Name: Lotus Wisdom
Author: linxule

LABSCO SUMMARY

A thinking structure for questions where the fast answer is the wrong one, and a record of how the answer was reached.

The value is the constraint: the model has to name what it is doing at each step — recognise, examine, integrate, transcend — instead of producing one confident paragraph. The journey it returns is readable afterwards, so you can see where an answer turned, and the tool only releases the model to speak once it reports WISDOM_READY.

What it is

A reasoning-scaffold server built on the Lotus Sutra framework: the model works a problem step by step, each step tagged with a technique, until the tool reports the contemplation complete.

What you get

A stepwise process where each step carries a tag from one of the wisdom domains — skillful means, non-dual recognition, meta-cognitive, process flow — and the first begin step returns the full framework
Meditation steps that pause deliberately to let an insight settle, with a duration between 1 and 10 seconds
Journey tracking: both the tag path and the movement between wisdom domains, retrievable as a summary of every step taken
Explicit statuses to drive the loop — FRAMEWORK_RECEIVED on the opening step, MEDITATION_COMPLETE on a pause, WISDOM_READY when the process is done
Structured output alongside the text response, validated against the tool's own output schema
Two prompts, contemplate and deep-inquiry, that set up a guided session in one step
An interactive inline trace in clients supporting MCP ext-apps, following the host's light or dark theme and reachable by keyboard
Behavioural annotations on the tool — readOnlyHint, idempotentHint, destructiveHint false, openWorldHint false — so a host can treat the call as side-effect free

Requirements

Nothing to authorize. Published on npm as lotus-wisdom-mcp for stdio use, and also hosted as a remote streamable-http endpoint at https://lotus-wisdom-mcp.linxule.workers.dev/mcp. The hosted one keeps no session state, so pass the previousJourney string back to carry a contemplation forward.

Setup effort

One command — npx -y lotus-wisdom-mcp

See installation options

USE CASES

01

Working a question that holds a real contradiction

Run the contemplation across domains so the tension gets examined and integrated rather than resolved away in the first sentence.

lotuswisdom

02

Starting a guided session without writing the scaffolding

Use the contemplate prompt for a single question, or deep-inquiry for a longer pass across the domains.

lotuswisdom

03

Reviewing how a conclusion was reached

Pull the summary of the journey — every step with its tag, its domain and its content.

lotuswisdom_summary

04

Continuing a contemplation in a client that keeps no state

Pass the previous journey string back in, and the process picks up where it left off.

lotuswisdomlotuswisdom_summary

2 tools

Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.

`lotuswisdom`

Contemplative reasoning tool. Use for complex problems needing multi-perspective understanding, contradictions requiring integration, or questions holding their own wisdom.

Workflow: Always start with tag='begin' (returns framework). Then continue with contemplation tags. Do NOT output wisdom until status='WISDOM_READY'.

Tags: begin (FIRST - receives framework), then: open/engage/express (process), examine/reflect/verify/refine/complete (meta-cognitive), recognize/transform/integrate/transcend/embody (non-dual), upaya/expedient/direct/gradual/sudden (skillful-means), meditate (pause).

BEFORE YOU INSTALL

What to know first

Tools you get

2 tools when we connected. The 24 wisdom tags are values of the tag parameter of lotuswisdom, and contemplate and deep-inquiry are MCP prompts, not tools.

Requires

npx on PATH

CONTEXT COST

Light Standing cost

Rated by the size of the 2 tool definitions that ride along on every turn, not by how many there are

INSTALLATION

Connect your client

Server setup

npx

TERMINAL

npx -y lotus-wisdom-mcp

Hosted endpoint

ENDPOINT URL

https://lotus-wisdom-mcp.linxule.workers.dev/mcp

Add this hosted endpoint to your MCP client.

MCP Clients

Claude Code

CLAUDE CODE · TERMINAL

claude mcp add lotus-wisdom -- npx -y lotus-wisdom-mcp

Codex

CODEX · TOML

[mcp_servers.lotus-wisdom]
command = "npx"
args = ["-y", "lotus-wisdom-mcp"]

Gemini CLI, Claude Desktop, Cursor, Windsurf, Cline

JSON

{
  "mcpServers": {
    "lotus-wisdom": {
      "command": "npx",
      "args": [
        "-y",
        "lotus-wisdom-mcp"
      ]
    }
  }
}

VS Code

VS CODE · JSON

{
  "servers": {
    "lotus-wisdom": {
      "command": "npx",
      "args": [
        "-y",
        "lotus-wisdom-mcp"
      ]
    }
  }
}

Cherry Studio

CHERRY STUDIO · JSON

{
  "mcpServers": {
    "lotus-wisdom": {
      "name": "Lotus Wisdom",
      "command": "npx",
      "args": [
        "-y",
        "lotus-wisdom-mcp"
      ],
      "isActive": true
    }
  }
}

Witsy

Settings > MCP Servers, Type: stdio, Command: npx, Args: -y lotus-wisdom-mcp

ChatGPT

Settings > Connectors → https://lotus-wisdom-mcp.linxule.workers.dev/mcp (remote only)

Any MCP client — mcp-remote

ANY MCP CLIENT — MCP-REMOTE · JSON

{
  "mcpServers": {
    "lotus-wisdom": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://lotus-wisdom-mcp.linxule.workers.dev/mcp"
      ]
    }
  }
}

Lotus Wisdom