An MCP server implementation that provides a tool for problem-solving using the Lotus Sutra's wisdom framework, combining analytical thinking with intuitive wisdom. Multi-faceted problem-solving approach inspired by the Lotus Sutra Step-by-step thought process with different thinking techniques Meditation pauses to allow insights to emerge naturally Beautifully formatted thought process visualizat
Add this skill
npx mdskills install linxule/lotus-wisdom-mcpWell-documented contemplative problem-solving framework with clear tool design and extensive setup guides
1# 🪷 Lotus Wisdom MCP Server23<p align="center">4 <img src="assets/lotus-flower.png" alt="Lotus Flower" width="400"/>5</p>67An MCP server implementation that provides a tool for problem-solving using the Lotus Sutra's wisdom framework, combining analytical thinking with intuitive wisdom.89## Features1011* Multi-faceted problem-solving approach inspired by the Lotus Sutra12* Step-by-step thought process with different thinking techniques13* Meditation pauses to allow insights to emerge naturally14* Beautifully formatted thought process visualization with colors and symbols15* Tracks both tag journey and wisdom domain movements16* Final integration of insights into a clear response1718## Background1920This MCP server was developed from the [Lotus OS prompt](https://github.com/linxule/prompts/blob/main/cognitive-techniques/lotus_os.md), which was designed to implement a cognitive framework based on the Lotus Sutra. The MCP server format makes this framework more accessible and easier to use with Claude and other AI assistants.2122Note: The original prompt framework may work less effectively with newer Claude models, but this MCP server implementation provides consistent functionality across model versions.2324## Implementation Details2526The server implements a structured thinking process using wisdom domains inspired by the Lotus Sutra:2728### Wisdom Domains and Tags2930The server organizes thoughts using wisdom domains (all valid values for the `tag` input parameter):3132* **Entry** (🚪): `begin`33 - Begin your journey here - receives the full framework before contemplation starts3435* **Skillful Means** (🔆): `upaya`, `expedient`, `direct`, `gradual`, `sudden`36 - Different approaches to truth - sometimes direct pointing, sometimes gradual unfolding3738* **Non-Dual Recognition** (☯️): `recognize`, `transform`, `integrate`, `transcend`, `embody`39 - Aspects of awakening to what's already present - recognition IS transformation4041* **Meta-Cognitive** (🧠): `examine`, `reflect`, `verify`, `refine`, `complete`42 - The mind watching its own understanding unfold4344* **Process Flow** (🌊): `open`, `engage`, `express`45 - A natural arc that can contain any of the above approaches4647* **Meditation** (🧘): `meditate`48 - Pausing to let insights emerge from stillness4950### Thought Visualization5152Each thought is beautifully formatted with:5354* Colorful output using the chalk library55* Domain-specific symbols and colors56* Box-drawing characters to create clear thought boundaries57* Special meditation formatting with pause indicators58* Journey tracking showing both tag path and domain movements5960Note: The visualization appears in the server console output, helping developers track the thinking process.6162### Process Flow63641. The user submits a problem to solve652. The model begins with `tag='begin'` to receive the full framework663. The model continues with contemplation tags (open, examine, integrate, etc.)674. Each thought builds on previous ones and may revise understanding685. The tool tracks both the tag journey and wisdom domain movements696. Meditation pauses can be included for clarity707. When status='WISDOM_READY' is returned, the tool's work is complete718. The model then expresses the final wisdom naturally in its own voice7273## Available Tools7475### lotuswisdom7677A tool for problem-solving using the Lotus Sutra's wisdom framework, with various approaches to understanding.7879**Begin your journey with `tag='begin'`** - this returns the full framework (philosophy, domains, guidance) to ground your contemplation. Then