lotus-wisdom-mcp 0.7.1 → 0.8.1
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 +80 -17
- package/dist/bundle.js +32678 -8632
- package/dist/journey.html +60 -174
- package/package.json +14 -10
- package/dist/cli.js +0 -3
- package/dist/index.js +0 -533
- package/dist/server.js +0 -522
package/README.md
CHANGED
|
@@ -6,14 +6,18 @@
|
|
|
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
|
+
Available at: https://lotus-wisdom-mcp.linxule.workers.dev/mcp
|
|
10
|
+
|
|
9
11
|
## Features
|
|
10
12
|
|
|
11
13
|
* Multi-faceted problem-solving approach inspired by the Lotus Sutra
|
|
12
14
|
* Step-by-step thought process with different thinking techniques
|
|
13
15
|
* Meditation pauses to allow insights to emerge naturally
|
|
14
|
-
* **Interactive visualization** via MCP ext-apps (Claude Desktop, Cursor, ChatGPT)
|
|
15
|
-
*
|
|
16
|
+
* **Interactive visualization** via MCP ext-apps (Claude Desktop, Cursor, ChatGPT) — adapts to the host light/dark theme and is keyboard-accessible
|
|
17
|
+
* **MCP Prompts** (`contemplate`, `deep-inquiry`) for one-step guided contemplative sessions
|
|
18
|
+
* **Structured tool output** (`structuredContent` + `outputSchema`) alongside the text response
|
|
16
19
|
* Tracks both tag journey and wisdom domain movements
|
|
20
|
+
* Available as a local stdio package (`npx`) or a hosted remote Connector
|
|
17
21
|
* Final integration of insights into a clear response
|
|
18
22
|
|
|
19
23
|
## Background
|
|
@@ -50,15 +54,13 @@ The server organizes thoughts using wisdom domains (all valid values for the `ta
|
|
|
50
54
|
|
|
51
55
|
### Thought Visualization
|
|
52
56
|
|
|
53
|
-
|
|
57
|
+
In clients that support MCP ext-apps, each step renders inline as an interactive "Living Trace" (see [Interactive Visualization](#interactive-visualization-ext-apps) below). For every client, each step also returns:
|
|
54
58
|
|
|
55
|
-
*
|
|
56
|
-
* Domain-specific
|
|
57
|
-
*
|
|
58
|
-
* Special meditation formatting with pause indicators
|
|
59
|
-
* Journey tracking showing both tag path and domain movements
|
|
59
|
+
* Journey tracking showing both the tag path and the wisdom-domain movements
|
|
60
|
+
* Domain-specific labels and the current contemplation text
|
|
61
|
+
* Structured output (`structuredContent` + `outputSchema`) for programmatic consumers
|
|
60
62
|
|
|
61
|
-
Note: The
|
|
63
|
+
Note: The local stdio server can emit per-step trace lines to its console (stderr) when run with `LOTUS_DEBUG=true`, helping developers follow the thinking process.
|
|
62
64
|
|
|
63
65
|
### Process Flow
|
|
64
66
|
|
|
@@ -88,23 +90,36 @@ A tool for problem-solving using the Lotus Sutra's wisdom framework, with variou
|
|
|
88
90
|
* `nextStepNeeded` (boolean, required): Whether another step is needed
|
|
89
91
|
* `isMeditation` (boolean, optional): Whether this step is a meditative pause
|
|
90
92
|
* `meditationDuration` (integer, optional): Duration for meditation in seconds (1-10)
|
|
93
|
+
* `previousJourney` (string, optional): The `journey` string from a previous response, e.g. `"begin → open → examine"`. Lets the AI carry journey continuity forward in stateless clients (such as the remote Worker), where the server keeps no session state.
|
|
91
94
|
|
|
92
|
-
**Returns:**
|
|
95
|
+
**Returns:** both a JSON text block and matching `structuredContent` (validated against the tool's `outputSchema`):
|
|
93
96
|
- Processing status with current step information, wisdom domain, and journey tracking
|
|
97
|
+
- `FRAMEWORK_RECEIVED` status (with the full framework) on the first `begin` step
|
|
94
98
|
- `MEDITATION_COMPLETE` status for meditation steps
|
|
95
99
|
- `WISDOM_READY` status when the contemplative process is complete
|
|
96
100
|
|
|
101
|
+
The tool also declares behavioral annotations — `readOnlyHint`, `idempotentHint`, `destructiveHint: false`, `openWorldHint: false` — so hosts can treat it as a safe, side-effect-free call.
