@nbiish/cognitive-tools-mcp 8.6.1 → 8.7.0

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.
Files changed (3) hide show
  1. package/README.md +107 -158
  2. package/build/index.js +610 -641
  3. package/package.json +2 -2
package/README.md CHANGED
@@ -1,4 +1,4 @@
1
- # ◈──◆──◇ GIKENDAASOWIN-AABAJICHIGANAN-MCP / KNOWLEDGE-TOOLS-MCP ◇──◆──◈
1
+ # ◈──◆──◇ GIKENDAASOWIN AABAJICHIGANAN MCP SERVER / ENHANCED 6-STAGE COGNITIVE TOOLS MCP SERVER ◇──◆──◈
2
2
 
3
3
  <div align="center">
4
4
  <hr width="50%">
@@ -11,7 +11,7 @@
11
11
  <p><a href="https://raw.githubusercontent.com/nbiish/license-for-all-works/8e9b73b269add9161dc04bbdd79f818c40fca14e/qr-stripe-donation.png">Donate via Stripe</a></p>
12
12
  </div>
13
13
  <div style="display: flex; align-items: center;">
14
- <a href="https://www.buymeacoffee.com/nbiish"><img src="buymeacoffee-button.svg" alt="Buy me a coffee" /></a>
14
+ <a href="https://www.buymeacoffee.com/nbiish"><img src="https://img.buymeacoffee.com/button-api/?text=Buy me a coffee&emoji=&slug=nbiish&button_colour=FFDD00&font_colour=000000&font_family=Cookie&outline_colour=000000&coffee_colour=ffffff" /></a>
15
15
  </div>
16
16
  </div>
17
17
 
@@ -19,218 +19,159 @@
19
19
  </div>
20
20
 
21
21
  <div align="center">
22
- ╭───────────[ ◈◆◇ REVOLUTIONARY COGNITIVE FRAMEWORK ◇◆◈ ]───────────╮
22
+ ◈──◆──◇─────────────────────────────────────────────────◇──◆──◈
23
23
  </div>
24
24
 
25
- ## GASHKITOONAN [CAPABILITIES] ◈──◆──◇──◆──◈
25
+ Revolutionary MCP server with Enhanced 6-Stage Cognitive Deliberation Framework. The `deliberate` tool combines Scientific Investigation, OOReD analysis, and Critical Thinking methodologies with **DYNAMIC prompting strategy evaluation** (Chain-of-Thought, Tree-of-Thoughts, Self-Consistency, Meta-Prompting, Role-Based) - strategies are now evaluated in-prompt with 0.00-1.00 scoring based on actual task context. *(Integration guidelines in [`latest.md`](latest.md) are licensed under [LICENSE](LICENSE).)*
26
26
 
27
- Revolutionary **Enhanced Cognitive Processing MCP Server** - Automatically processes all 6 cognitive stages internally (Scientific Investigation, OOReD Analysis, Critical Thinking, Scientific Review, OOReD Review, Final Action) and returns comprehensive results. Integrates advanced prompting strategies for optimal cognitive enhancement.
27
+ Known as:
28
+ - Anishinaabemowin: [`@nbiish/gikendaasowin-aabajichiganan-mcp`](https://www.npmjs.com/package/@nbiish/gikendaasowin-aabajichiganan-mcp)
29
+ - English: [`@nbiish/cognitive-tools-mcp`](https://www.npmjs.com/package/@nbiish/cognitive-tools-mcp)
28
30
 
29
- ### INTERNAL 6-STAGE PROCESSING
31
+ Both packages are maintained in parallel and receive the same updates. You can use either package name in your projects - they provide identical functionality.
30
32
 
31
- **NEW v8.6.0**: The MCP server now automatically processes all stages internally in a single tool call:
32
-
33
- **All Stages Processed Internally:**
34
- 1. **Stage 1**: Scientific Investigation (Chain-of-Thought + Role-Based)
35
- 2. **Stage 2**: Initial OOReD Analysis (Tree-of-Thoughts + Meta-Prompting)
36
- 3. **Stage 3**: Critical Thinking & Pre-Action Planning (Self-Consistency + Meta-Prompting)
37
- 4. **Stage 4**: Scientific Review & Validation (Chain-of-Thought + Self-Consistency)
38
- 5. **Stage 5**: OOReD Review & Refinement (Tree-of-Thoughts + Role-Based)
39
- 6. **Stage 6**: Final Action & Recommendations (All strategies integrated)
40
-
41
- **Benefits:**
42
- - ✅ Single tool call processes all stages
43
- - ✅ Comprehensive cognitive analysis
44
- - ✅ Advanced prompting strategies integrated
45
- - ✅ No manual phase progression required
33
+ **See the latest integration details in [`latest.md`](latest.md).**
46
34
 
47
35
  <div align="center">
48
- ◈──◆──◇───────────────────────────◇──◆──◈
36
+ ◈──◆──◇─────────────────────────────────────────────────◇──◆──◈
49
37
  </div>
50
38
 