continue with the other tags.8081**Inputs:**8283* `tag` (string, required): The current processing technique (must be one of the tags listed above)84* `content` (string, required): The content of the current processing step85* `stepNumber` (integer, required): Current number in sequence86* `totalSteps` (integer, required): Estimated total steps needed87* `nextStepNeeded` (boolean, required): Whether another step is needed88* `isMeditation` (boolean, optional): Whether this step is a meditative pause89* `meditationDuration` (integer, optional): Duration for meditation in seconds (1-10)9091**Returns:**92- Processing status with current step information, wisdom domain, and journey tracking93- `MEDITATION_COMPLETE` status for meditation steps94- `WISDOM_READY` status when the contemplative process is complete9596### lotuswisdom_summary9798Get a summary of the current contemplative journey.99100**Inputs:** None101102**Returns:**103- Journey length104- Domain journey showing movement between wisdom domains105- Summary of all steps with their tags, domains, and brief content106107## Usage108109The Lotus Wisdom tool is designed for:110111* Breaking down complex problems requiring multi-faceted understanding112* Questions that benefit from both direct and gradual approaches113* Problems where apparent contradictions need integration114* Situations requiring both analytical and intuitive understanding115* Tasks that benefit from meditative pauses to allow insight116* Questions containing their own inherent wisdom117118## Example Usage119120Here's how a conversation with Claude might flow when using the Lotus Wisdom MCP server:121122**User**: "Help me understand the relationship between freedom and responsibility."123124**Claude** would begin the journey with `tag='begin'` to receive the framework, then continue:1251261. First, enter the contemplative space:127```json128{129 "tag": "begin",130 "content": "Entering contemplation on freedom and responsibility.",131 "stepNumber": 1,132 "totalSteps": 6,133 "nextStepNeeded": true134}135```136→ Returns `FRAMEWORK_RECEIVED` with full framework1371382. Then, establish an opening thought:139```json140{141 "tag": "open",142 "content": "The question explores the relationship between freedom and responsibility, which contain an apparent tension but also deep connection.",143 "stepNumber": 2,144 "totalSteps": 6,145 "nextStepNeeded": true146}147```1481493. Engage with different perspectives:150```json151{152 "tag": "direct",153 "content": "Freedom and responsibility are two sides of the same coin. True freedom isn't absence of constraints but the capacity to choose our response within constraints.",154 "stepNumber": 3,155 "totalSteps": 6,156 "nextStepNeeded": true157}158```1591604. Perhaps take a meditation pause:161```json162{163 "tag": "meditate",164 "content": "Contemplating how freedom without responsibility becomes chaos, and responsibility without freedom becomes oppression.",165 "stepNumber": 4,166 "totalSteps": 6,167 "nextStepNeeded": true,168 "isMeditation": true169}170```1711725. Integrate the understanding:173```json174{175 "tag": "integrate",176 "content": "Freedom and responsibility mutually enable each other. Our freedom to choose gives rise to our responsibility for what we choose, and our willingness to take responsibility expands our freedom.",177 "stepNumber": 5,178 "totalSteps": 6,179 "nextStepNeeded": true180}181```1821836. Express the final understanding:184```json185{186 "tag": "express",187 "content": "The paradox resolves when we see that authentic freedom includes responsibility as its natural expression.",188 "stepNumber": 6,189 "totalSteps": 6,190 "nextStepNeeded": false191}192```193194When the tool returns `status: 'WISDOM_READY'`, Claude then speaks the final wisdom naturally, integrating all the insights from the contemplative journey.195196## Installation197198[](https://smithery.ai/server/lotus-wisdom-mcp)199200Install via [Smithery](https://smithery.ai/server/lotus-wisdom-mcp) for one-click setup, or follow the manual instructions below.201202Requires [Node.js](https://nodejs.org/) 18+. The server runs locally via `npx`.203204### CLI