|
|
102
|
+
|
|
97
103
|
### lotuswisdom_summary
|
|
98
104
|
|
|
99
105
|
Get a summary of the current contemplative journey.
|
|
100
106
|
|
|
101
|
-
**Inputs:**
|
|
107
|
+
**Inputs:**
|
|
108
|
+
|
|
109
|
+
* `previousJourney` (string, optional): The `journey` string from a previous response, used to reconstruct the summary in stateless clients.
|
|
102
110
|
|
|
103
111
|
**Returns:**
|
|
104
112
|
- Journey length
|
|
105
113
|
- Domain journey showing movement between wisdom domains
|
|
106
114
|
- Summary of all steps with their tags, domains, and brief content
|
|
107
115
|
|
|
116
|
+
## MCP Prompts
|
|
117
|
+
|
|
118
|
+
The server registers two prompts that scaffold a guided contemplative session (surfaced as slash commands or prompt pickers in clients that support MCP Prompts):
|
|
119
|
+
|
|
120
|
+
* **`contemplate`** — argument `question`: opens a single-question contemplation, instructing the model to start with `tag='begin'`, iterate, and speak the wisdom only once `status='WISDOM_READY'`.
|
|
121
|
+
* **`deep-inquiry`** — argument `topic`: begins a longer inquiry that moves deliberately across the wisdom domains (process → meta-cognitive → non-dual → meditation).
|
|
122
|
+
|
|
108
123
|
## Usage
|
|
109
124
|
|
|
110
125
|
The Lotus Wisdom tool is designed for:
|
|
@@ -196,9 +211,9 @@ When the tool returns `status: 'WISDOM_READY'`, Claude then speaks the final wis
|
|
|
196
211
|
|
|
197
212
|
## Installation
|
|
198
213
|
|
|
199
|
-
[](https://smithery.ai/server/lotus-wisdom-mcp)
|
|
214
|
+
[](https://smithery.ai/server/@linxule/lotus-wisdom-mcp)
|
|
200
215
|
|
|
201
|
-
Install via [Smithery](https://smithery.ai/server/lotus-wisdom-mcp) for one-click setup, or follow the manual instructions below.
|
|
216
|
+
Install via [Smithery](https://smithery.ai/server/@linxule/lotus-wisdom-mcp) for one-click setup, or follow the manual instructions below.
|
|
202
217
|
|
|
203
218
|
Requires [Node.js](https://nodejs.org/) 18+. The server runs locally via `npx`.
|
|
204
219
|
|
|
@@ -362,7 +377,7 @@ codex mcp add lotus-wisdom -- cmd /c npx -y lotus-wisdom-mcp
|
|
|
362
377
|
|
|
363
378
|
### ChatGPT
|
|
364
379
|
|
|
365
|
-
ChatGPT 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.
|
|
380
|
+
ChatGPT only supports remote MCP servers over HTTPS. Use [Smithery](https://smithery.ai/server/@linxule/lotus-wisdom-mcp) or connect directly to the hosted instance below via ChatGPT Settings > Connectors.
|
|
366
381
|
|
|
367
382
|
### Remote (hosted)
|
|
368
383
|
|
|
@@ -385,12 +400,26 @@ To self-host your own instance, see [`worker/README.md`](worker/README.md).
|
|
|
385
400
|
|
|
386
401
|
### Building from source
|
|
387
402
|
|
|
403
|
+
Use Bun 1.4.2 and Node.js 24 to match CI.
|
|
404
|
+
|
|
388
405
|
```bash
|
|
389
|
-
bun install
|
|
406
|
+
bun install --frozen-lockfile
|
|
407
|
+
bun run typecheck
|
|
408
|
+
bun run test
|
|
390
409
|
bun run build
|
|
391
410
|
bun run start
|
|
392
411
|
```
|
|
393
412
|
|
|
413
|
+
The build installs the app's locked dependencies and rebuilds the tracked
|
|
414
|
+
`dist/bundle.js` and `dist/journey.html` artifacts. Check app types with
|
|
415
|
+
`cd app && bunx tsc --noEmit`; see [worker validation](worker/README.md#local-dev)
|
|
416
|
+
for the worker typecheck, dry-run build, and local HTTP regression.
|
|
417
|
+
|
|
418
|
+
Dependabot uses the `bun` ecosystem for the root, app, and worker packages so
|
|
419
|
+
updates include their `bun.lock` files. CI verifies all three packages on pull
|
|
420
|
+
requests. Merging a PR updates source only: a version tag publishes to npm and
|
|
421
|
+
the MCP Registry, and the Cloudflare Worker requires a separate deployment.
