# Lotus Wisdom

> Lotus Wisdom is a free MCP server for ai models and llm tooling. Step-by-step contemplative reasoning tool based on the Lotus Sutra, with a halo view. It can run locally on your machine or as a hosted remote server.

- **Kind:** MCP server
- **Pricing:** Free
- **Platforms:** Web, CLI, API
- **Website:** https://lotus-wisdom-mcp.linxule.workers.dev
- **Repository:** https://github.com/linxule/lotus-wisdom-mcp
- **MCP Registry name:** io.github.linxule/lotus-wisdom
- **Categories:** AI models and LLM tooling
- **Listing updated:** 2026-11-14

## About

One tool, lotuswisdom, guides a model through a structured thought process. The first call uses the tag begin, which returns the full framework, and later calls use tags from named groups: skillful means, non-dual recognition, meta-cognitive steps such as examine, verify and refine, a process-flow arc of open, engage and express, and meditate for a pause. The tool tracks both the tag path and movement between wisdom domains, and when it returns status WISDOM_READY its work is done and the model states the final answer in its own voice.

The framework comes from the author's Lotus OS prompt. The README is candid that how well a model follows it depends on the model and the host. Prompts named contemplate and deep-inquiry provide one-step guided sessions, and results include structured output with an output schema.

In clients that support MCP ext-apps, each step appears inline as a pixel halo that lights one segment per step, in night and day variants that follow the host theme, with keyboard access and reduced-motion support. It can be run locally with npx or used as a hosted connector, and LOTUS_DEBUG=true prints per-step traces to the local console.

## Features

- **Begin tag framework:** The first step returns the whole framework before contemplation starts.
- **Wisdom domain tracking:** Records the path of tags and the domains they belong to.
- **Meditation pauses:** A meditate tag pauses so insights can emerge.
- **Halo visualization:** Inline halo that lights a segment per step in supporting clients.
- **Guided prompts:** contemplate and deep-inquiry prompts start a session in one step.
- **Structured output:** Returns structured content with an output schema for programs.

## Good for

- Work through a decision step by step with reflective prompts
- Add a slower reasoning pass before an assistant answers
- Visualise a chain of reasoning as a halo in the chat
- Experiment with an unusual prompting framework

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http lotus-wisdom https://lotus-wisdom-mcp.linxule.workers.dev/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

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

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "lotus-wisdom": {
      "url": "https://lotus-wisdom-mcp.linxule.workers.dev/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "lotus-wisdom": {
      "type": "http",
      "url": "https://lotus-wisdom-mcp.linxule.workers.dev/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "lotus-wisdom": {
      "serverUrl": "https://lotus-wisdom-mcp.linxule.workers.dev/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "lotus-wisdom": {
      "type": "http",
      "url": "https://lotus-wisdom-mcp.linxule.workers.dev/mcp"
    }
  }
}
```

## Tools

- `lotuswisdom`: Guides problem-solving step by step through the Lotus Sutra's wisdom framework, starting with tag begin.

## FAQ

### How do I connect it?

Add https://lotus-wisdom-mcp.linxule.workers.dev/mcp as a connector, or run npx -y lotus-wisdom-mcp.

### When is the work complete?

When the tool returns status WISDOM_READY, after which the model writes the final answer.

### Does the model always follow the framework?

No. The README says it depends on the model and host.

### Can I see debug traces?

The local server prints per-step traces to stderr when LOTUS_DEBUG=true.

### Is Lotus Wisdom free?

Yes. Lotus Wisdom is free to use.

### How do I add Lotus Wisdom to Claude Code?

Run this command in your terminal: claude mcp add --transport http lotus-wisdom https://lotus-wisdom-mcp.linxule.workers.dev/mcp

### What are the best alternatives to Lotus Wisdom?

The closest alternatives to Lotus Wisdom are Claude Code Ultimate Guide, signafAIde, Toolkien, Lugh and HypePaper.

## Alternatives

- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [signafAIde](https://ai-powered.com/mcp/signafaide): signafAIde is a freemium MCP server for security.
- [Toolkien](https://ai-powered.com/mcp/toolkien): Toolkien is an open-source MCP server for ai models and llm tooling.
- [Lugh](https://ai-powered.com/mcp/lugh): Lugh is an open-source MCP server for ai models and llm tooling.
- [HypePaper](https://ai-powered.com/mcp/hypepaper): HypePaper is a freemium MCP server for ai models and llm tooling.
- [Agent Data Tools: Compact (find, describe, run)](https://ai-powered.com/mcp/agent-data-tools-compact-find-describe-run): Agent Data Tools: Compact (find, describe, run) is a freemium MCP server for developer tools.
- [Angel Agent Guard: pre-purchase check + prompt-injection scan](https://ai-powered.com/mcp/angel-agent-guard-pre-purchase-check-prompt-injection-scan): Angel Agent Guard: pre-purchase check + prompt-injection scan is a freemium MCP server for ai models and llm tooling.
- [Mizan Calibration](https://ai-powered.com/mcp/mizan-calibration): Mizan Calibration is a free MCP server for ai models and llm tooling.

---
Source: https://ai-powered.com/mcp/lotus-wisdom