Install (one-liner)205206```bash207# Claude Code208claude mcp add lotus-wisdom -- npx -y lotus-wisdom-mcp209210# Codex CLI (OpenAI)211codex mcp add lotus-wisdom -- npx -y lotus-wisdom-mcp212213# Gemini CLI (Google)214gemini mcp add lotus-wisdom npx -y lotus-wisdom-mcp215```216217### Claude Desktop218219Add to your `claude_desktop_config.json`:220221| OS | Config path |222|----|-------------|223| macOS | `~/Library/Application Support/Claude/claude_desktop_config.json` |224| Windows | `%APPDATA%\Claude\claude_desktop_config.json` |225| Linux | `~/.config/Claude/claude_desktop_config.json` |226227```json228{229 "mcpServers": {230 "lotus-wisdom": {231 "command": "npx",232 "args": ["-y", "lotus-wisdom-mcp"]233 }234 }235}236```237238### VS Code239240Add to `.vscode/mcp.json` (workspace) or open Command Palette > `MCP: Open User Configuration` (global):241242```json243{244 "servers": {245 "lotus-wisdom": {246 "command": "npx",247 "args": ["-y", "lotus-wisdom-mcp"]248 }249 }250}251```252253> **Note**: VS Code uses `"servers"` as the top-level key, not `"mcpServers"`. Other VS Code forks (Trae, Void, PearAI, etc.) typically use this same format.254255### Cursor256257Add to `~/.cursor/mcp.json` (global) or `.cursor/mcp.json` (project):258259```json260{261 "mcpServers": {262 "lotus-wisdom": {263 "command": "npx",264 "args": ["-y", "lotus-wisdom-mcp"]265 }266 }267}268```269270### Windsurf271272Add to `~/.codeium/windsurf/mcp_config.json` (Windows: `%USERPROFILE%\.codeium\windsurf\mcp_config.json`):273274```json275{276 "mcpServers": {277 "lotus-wisdom": {278 "command": "npx",279 "args": ["-y", "lotus-wisdom-mcp"]280 }281 }282}283```284285### Cline286287Open MCP Servers icon in Cline panel > Configure > Advanced MCP Settings, then add:288289```json290{291 "mcpServers": {292 "lotus-wisdom": {293 "command": "npx",294 "args": ["-y", "lotus-wisdom-mcp"]295 }296 }297}298```299300### Cherry Studio301302In Settings > MCP Servers > Add Server, set Type to `STDIO`, Command to `npx`, Args to `-y lotus-wisdom-mcp`. Or paste in JSON/Code mode:303304```json305{306 "lotus-wisdom": {307 "name": "Lotus Wisdom",308 "command": "npx",309 "args": ["-y", "lotus-wisdom-mcp"],310 "isActive": true311 }312}313```314315### Witsy316317In Settings > MCP Servers, add a new server with Type: `stdio`, Command: `npx`, Args: `-y lotus-wisdom-mcp`.318319### Codex CLI (TOML config)320321Alternatively, edit `~/.codex/config.toml` directly:322323```toml324[mcp_servers.lotus-wisdom]325command = "npx"326args = ["-y", "lotus-wisdom-mcp"]327```328329### Gemini CLI (JSON config)330331Alternatively, edit `~/.gemini/settings.json` directly:332333```json334{335 "mcpServers": {336 "lotus-wisdom": {337 "command": "npx",338 "args": ["-y", "lotus-wisdom-mcp"]339 }340 }341}342```343344### Windows345346On Windows, `npx` requires a shell wrapper. Replace `"command": "npx"` with:347348```json349{350 "command": "cmd",351 "args": ["/c", "npx", "-y", "lotus-wisdom-mcp"]352}353```354355For CLI tools on Windows:356357```bash358claude mcp add lotus-wisdom -- cmd /c npx -y lotus-wisdom-mcp359codex mcp add lotus-wisdom -- cmd /c npx -y lotus-wisdom-mcp360```361362### ChatGPT363364ChatGPT only supports remote MCP servers over HTTPS. Use [Smithery](https://smithery.ai/server/lotus-wisdom-mcp) or connect directly to the hosted instance below via ChatGPT Settings > Connectors.365366### Remote (hosted)367368A public instance is available at `https://lotus-wisdom-mcp.linxule.workers.dev/mcp`. No API key needed.369370For clients supporting Streamable HTTP, connect directly to the URL. For stdio-only clients, use `mcp-remote`:371372```json373{374 "mcpServers": {375 "lotus-wisdom": {376 "command": "npx",377 "args": ["-y", "mcp-remote", "https://lotus-wisdom-mcp.linxule.workers.dev/mcp"]378 }379 }380}381```382383To self-host your own instance, see [`worker/README.md`](worker/README.md).384385### Building from source386387```bash388bun install389bun run build390bun run start391```392393Enable debug mode:394395```bash396LOTUS_DEBUG=true bun run start397```398399## How It Works400401The Lotus Wisdom framework recognizes that wisdom often emerges not through linear thinking