|
|
422
|
+
|
|
394
423
|
Enable debug mode:
|
|
395
424
|
|
|
396
425
|
```bash
|
|
@@ -449,7 +478,41 @@ Contributions are welcome! Please feel free to submit issues or pull requests on
|
|
|
449
478
|
|
|
450
479
|
## Version
|
|
451
480
|
|
|
452
|
-
Current version: 0.
|
|
481
|
+
Current version: 0.8.1
|
|
482
|
+
|
|
483
|
+
### What's New in 0.8.1
|
|
484
|
+
|
|
485
|
+
- Updated dependencies and GitHub Actions, regenerated Bun lockfiles, and added
|
|
486
|
+
app and worker validation to CI.
|
|
487
|
+
- Updated vulnerable transitive dependencies across all three packages and added
|
|
488
|
+
dependency audits to CI. The release candidate passes all three Bun audits.
|
|
489
|
+
- Migrated the visualization to ext-apps 2 with its MCP client v2 and Zod 4
|
|
490
|
+
dependencies. The server transports remain on MCP SDK v1; the worker uses
|
|
491
|
+
the agents SDK's explicit compatibility handler and retains stateless JSON
|
|
492
|
+
responses.
|
|
493
|
+
|
|
494
|
+
### What's New in 0.8.0
|
|
495
|
+
|
|
496
|
+
- **Single source of truth**: domain logic, tool/server metadata, prompts, and the client parser now live in `src/shared/` and are imported by both the stdio entry (`index.ts`) and the Cloudflare Worker — no more local-vs-remote drift
|
|
497
|
+
- **High-level `McpServer` everywhere**: the local stdio server was migrated from the low-level `Server` API to `McpServer`, matching the Worker
|
|
498
|
+
- **MCP Prompts**: `contemplate` and `deep-inquiry` for guided contemplative sessions
|
|
499
|
+
- **Structured tool output**: tools now return `structuredContent` validated against an `outputSchema`, plus behavioral annotations (`readOnlyHint`, `idempotentHint`, `destructiveHint: false`, `openWorldHint: false`) and a server `instructions` field
|
|
500
|
+
- **Theme-aware, accessible UI**: the ext-apps journey visualization adapts to the host light/dark theme and is keyboard-accessible
|
|
501
|
+
- **Security & cleanup**: `@modelcontextprotocol/sdk` bumped to `^1.27.1`, `zod` added, `chalk` removed; the legacy Express SSE server (`server.ts`), the `express` deps, and the `Dockerfile` were removed; the repo moved to bun lockfiles. Added a vitest test suite (`tests/`) and a single-source version workflow (`src/shared/version.ts` + `bun run sync-version`)
|
|
502
|
+
- **Server icon & website**: `server.json` advertises the remote Worker (`remotes[]`), a `websiteUrl`, and icon `sizes`; the Worker advertises icons/website in the initialize handshake and serves the icon as same-origin bytes at `/icon.png`
|
|
503
|
+
|
|
504
|
+
### What's New in 0.7.0
|
|
505
|
+
|
|
506
|
+
- **Fully stateless Worker**: removed the Durable Object — the remote Worker now creates a fresh server per request and relies on the client-driven `previousJourney` parameter for journey continuity (eliminating accumulated SSE wall time)
|
|
507
|
+
|
|
508
|
+
### What's New in 0.6.0
|
|
509
|
+
|
|
510
|
+
- **Server icon**: added an icon to `server.json` and the Worker so MCP Registry and claude.ai Connectors display the lotus logo
|
|
511
|
+
- **Warmer UI** and (since reverted) experimental Durable Object session state
|
|
512
|
+
|
|
513
|
+
### What's New in 0.5.0
|
|
514
|
+
|
|
515
|
+
- **npm + MCP Registry publish**: hardened packaging and published to npm and the official MCP Registry
|
|
453
516
|
|
|
454
517
|
### What's New in 0.4.0
|
|
455
518
|
|
|
@@ -486,4 +549,4 @@ Current version: 0.4.0
|
|
|
486
549
|
- 🔄 **Dual Transport**: Maintains stdio support for npm/CLI users while adding HTTP for remote deployment
|
|
487
550
|
- 📦 **Updated SDK**: Upgraded to @modelcontextprotocol/sdk 1.20.1 with Streamable HTTP support
|
|
488
551
|
- 🪷 **New Logo**: Terminal-aesthetic lotus logo perfect for developer tools
|
|
489
|
-
- ⚡ **Session Management**: HTTP version includes full session management for stateful wisdom journeys
|
|
552
|
+
- ⚡ **Session Management**: HTTP version includes full session management for stateful wisdom journeys
|