lotus-wisdom-mcp 0.1.2 → 0.2.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -5,12 +5,14 @@
5
5
  </p>
6
6
 
7
7
  An MCP server implementation that provides a tool for problem-solving using the Lotus Sutra's wisdom framework, combining analytical thinking with intuitive wisdom.
8
+
8
9
  ## Features
9
10
 
10
11
  * Multi-faceted problem-solving approach inspired by the Lotus Sutra
11
12
  * Step-by-step thought process with different thinking techniques
12
13
  * Meditation pauses to allow insights to emerge naturally
13
14
  * Beautifully formatted thought process visualization with colors and symbols
15
+ * Tracks both tag journey and wisdom domain movements
14
16
  * Final integration of insights into a clear response
15
17
 
16
18
  ## Background
@@ -21,27 +23,36 @@ Note: The original prompt framework may work less effectively with newer Claude
21
23
 
22
24
  ## Implementation Details
23
25
 
24
- The server implements a structured thinking process using the following components:
26
+ The server implements a structured thinking process using wisdom domains inspired by the Lotus Sutra:
27
+
28
+ ### Wisdom Domains and Tags
29
+
30
+ The server organizes thoughts using five wisdom domains (all valid values for the `tag` input parameter):
31
+
32
+ * **Skillful Means** (🔆): `upaya`, `expedient`, `direct`, `gradual`, `sudden`
33
+ - Different approaches to truth - sometimes direct pointing, sometimes gradual unfolding
25
34
 
26
- ### Tag Types
35
+ * **Non-Dual Recognition** (☯️): `recognize`, `transform`, `integrate`, `transcend`, `embody`
36
+ - Aspects of awakening to what's already present - recognition IS transformation
27
37
 
28
- The server organizes thoughts using various tag categories (all valid values for the `tag` input parameter):
38
+ * **Meta-Cognitive** (🧠): `examine`, `reflect`, `verify`, `refine`, `complete`
39
+ - The mind watching its own understanding unfold
29
40
 
30
- * **Skillful Means**: upaya, expedient, direct, gradual, sudden
31
- * **Non-Dual Recognition**: recognize, transform, integrate, transcend, embody
32
- * **Meta-Cognitive Awareness**: examine, reflect, verify, refine, complete
33
- * **Process Steps**: open, engage, transform, express, meditate
34
- * **Final Output**: OUTPUT
41
+ * **Process Flow** (🌊): `open`, `engage`, `express`
42
+ - A natural arc that can contain any of the above approaches
43
+
44
+ * **Meditation** (🧘): `meditate`
45
+ - Pausing to let insights emerge from stillness
35
46
 
36
47
  ### Thought Visualization
37
48
 
38
49
  Each thought is beautifully formatted with:
39
50
 
40
51
  * Colorful output using the chalk library
41
- * Tag-specific symbols (e.g., 🔆 for skillful means, ☯️ for non-dual recognition)
52
+ * Domain-specific symbols and colors
42
53
  * Box-drawing characters to create clear thought boundaries
43
54
  * Special meditation formatting with pause indicators
44
- * Final output with double-line borders for emphasis
55
+ * Journey tracking showing both tag path and domain movements
45
56
 
46
57
  Note: The visualization appears in the server console output, helping developers track the thinking process.
47
58
 
@@ -50,10 +61,12 @@ Note: The visualization appears in the server console output, helping developers
50
61
  1. The user submits a problem to solve
51
62
  2. The model works through a sequence of thoughts using different tags
52
63
  3. Each thought builds on previous ones and may revise understanding
53
- 4. Meditation pauses can be included for clarity
54
- 5. The process concludes with a final OUTPUT thought
64
+ 4. The tool tracks both the tag journey and wisdom domain movements
65
+ 5. Meditation pauses can be included for clarity
66
+ 6. When status='WISDOM_READY' is returned, the tool's work is complete
67
+ 7. The model then expresses the final wisdom naturally in its own voice
55
68
 