but through a dance between different modes of understanding. The tool facilitates this by:4024031. **Tracking Wisdom Domains**: As you move through different tags, the tool tracks which wisdom domains you're engaging, helping you see the shape of your inquiry.4044052. **Journey Consciousness**: The tool maintains awareness of your complete journey, showing both the sequence of tags used and the movement between wisdom domains.4064073. **Non-Linear Progress**: While steps are numbered, the process isn't strictly linear. You can revisit, revise, and branch as understanding deepens.4084094. **Integration Points**: Tags like `integrate`, `transcend`, and `embody` help weave insights together rather than keeping them separate.4104115. **Natural Expression**: The tool handles the contemplative process, but the final wisdom is always expressed naturally by the AI, not as formatted output.412413### Token Optimization Design414415MCP tool descriptions stay in the AI's context window constantly when the server is connected. To minimize this overhead while preserving the full teaching content:416417- **Constant context (~150 tokens)**: The `lotuswisdom` tool description is kept minimal—just enough for the AI to know when and how to use it418- **On-demand learning (~1,200 tokens)**: The complete framework is delivered when calling with `tag='begin'`, including:419 - Philosophy and domain spirits420 - Parameter explanations (tag, content, stepNumber, etc.)421 - Response format details (wisdomDomain, journey, domainJourney)422 - Meditation handling (MEDITATION_COMPLETE status)423 - When to use guidance424- **Learn first, practice second**: The `begin` tag ensures models receive complete understanding before contemplating425426This approach reduces constant context overhead by ~85% when the tool is idle. When actually used, the full framework is delivered on first step—nothing is lost.427428## License429430This MCP server is licensed under the MIT License. For more details, please see the LICENSE file in the project repository.431432## Contributing433434Contributions are welcome! Please feel free to submit issues or pull requests on the [GitHub repository](https://github.com/linxule/lotus-wisdom-mcp).435436## Version437438Current version: 0.3.2439440### What's New in 0.3.2441442- 🚪 **Simplified Begin**: `tag='begin'` can now be called with just `{"tag":"begin"}` - all other params auto-filled443- 🤖 **Better Haiku/Small Model Support**: Removes friction for models that don't infer all required params444445### What's New in 0.3.1446447- 📚 **Complete Framework Learning**: `begin` tag now returns full parameter explanations, response format details, and meditation handling448- 🔢 **Accurate Token Counts**: Updated documentation with actual token measurements (~150 constant, ~1,200 on-demand)449450### What's New in 0.3.0451452- 🚪 **Begin Tag**: New `tag='begin'` opens the journey—returns full framework before contemplation starts453- ⚡ **Optimized Token Footprint**: Reduced constant context overhead from ~1400 to ~200 tokens while preserving full teaching content454- 🧘 **Learn First, Practice Second**: The `begin` tag ensures models receive complete understanding before contemplating455- 📦 **Updated SDK**: Upgraded to @modelcontextprotocol/sdk 1.23.0456457### What's New in 0.2.1458459- 📋 **MCP Registry Enhancement**: Added `title` field for better discoverability460- 🎯 **Full Compliance**: Now fully compliant with official MCP publishing guide461- 🔗 **Registry Links**: Available on [Official MCP Registry](https://registry.mcpservers.org/)462463### What's New in 0.2.0464465- 🌐 **HTTP Transport Support**: Now deployable on smithery.ai and other HTTP-based platforms466- 🔄 **Dual Transport**: Maintains stdio support for npm/CLI users while adding HTTP for remote deployment467- 📦 **Updated SDK**: Upgraded to @modelcontextprotocol/sdk 1.20.1 with Streamable HTTP support468- 🪷 **New Logo**: Terminal-aesthetic lotus logo perfect for developer tools469- ⚡ **Session Management**: HTTP version includes full session management for stateful wisdom journeys
Full transparency — inspect the skill content before installing.