広告掲載
MCP.so
ログイン
P

Petromcp MCP Server

@ameyxd

リポジトリ

基本情報

カテゴリ

開発者ツール

トランスポート

stdio

作者

ameyxd

投稿者

Amey Ambade

Petromcp MCP Server について

petromcp is a small MCP server that lets Claude (or Cursor, or Codex CLI,

Petromcp MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "petromcp": {
      "command": "uv",
      "args": [
        "run",
        "--no-sync",
        "--project",
        "/absolute/path/to/petromcp",
        "petromcp",
        "serve"
      ]
    }
  }
}

Petromcp MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Petromcp?

Petromcp is a local-first MCP server that lets Claude read LAS well log files directly. It wraps open-source parsers like lasio and exposes them as MCP tools, enabling natural conversation with petroleum data without copy-pasting curve values.

How to use Petromcp?

Requires Python 3.10+, uv, and Claude Desktop. After cloning the repo and running make setup and make install-claude, configure an allowlist of directories Petromcp can read using the CLI subcommands petromcp config init and petromcp config add-path. Restart Claude Desktop, then ask questions like "What's wrong with this well log?" in a new conversation.

Key features of Petromcp

  • MCP tools for reading, summarizing, and comparing LAS files
  • Unit conversion between common petroleum units (ft↔m, psi↔kPa, etc.)
  • Built-in qc_a_well_log prompt for standard QC workflow
  • Strict file allowlist – cannot read outside allowed directories
  • Zero telemetry, no automatic updates, runs entirely on your machine
  • Ships with synthetic sample data for testing without real files

Use cases of Petromcp

  • Diagnose well log quality issues by asking Claude to read and analyze a LAS file
  • Compare two wells for common curves, depth overlap, and unit consistency
  • Convert units (e.g., psi to kPa) during data interpretation
  • Walk through a standardized QC pass using the built-in prompt
  • Explore LAS files without installing specialized petroleum software

よくある質問

1

How does Petromcp protect my data?

Petromcp runs locally and refuses to read any file outside an explicit allowlist you configure. It contains no telemetry, no phone-home, and no automatic updates.

2

What dependencies does Petromcp require?

It requires Python 3.10+, `uv` (the Astral package manager), and the Claude Desktop application.

3

Where does Petromcp store my data?

All data remains on your machine. Petromcp only reads files from directories you explicitly add to its allowlist via `petromcp config add-path`.

4

What file formats does Petromcp support?

Currently, Petromcp supports LAS well log files (v0.2). Support for DLIS, SEG-Y, and pump card data is planned for future releases.

5

How do I invoke Petromcp tools?

Once installed and configured, open a new conversation in Claude Desktop and ask plain-language questions about your well logs. Claude automatically selects the appropriate MCP tool (e.g., `read_las_file`, `summarize_las_curves`, `compare_well_logs`) and reads the file through Petromcp.

コメント

「開発者ツール」の他のコンテンツ

Mcp-Warden

ermoluk

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

4

Perfex CRM

themesic

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

1

Foremerge

naw103

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.

50

GAIP Agents

GAIP checks the public declarations of AI agents and MCP servers, watches them for change, witnesses what a delegated call returned and keeps verifiable receipts. Free, read-only, no account or API key. Every result sta

FARPY

mangomunchr

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

1
広告掲載