56
- ## Tool
69
+ ## Available Tools
57
70
 
58
71
  ### lotuswisdom
59
72
 
@@ -61,13 +74,29 @@ A tool for problem-solving using the Lotus Sutra's wisdom framework, with variou
61
74
 
62
75
  **Inputs:**
63
76
 
64
- * `tag` (string): The current processing technique (must be one of the core tags listed above)
65
- * `content` (string): The content of the current processing step
66
- * `stepNumber` (integer): Current number in sequence
67
- * `totalSteps` (integer): Estimated total steps needed
68
- * `nextStepNeeded` (boolean): Whether another step is needed
77
+ * `tag` (string, required): The current processing technique (must be one of the tags listed above)
78
+ * `content` (string, required): The content of the current processing step
79
+ * `stepNumber` (integer, required): Current number in sequence
80
+ * `totalSteps` (integer, required): Estimated total steps needed
81
+ * `nextStepNeeded` (boolean, required): Whether another step is needed
69
82
  * `isMeditation` (boolean, optional): Whether this step is a meditative pause
70
- * `meditationDuration` (integer, optional): Duration for meditation in seconds
83
+ * `meditationDuration` (integer, optional): Duration for meditation in seconds (1-10)
84
+
85
+ **Returns:**
86
+ - Processing status with current step information, wisdom domain, and journey tracking
87
+ - `MEDITATION_COMPLETE` status for meditation steps
88
+ - `WISDOM_READY` status when the contemplative process is complete
89
+
90
+ ### lotuswisdom_summary
91
+
92
+ Get a summary of the current contemplative journey.
93
+
94
+ **Inputs:** None
95
+
96
+ **Returns:**
97
+ - Journey length
98
+ - Domain journey showing movement between wisdom domains
99
+ - Summary of all steps with their tags, domains, and brief content
71
100
 
