# xfloukiex-lab/road-poneglyph [Health: Active]

**Category:** 📋 Product Management  
**Repository:** https://github.com/xfloukiex-lab/road-poneglyph  
**GitHub Stars:** 2  
**Views:** 3  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/xfloukiex-lab-road-poneglyph

## Description
Reviews a plan for what's missing — unstated assumptions, omitted technical risks, and execution blind spots (a structured pre-mortem). pip install road-poneglyph-mcp

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `uvx` (confidence: high):

```json
"mcpServers": {
  "road-poneglyph": {
    "command": "uvx",
    "args": ["road-poneglyph-mcp"]
  }
}
```

## Documentation

## What xfloukiex-lab/road-poneglyph MCP server does

The xfloukiex-lab/road-poneglyph MCP server examines a written plan for important details that are absent rather than simply responding to the plan's stated content. It is intended for structured pre-mortems: reviews that surface what could undermine execution before work begins.

The returned analysis is divided into three areas:

- **The Void Century:** assumptions the plan relies on without establishing them.
- **Hidden Reef:** technical and architectural risks that the plan leaves out.
- **The Treacherous Seas:** operational and execution blind spots that could affect delivery.

This makes the server suitable for reviewing software plans and other project plans where missing assumptions or unexamined risks could create problems during implementation.

## How it works

The xfloukiex-lab/road-poneglyph MCP server exposes one MCP tool: `read_poneglyph`. It accepts a required `current_plan` string and an optional `project_type` string, which defaults to `Software`.

Rather than invoking a language model itself, the server generates a carefully structured analysis prompt. The MCP-compatible client passes that prompt to the model the user is already interacting with. As a result, the server requires no API key, makes no network calls, and does not send the plan to an external service itself.

The tool reference is:

```text
read_poneglyph(current_plan: str, project_type: str = "Software")
```

The client and model therefore remain responsible for executing the review prompt and presenting the resulting critique.

## Setup and configuration

The package requires Python 3.10 or newer. Install it from PyPI with:

```bash
pip install road-poneglyph-mcp
```

Installation provides the `road-poneglyph` command. A Claude Desktop configuration can register it as a local stdio MCP server:

```json
{
  "mcpServers": {
    "road-poneglyph": { "command": "road-poneglyph" }
  }
}
```

The README also shows registration through the Claude CLI:

```bash
claude mcp add road-poneglyph -- road-poneglyph
```

Restart the MCP client after registration so the tool becomes available. The README specifically identifies Claude Desktop, Claude Code, and Cursor as compatible clients; this listing includes the supported client names available in its client taxonomy.

## Tools and capabilities

The xfloukiex-lab/road-poneglyph MCP server provides one focused capability rather than a collection of project-management operations:

- Submit a plan for a structured pre-mortem.
- Set the project type or use the `Software` default.
- Identify unstated assumptions.
- Surface omitted technical and architectural risks.
- Highlight operational and execution gaps.

It does not provide a model, a hosted analysis endpoint, or a separate credential system. The analysis depends on the model connected through the MCP client.

_Full upstream README: https://allmcps.com/mcp/xfloukiex-lab-road-poneglyph/readme_