deepthinking-mcp 2.3.0 → 2.4.0
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 +54 -4
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -1,10 +1,10 @@
|
|
|
1
|
-
# DeepThinking MCP v2.
|
|
1
|
+
# DeepThinking MCP v2.4
|
|
2
2
|
|
|
3
|
-
A comprehensive Model Context Protocol (MCP) server featuring **13 advanced reasoning modes** for complex problem-solving, analysis, and decision-making.
|
|
3
|
+
A comprehensive Model Context Protocol (MCP) server featuring **13 advanced reasoning modes** with intelligent mode recommendation for complex problem-solving, analysis, and decision-making.
|
|
4
4
|
|
|
5
5
|
## Overview
|
|
6
6
|
|
|
7
|
-
DeepThinking MCP v2.
|
|
7
|
+
DeepThinking MCP v2.4 provides a complete toolkit for structured reasoning with 13 specialized modes and an intelligent recommendation system:
|
|
8
8
|
|
|
9
9
|
### Core Modes
|
|
10
10
|
- **Sequential**: Iterative refinement with revision capabilities
|
|
@@ -26,7 +26,7 @@ n### Phase 3 Modes (v2.3+)
|
|
|
26
26
|
|
|
27
27
|
## Features
|
|
28
28
|
|
|
29
|
-
###
|
|
29
|
+
### 13 Specialized Reasoning Modes
|
|
30
30
|
|
|
31
31
|
#### Core Modes
|
|
32
32
|
- **Sequential**: Iterative refinement with revision capabilities and branching
|
|
@@ -66,6 +66,13 @@ n#### Phase 3 Reasoning Modes (v2.3+)
|
|
|
66
66
|
- Mode switching during problem-solving
|
|
67
67
|
- Export to multiple formats (Markdown, LaTeX, JSON)
|
|
68
68
|
|
|
69
|
+
### Mode Recommendation System (v2.4)
|
|
70
|
+
- **Intelligent Mode Selection**: Automatically recommends the best reasoning modes based on problem characteristics
|
|
71
|
+
- **Combination Suggestions**: Identifies synergistic mode combinations for complex problems
|
|
72
|
+
- **Quick Recommendations**: Simple problem-type based recommendations
|
|
73
|
+
- **Problem Characteristics Analysis**: Analyzes domain, complexity, uncertainty, time-dependence, and more
|
|
74
|
+
- **Ranked Recommendations**: Returns modes sorted by suitability score with detailed reasoning
|
|
75
|
+
|
|
69
76
|
## Installation
|
|
70
77
|
|
|
71
78
|
```bash
|
|
@@ -117,6 +124,49 @@ Use deepthinking to solve this complex problem...
|
|
|
117
124
|
|
|
118
125
|
The hybrid mode automatically selects the best features from each mode.
|
|
119
126
|
|
|
127
|
+
### Mode Recommendations (v2.4)
|
|
128
|
+
|
|
129
|
+
The recommendation system helps you choose the best reasoning mode for your problem:
|
|
130
|
+
|
|
131
|
+
```
|
|
132
|
+
What mode should I use for debugging this application?
|
|
133
|
+
```
|
|
134
|
+
|
|
135
|
+
Returns: **Abductive mode** - Perfect for hypothesis generation and root cause analysis.
|
|
136
|
+
|
|
137
|
+
```
|
|
138
|
+
I need to analyze a competitive business scenario with multiple players. What modes should I use?
|
|
139
|
+
```
|
|
140
|
+
|
|
141
|
+
Returns: **Game Theory mode** for strategic analysis, potentially combined with **Counterfactual mode** for scenario exploration.
|
|
142
|
+
|
|
143
|
+
#### Problem Characteristics
|
|
144
|
+
|
|
145
|
+
The recommender analyzes:
|
|
146
|
+
- **Domain**: General, mathematics, physics, engineering, etc.
|
|
147
|
+
- **Complexity**: Low, medium, or high
|
|
148
|
+
- **Uncertainty**: How much unknown information exists
|
|
149
|
+
- **Time-dependent**: Whether events occur over time
|
|
150
|
+
- **Multi-agent**: Whether multiple actors interact strategically
|
|
151
|
+
- **Requires proof**: Whether formal mathematical proof is needed
|
|
152
|
+
- **Requires quantification**: Whether probabilities or measurements are needed
|
|
153
|
+
- **Incomplete information**: Whether data gaps exist
|
|
154
|
+
- **Requires explanation**: Whether understanding "why" is important
|
|
155
|
+
- **Has alternatives**: Whether alternative scenarios should be explored
|
|
156
|
+
|
|
157
|
+
#### Quick Recommendations
|
|
158
|
+
|
|
159
|
+
For simple cases, use problem-type keywords:
|
|
160
|
+
- `debugging` → Abductive mode
|
|
161
|
+
- `proof` → Mathematics mode
|
|
162
|
+
- `timeline` → Temporal mode
|
|
163
|
+
- `strategy` → Game Theory mode
|
|
164
|
+
- `uncertainty` → Evidential mode
|
|
165
|
+
- `causality` → Causal mode
|
|
166
|
+
- `probability` → Bayesian mode
|
|
167
|
+
- `what-if` → Counterfactual mode
|
|
168
|
+
|
|
169
|
+
|
|
120
170
|
## Tool Parameters
|
|
121
171
|
|
|
122
172
|
### Core Parameters
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "deepthinking-mcp",
|
|
3
|
-
"version": "2.
|
|
3
|
+
"version": "2.4.0",
|
|
4
4
|
"description": "Comprehensive MCP server with 10 advanced reasoning modes: Sequential, Shannon, Mathematics, Physics, Hybrid, Abductive, Causal, Bayesian, Counterfactual, and Analogical reasoning",
|
|
5
5
|
"author": "Daniel Simon Jr.",
|
|
6
6
|
"license": "MIT",
|