Skip to main content
Glama

⚔️ Conqueror's Haki

An MCP server that cuts a long list down to the one to three things that actually matter right now.

A Model Context Protocol (MCP) server — one focused tool you plug into an MCP-compatible client (Claude Desktop, Claude Code, Cursor, and others).

What it does

Models tend to treat every item on a list as equally worthy of attention. That's the opposite of prioritization. Real prioritization means deciding what to ignore.

Conqueror's Haki takes a list and a single goal, forces a ruthless head-to-head ranking, and eliminates everything that doesn't directly serve that goal.

Related MCP server: mcp-context-guard

Usage

Give it your backlog and a North Star (e.g. "Launch a paid MVP in two weeks"). It returns:

  • The Conquered — what was eliminated, each with a one-line reason it's a distraction

  • The Standing Kings — the survivors, strictly ranked (at most three)

  • Reason for Dominance — why each survivor earns the focus

Set strictness_level="Overwhelming" to force exactly one survivor.

Tool reference: assert_conquerors_haki(items_to_evaluate: list[str], north_star_goal: str, strictness_level: str = "Supreme King")

How it works

No API key, no cost, nothing leaves your machine. The server returns an engineered ranking prompt that your existing model executes — it makes no language-model call of its own.

Install

Requires Python 3.10 or newer.

pip install conquerors-haki-mcp

This installs the conquerors-haki command.

Then register it with your MCP client — either run claude mcp add conquerors-haki -- conquerors-haki, or add this to the client's config (e.g. claude_desktop_config.json):

{
  "mcpServers": {
    "conquerors-haki": { "command": "conquerors-haki" }
  }
}

Restart the client and the tool is available.

The Grand Line stack

Conqueror's Haki is part of a four-tool set. Each tool stands alone, but installing all of them unlocks a final surprise via Laugh Tale.

Package

🗿

road-poneglyph

Road Poneglyph

⚔️

conquerors-haki

Conqueror's Haki · ← this repo

⏳

toki-toki

Toki Toki no Mi

🏴‍☠️

laugh-tale

Laugh Tale

Develop

git clone https://github.com/xfloukiex-lab/conquerors-haki
cd conquerors-haki
python -m venv .venv && . .venv/Scripts/activate   # macOS/Linux: source .venv/bin/activate
pip install -e ".[dev]"
python tests/test_conquerors_haki.py

Attribution & license

Released 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.

Available Tools

1 tool
assert_conquerors_hakiA

Exert supreme willpower over a chaotic list of ideas/tasks/features.

Knocks out the weak elements and forces a definitive, ranked priority list against one goal.

Args: items_to_evaluate: Raw list of features, tasks, bugs, or ideas. north_star_goal: The one objective that matters now (e.g. "Launch MVP in 2 weeks", "Get 10 active users"). strictness_level: "Supreme King" → max 3 survivors; "Overwhelming" → exactly 1 survivor.

Inputs: items_to_evaluate (required), north_star_goal (required), strictness_level. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 1 tool

    Disambiguation5/5

    Only one tool exists, so there is no possibility of confusion between tools.

    Naming Consistency5/5

    With a single tool, naming is trivially consistent; the name follows a clear verb_noun pattern.

    Tool Count3/5

    A single tool feels thin for a server, but it serves a focused purpose (prioritization), which is borderline acceptable.

    Completeness3/5

    The tool covers its single targeted operation well, but lacks any auxiliary or complementary operations, leaving notable gaps.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Turns an LLM agent into a personal planner by providing atomic context (roles, goals, decision matrix) and routing classified items to Obsidian, with optional projection to Google Calendar and Tasks.
      Apache 2.0
    • F
      license
      Not graded
      quality
      D
      maintenance
      A deterministic scoring engine for prioritizing workstreams across projects and clients, answering 'what should I work on right now?' with auditable rankings based on staleness, deadlines, revenue weight, and cascade risk.
      1
      -
    • A
      license
      Not graded
      quality
      B
      maintenance
      Provides deterministic context compaction and safety gating for AI agents, preserving original messages verbatim while dropping irrelevant ones and flagging destructive commands.
      2
      MIT