72
101
  ## Usage
73
102
 
@@ -133,18 +162,18 @@ Here's how a conversation with Claude might flow when using the Lotus Wisdom MCP
133
162
  }
134
163
  ```
135
164
 
136
- 5. Provide a final output:
165
+ 5. Express the final understanding:
137
166
  ```json
138
167
  {
139
- "tag": "OUTPUT",
140
- "content": "Freedom and responsibility exist in dynamic balance. Freedom is the power to choose, while responsibility is accountability for those choices. They're not opposing forces but complementary aspects of human agency. Without freedom, responsibility would be mere obligation. Without responsibility, freedom would degrade into impulsivity. The most fulfilled lives embrace both: using freedom to make meaningful choices while taking responsibility for their consequences.",
168
+ "tag": "express",
169
+ "content": "The paradox resolves when we see that authentic freedom includes responsibility as its natural expression.",
141
170
  "stepNumber": 5,
142
171
  "totalSteps": 5,
143
172
  "nextStepNeeded": false
144
173
  }
145
174
  ```
146
175
 
147
- The result would be a thoughtful, multi-perspective response to the question that shows the process of arriving at wisdom rather than just stating conclusions.
176
+ When the tool returns `status: 'WISDOM_READY'`, Claude then speaks the final wisdom naturally, integrating all the insights from the contemplative journey.
148
177
 
149
178
  ## Configuration
150
179
 
@@ -152,7 +181,25 @@ The result would be a thoughtful, multi-perspective response to the question tha
152
181
 
153
182
  Add this to your `claude_desktop_config.json`:
154
183
 
155
- #### From npm (recommended)
184
+ #### From Smithery (recommended for easy installation)
185
+
186
+ ```json
187
+ {
188
+ "mcpServers": {
189
+ "lotus-wisdom": {
190
+ "command": "npx",
191
+ "args": [
192
+ "-y",
193
+ "@smithery/server-linxule-lotus-wisdom-mcp"
194
+ ]
195
+ }
196
+ }
197
+ }
198
+ ```
199
+
200
+ Or install directly via [Smithery.ai](https://smithery.ai/server/@linxule/lotus-wisdom-mcp)
201
+
202
+ #### From npm
156
203
 
157
204
  ```json
158
205
  {
@@ -184,7 +231,7 @@ Add this to your `claude_desktop_config.json`:
184
231
  }
185
232
  ```
186
233
 
187
- #### docker
234
+ #### Docker
188
235
 
189
236
  ```json
190
237
  {
@@ -202,45 +249,66 @@ Add this to your `claude_desktop_config.json`:
202
249
  }
203
250
  ```
204
251
 
205
- ## Building
252
+ ### Building
206
253
 
207
- Docker:
254
+ To build the project locally:
208
255
 
256
+ ```bash
257
+ npm install
258
+ npm run build
209
259
  ```
260
+
261
+ To build the Docker image:
262
+
263
+ ```bash
210
264
  docker build -t lotus-wisdom-mcp -f Dockerfile .
211
265
  ```
212
266
 
213
- ## License
267
+ ### Development
214
268
 
215
- This MCP server is licensed under the MIT License. For more details, please see the LICENSE file in the project repository.
269
+ For local development:
216
270
 
217
- ## Connect from Claude Desktop
271
+ ```bash
272
+ npm install
273
+ npm run dev
274
+ ```
218
275
 
219
- Since Claude Desktop doesn't yet have native support for remote MCP servers with authentication, you'll need to use the `mcp-remote` proxy:
276
+ Enable debug mode by setting the environment variable:
220
277
 
221
- 1. Update your Claude Desktop configuration file:
222
- - macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`
223
- - Windows: `%APPDATA%\Claude\claude_desktop_config.json`
278
+ ```bash
279
+ LOTUS_DEBUG=true npm start
280
+ ```
224
281
 
225
- 2. Add the following configuration:
282
+ ## How It Works
226
283
 
227
- ```json
228
- {
229
- "mcpServers": {
230
- "lotus-wisdom": {
231
- "command": "npx",
232
- "args": ["mcp-remote", "https://lotus-wisdom-mcp.linxule.workers.dev/sse"]
233
- }
234
- }
235
- }
236
- ```
284
+ The 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:
237
285
 
238
- 3. Restart Claude Desktop (Cmd/Ctrl + R)
286
+ 1. **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.
239
287
 
240
- 4. When Claude restarts, a browser window will open for OAuth authentication. Complete the authorization flow to grant Claude access to the MCP server.
288
+ 2. **Journey Consciousness**: The tool maintains awareness of your complete journey, showing both the sequence of tags used and the movement between wisdom domains.
241
289
 
242
- 5. Once authenticated, you'll see the Lotus Wisdom tools available in Claude's tool menu (bottom right corner).
290
+ 3. **Non-Linear Progress**: While steps are numbered, the process isn't strictly linear. You can revisit, revise, and branch as understanding deepens.
243
291
 
244
- ## Available Tools
292
+ 4. **Integration Points**: Tags like `integrate`, `transcend`, and `embody` help weave insights together rather than keeping them separate.
293
+
294
+ 5. **Natural Expression**: The tool handles the contemplative process, but the final wisdom is always expressed naturally by the AI, not as formatted output.
295
+
296
+ ## License
297
+
298
+ This MCP server is licensed under the MIT License. For more details, please see the LICENSE file in the project repository.
299
+
300
+ ## Contributing
301
+
302
+ Contributions are welcome! Please feel free to submit issues or pull requests on the [GitHub repository](https://github.com/linxule/lotus-wisdom-mcp).
303
+
304
+ ## Version
305
+
306
+ Current version: 0.2.0
307
+
308
+ ### What's New in 0.2.0
245
309
 
246
- // ... existing code ...
310
+ - 🌐 **HTTP Transport Support**: Now deployable on smithery.ai and other HTTP-based platforms
311
+ - 🔄 **Dual Transport**: Maintains stdio support for npm/CLI users while adding HTTP for remote deployment
312
+ - 📦 **Updated SDK**: Upgraded to @modelcontextprotocol/sdk 1.20.1 with Streamable HTTP support
313
+ - 🪷 **New Logo**: Terminal-aesthetic lotus logo perfect for developer tools
314
+ - ⚡ **Session Management**: HTTP version includes full session management for stateful wisdom journeys