@elf004-star
基本信息
这是一个基于 MCP (Model Context Protocol) 协议的井身示意图生成工具，可以根据井数据自动生成井身结构图。由西南石油大学钻井所，何世明——汤明实验室团体提供技术支持。
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"awesome_well_mcp": {
"command": "uvx",
"args": [
"awesome_well_mcp"
]
}
}
}生成井身结构图 Args: well_data: 井数据JSON对象（必需）。 其中`legendConfig` 配置项用于自定义井眼轨迹示意图的图例和样式。可以通过 `casingLegend`、`holeLegend`、`kickoffLegend` 和 `targetPointsLegend` 这几个选项，分别控制是否在绘图时显示套管、井筒、造斜点和靶点的说明。此外，`fill` 选项控制是否对套管与井筒之间的环空进行颜色填充，以直观地表示固井水泥；`simpleinfo` 选项控制是否采用简化的方式打印（输出为PNG图片）井身结构信息。 **配置示例：** ```json "legendConfig": { "casingLegend": false, "holeLegend": false, "kickoffLegend": true, "targetPointsLegend": true, "fill": true, "simpleinfo": false } ``` 上述配置将会在井身结构旁中显示造斜点和靶点的说明（图例说明），但隐藏套管和井筒的说明（备注说明），同时会对井筒与套管间的环空进行填充，打印出详细形式的井身结构信息（PNG）。 JSON对象中`pilotHoleGuideLine` 配置项用于导眼井辅助线、侧钻点的显示设置。可以通过 `topDepth_m` 和 `bottomDepth_m` 分别设置辅助线的顶深和底深（单位：米），使用 `diameter_mm` 设置其尺寸（单位：毫米），（前三项用户没有具体要求不进行设置，服务端会自动配置）。`display` 选项控制该辅助线是否显示，`highlight` 选项决定其是否以更明显的样式（黑色虚线）突出显示。最后，`side_tracking` 选项用于将关联的图例样式从“造斜点”切换为“侧钻点”。 **配置示例：** ```json "pilotHoleGuideLine": { "display": true, "highlight": true, "side_tracking": true } ``` 上述配置将显示一条从 造斜点 到 井底、尺寸为默认毫米 的导眼井辅助线，并以高亮的黑色虚线样式呈现，同时其关联图例将显示为侧钻点样式。注意要显示侧钻点，必须先将 `legendConfig` 中的 `kickoffLegend` 设置为true（显示）。 Returns: 包含生成结果和图片数据的字典，包含井身结构图片（PNG）文件路径、井身结构信息图片（PNG）文件路径的和详细生成过程信息等
awesome_well_mcp is a borehole structure diagram generation tool built on the Model Context Protocol (MCP). It automatically generates borehole structure diagrams and information charts from well data, and is technically supported by the He Shiming and Tang Ming research group at the Drilling Research Institute of Southwest Petroleum University.
You can install via PyPI using uvx awesome_well_mcp, or by cloning the source repository and running uv run main.py. Configure an MCP client (e.g., Cherry Studio) with a stdio server pointing to the installed command. The tool exposes one MCP tool named generate_well_structure which accepts a well_data dictionary as its only parameter.
It supports four basic types: straight well, deviated well, horizontal well, and vertical‑to‑horizontal well. Side‑tracking (branch) wells can be represented by enabling the `pilotHoleGuideLine` with `"side_tracking": true`.
The recommended method is via PyPI using `uvx awesome_well_mcp`. Alternatively, you can clone the source repository and run `uv run main.py`. Both methods require Python 3.8 or later and the uv package manager.
It generates a PNG borehole structure diagram (`well_structure_plot.png`), a PNG information chart (`well_info.png`), a Markdown report (`well_structure_report.md`), and several CSV files (e.g., `stratigraphy.csv`, `casing_sections.csv`, `hole_sections.csv`, `drilling_fluid_pressure.csv`, `deviationData.csv`, `location.csv`) along with their raw data versions. All files are archived in a timestamp folder.
Include a `pilotHoleGuideLine` object in your `wellboreStructure` data with fields `topDepth_m`, `bottomDepth_m`, `diameter_mm`, `display`, `highlight`, and `side_tracking: true`. This is available for `horizontal well` or `deviated well` types.
Stratigraphy must be ordered from shallow to deep with consecutive depths. Hole sections and casing sections must also follow depth order; casing outer diameter typically decreases downwards. The last hole section’s bottom depth must equal `totalDepth_m`. Pressure segments must have contiguous depth intervals and a pressure window minimum greater than pore pressure.
Email security and AI discoverability scores for any domain, with the exact DNS record or tag to fix. Five read-only tools, no account or key needed.
Layro connects your AI coding tool (Cursor, Claude Code, VS Code, Windsurf, Codex, Gemini CLI) to 112 production React, TypeScript and Tailwind CSS components. Your agent can search the library, read each component's pro
Official Porkbun MCP server, maintained by Porkbun. Check domain availability and pricing, register, renew and transfer domains, and manage DNS records, nameservers, URL forwarding, glue records, DNSSEC and domain contac
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.
Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.
评论