Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@io.github.xfloukiex-lab/road-poneglyph Review my project plan for missing assumptions and risks."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server that reviews a plan for what's missing โ the assumptions, risks, and gaps you never wrote down.
A Model Context Protocol (MCP) server โ one focused tool you plug into an MCP-compatible client (Claude Desktop, Claude Code, Cursor, and others).
Language models are good at responding to what's in front of them and poor at noticing what isn't there. Ask one to critique a plan and it tends to react to the words on the page rather than the unstated assumptions behind them.
Road Poneglyph runs a structured pre-mortem over a plan and reports only the negative space โ what was assumed without proof, what was technically glossed over, and what was skipped on the way to shipping.
Related MCP server: sequential-thinking
Point your assistant at a plan and ask it to read the poneglyph. The tool returns a focused analysis in three sections:
The Void Century โ unstated assumptions the plan depends on
Hidden Reef โ omitted technical and architectural risks
The Treacherous Seas โ operational and execution blind spots
Tool reference: read_poneglyph(current_plan: str, project_type: str = "Software")
No API key, no cost, nothing leaves your machine. The server doesn't call a language model itself โ it returns a carefully engineered analysis prompt that the model you're already talking to executes. Zero credentials, zero network calls.
Requires Python 3.10 or newer.
pip install road-poneglyph-mcpThis installs the road-poneglyph command.
Then register it with your MCP client โ either run claude mcp add road-poneglyph -- road-poneglyph,
or add this to the client's config (e.g. claude_desktop_config.json):
{
"mcpServers": {
"road-poneglyph": { "command": "road-poneglyph" }
}
}Restart the client and the tool is available.
Road Poneglyph is part of a four-tool set. Each tool stands alone, but installing all of them unlocks a final surprise via Laugh Tale.
Package | ||
๐ฟ | Road Poneglyph ยท โ this repo | |
โ๏ธ | Conqueror's Haki | |
โณ | Toki Toki no Mi | |
๐ดโโ ๏ธ | Laugh Tale |
git clone https://github.com/xfloukiex-lab/road-poneglyph
cd road-poneglyph
python -m venv .venv && . .venv/Scripts/activate # macOS/Linux: source .venv/bin/activate
pip install -e ".[dev]"
python tests/test_road_poneglyph.pyReleased under the Apache-2.0 license. The icon is original artwork
(see icon.svg), generated locally; the repository ships no third-party assets.
This is a fan-inspired project. It is not affiliated with, sponsored by, or endorsed by the creators or rights holders of One Piece (Eiichiro Oda / Shueisha / Toei Animation). "One Piece" and related names are used only as thematic flavour and remain the property of their respective owners.
Reveal the 'Void History' of a plan.
Uncovers hidden risks, missing technical dependencies, and completely unstated assumptions. Pass the plan/code/architecture you want decoded.
Args: current_plan: The proposal, code snippet, feature set, or architecture. project_type: Category (e.g. SaaS, Mobile App, AI Agent, Protocol Design).
| Name | Required | Description | Default |
|---|---|---|---|
| current_plan | Yes | ||
| project_type | No | Software |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden. It explains the tool uncovers hidden risks and dependencies, suggesting a read-only analysis. However, it does not confirm no side effects, auth needs, or output behavior beyond the presence of an output schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with two sentences for purpose and then parameter descriptions. No unnecessary words, front-loaded with the main action. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has an output schema (so return info is covered), the description is fairly complete. It explains the tool's purpose and usage. Minor gaps: no mention of required permissions or best practices, but overall sufficient for a non-complex tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description must compensate. It provides clear but concise explanations for both parameters: 'current_plan' as the input to decode, and 'project_type' with examples. This adds meaning beyond the schema, though default values or formats are not detailed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool reveals the 'Void History' of a plan, uncovering hidden risks, dependencies, and assumptions. The verb 'Reveal/Uncovers' is specific, and the resource (plan/code/architecture) is well-defined. With no sibling tools, differentiation is not needed.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description says to pass a plan/code/architecture for decoding, implying when to use it. However, it does not specify when not to use it or provide alternatives, but the context is clear given no sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0read_poneglyphScored across 1 tool
With only one tool, there is no risk of confusion between tools. The single tool's purpose is clearly described.
The single tool name 'read_poneglyph' follows a clear verb_noun pattern, which is consistent and descriptive.
A single tool for broad plan analysis feels thin for the scope implied. While functional, it could be expanded into multiple specialized tools.
The tool claims to uncover risks, dependencies, and assumptions, bundling multiple analyses into one. This covers the basic need but lacks granularity for complex scenarios.
Structured visual plans and PR recaps with diagrams, prototypes, annotations, and sharing
Stress-test a decision through named thinkers' lenses: assumptions, counter-arguments, receipt.
Find your AI agent's likely failure mode, get runtime settings, and clarify ambiguous prompts.
Turn grounded AI answers into trusted comparisons, plans, timelines, and decision views.