirangi, Stanford PhD in energy systems optimization.

Your Files Stay on Disk. You Control What Reaches the LLM.

petro-mcp runs as a local process — your LAS files, production CSVs, and well data never leave your machine. What crosses the network is the prompt you type and the tool outputs your AI assistant sees, which go to your chosen LLM provider (Claude, OpenAI, etc.). For full data isolation, pair petro-mcp with a self-hosted model (Ollama, vLLM, or your own endpoint) — the protocol is provider-agnostic.

Try It on a Real Well

About five minutes to install and configure. Point it at an LAS or production CSV and ask a question.

The open-source foundation

petro-mcp is free, MIT-licensed, and stays that way.

Need to scale this across your fleet — private-cloud hosting, ingestion into your wells database, governance for shared teams, or custom tools on top? That’s Groundwork’s paid engagement, not petro-mcp itself.

Book a Discovery Call →