deepthinking-mcp 5.0.1 → 6.1.0
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 +19 -5
- package/dist/index.js +1773 -86
- package/dist/index.js.map +1 -1
- package/package.json +6 -3
package/README.md
CHANGED
|
@@ -4,11 +4,11 @@
|
|
|
4
4
|
[](https://opensource.org/licenses/MIT)
|
|
5
5
|
[](https://modelcontextprotocol.io)
|
|
6
6
|
|
|
7
|
-
A comprehensive Model Context Protocol (MCP) server featuring **
|
|
7
|
+
A comprehensive Model Context Protocol (MCP) server featuring **21 advanced reasoning modes** including meta-reasoning for strategic oversight, with intelligent mode recommendation, taxonomy-based classification, enterprise security, and production-ready features for complex problem-solving, analysis, and decision-making.
|
|
8
8
|
|
|
9
|
-
> 📋 **Latest Release**:
|
|
9
|
+
> 📋 **Latest Release**: v6.0.0 - See [CHANGELOG](CHANGELOG.md) for updates and improvements.
|
|
10
10
|
>
|
|
11
|
-
> 🎉 **New in
|
|
11
|
+
> 🎉 **New in v6.0.0**: Meta-Reasoning mode for strategic oversight! Monitor reasoning effectiveness, get adaptive mode-switching recommendations, and assess quality metrics across 6 dimensions.
|
|
12
12
|
|
|
13
13
|
## Table of Contents
|
|
14
14
|
|
|
@@ -24,10 +24,12 @@ A comprehensive Model Context Protocol (MCP) server featuring **18 advanced reas
|
|
|
24
24
|
|
|
25
25
|
## Features
|
|
26
26
|
|
|
27
|
-
- **
|
|
27
|
+
- **21 Specialized Reasoning Modes** - From sequential thinking to game theory, formal logic, and meta-reasoning
|
|
28
|
+
- **Meta-Reasoning (NEW!)** - Strategic oversight that monitors effectiveness, recommends mode switches, and assesses quality
|
|
29
|
+
- **Adaptive Mode Switching** - Automatic evaluation-based mode switching when effectiveness drops below thresholds
|
|
28
30
|
- **Intelligent Mode Recommendation** - Automatic mode selection based on problem characteristics
|
|
29
31
|
- **Taxonomy Classifier** - 110+ reasoning types across 12 categories for intelligent task classification
|
|
30
|
-
- **Visual Exports** - Generate Mermaid diagrams, DOT graphs, ASCII art, and LaTeX documents
|
|
32
|
+
- **Visual Exports** - Generate Mermaid diagrams, DOT graphs, ASCII art, and LaTeX documents with meta-insights
|
|
31
33
|
- **Production-Ready** - Search engine, templates, batch processing, caching, backup/restore
|
|
32
34
|
- **Enterprise Security** - Input validation (Zod), rate limiting, path sanitization, PII redaction
|
|
33
35
|
- **High Performance** - LRU caching with auto-eviction, async I/O, 4-5x validation speedups
|
|
@@ -225,6 +227,18 @@ mode: 'first-principles'
|
|
|
225
227
|
// Use for: Fundamental analysis, conceptual understanding, basic truths
|
|
226
228
|
```
|
|
227
229
|
|
|
230
|
+
#### Meta-Reasoning ⭐ NEW
|
|
231
|
+
Strategic oversight of reasoning process - monitors effectiveness, recommends mode switches, assesses quality.
|
|
232
|
+
|
|
233
|
+
```typescript
|
|
234
|
+
mode: 'metareasoning'
|
|
235
|
+
// Use for: Strategy evaluation, adaptive mode switching, quality assessment
|
|
236
|
+
// Metrics: Effectiveness, Efficiency, Confidence, Quality (6 dimensions)
|
|
237
|
+
// Auto-switches at effectiveness < 0.3
|
|
238
|
+
```
|
|
239
|
+
|
|
240
|
+
See [full documentation](docs/modes/METAREASONING.md) for detailed usage.
|
|
241
|
+
|
|
228
242
|
#### Systems Thinking
|
|
229
243
|
Holistic analysis of complex systems, feedback loops, and emergence.
|
|
230
244
|
|