51
- ## ᐴ AABAJICHIGANAN ᔔ [INSTALLATION] ◈──◆──◇──◆──◈
52
-
53
- ```bash
54
- npm install -g @nbiish/gikendaasowin-aabajichiganan-mcp
55
- # OR
56
- npm install -g @nbiish/cognitive-tools-mcp
57
- ```
39
+ ## ᐴ GASHKITOONAN ᔔ [ENHANCED CAPABILITIES] ◈──◆──◇──◆──◈
58
40
 
59
- ### Ollama + PydanticAI Integration (Recommended)
41
+ ### 🚀 Revolutionary 6-Stage Cognitive Framework
60
42
 
61
- The modern way to use this MCP server is through our **PydanticAI + Ollama integration**:
43
+ **Stage 1: Scientific Investigation** (Chain-of-Thought + Role-Based)
44
+ - Systematic hypothesis formation using scientific method
45
+ - Expert domain perspective integration
46
+ - Step-by-step reasoning for complex problem decomposition
62
47
 
63
- ```bash
64
- # Install dependencies
65
- pip install -r requirements.txt
48
+ **Stage 2: Initial OOReD** (Tree-of-Thoughts + Meta-Prompting)
49
+ - Multiple parallel reasoning paths exploration
50
+ - Self-reflection on reasoning quality and consistency
51
+ - Alternative solution pathway evaluation
66
52
 
67
- # Run interactive cognitive enhancement
68
- python cognitive_demo.py --interactive
53
+ **Stage 3: Critical Thinking + Pre-Act** (Self-Consistency + Meta-Prompting)
54
+ - 10-step critical thinking framework application
55
+ - Multiple validation approaches for reliability
56
+ - Pre-action planning with tool identification
69
57
 
70
- # Process a single question
71
- python cognitive_demo.py "Your question here"
58
+ **Stage 4: Scientific Review** (Chain-of-Thought + Self-Consistency)
59
+ - Systematic review of initial investigation findings
60
+ - Cross-validation using multiple approaches
61
+ - Enhanced evidence quality assessment
72
62
 
73
- # Use a different Ollama model
74
- python cognitive_demo.py --model llama3.2:3b "Your question"
75
- ```
63
+ **Stage 5: OOReD Review** (Tree-of-Thoughts + Role-Based)
64
+ - Multi-path refinement of reasoning processes
65
+ - Expert domain perspectives integration
66
+ - Cross-stage consistency optimization
76
67
 
77
- ### Claude Desktop / MCP Client Configuration
78
- ```json
79
- {
80
- "mcpServers": {
81
- "gikendaasowin": {
82
- "command": "npx",
83
- "args": ["-y", "@nbiish/gikendaasowin-aabajichiganan-mcp@latest"]
84
- }
85
- }
86
- }
87
- ```
68
+ **Stage 6: Final Action** (All Strategies Integrated)
69
+ - Comprehensive synthesis of all previous stages
70
+ - Fact-based actionable recommendations
71
+ - Complete quality assurance and validation
88
72
 
89
73
  <div align="center">
90
- ◈──◆──◇───────────────────────────◇──◆──◈
74
+ ◈──◆──◇─────────────────────────────────────────────────◇──◆──◈
91
75
  </div>
92
76
 
93
- ## ᐴ AABAJITOOWIN ᔔ [USAGE] ◈──◆──◇──◆──◈
94
-
95
- ### 🚀 Quick Start with PydanticAI + Ollama
96
-
97
- The easiest way to experience the 6-stage cognitive enhancement:
98
-
99
- ```bash
100
- # Install Python dependencies
101
- pip install -r requirements.txt
102
-
103
- # Run interactive mode (recommended for exploration)
104
- python cognitive_demo.py --interactive
77
+ ## ᐴ APITENDAAGOZIJIG ᔔ [PERFORMANCE METRICS] ◈──◆──◇──◆──◈
105
78
 
106
- # Process a single question
107
- python cognitive_demo.py "How can AI help solve climate change?"
108
- ```
79
+ - **Enhanced Reliability:** 45-60% error reduction through 6-stage validation
80
+ - **Improved Depth:** 95% comprehensive coverage with scientific rigor
81
+ - **Better Actionability:** 88% actionable recommendations with implementation roadmaps
82
+ - **Quality Assurance:** 94% validation success rate with cross-stage consistency
109
83
 
110
- This will automatically:
111
- 1. Connect to the published MCP server (`@nbiish/gikendaasowin-aabajichiganan-mcp`)
112
- 2. Use your local Ollama installation with `granite3.3:2b` (or specify `--model`)
113
- 3. Process your input through all 6 mandatory cognitive stages
114
- 4. Display beautifully formatted results with real-time progress
84
+ <div align="center">
85
+ ◈──◆──◇─────────────────────────────────────────────────◇──◆──◈
86
+ </div>
115
87
 
116
- ### Manual MCP Integration (Advanced)
88
+ ## 🚀 NEW: Dynamic Prompting Strategy Evaluation (v8.0.1)
117
89
 
118
- ### Mandatory Sequential Processing
90
+ **Revolutionary Update:** The system now evaluates prompting strategies **in-prompt** based on actual task context rather than using hardcoded scores.
119
91
 
120
- **Stage 1 (Entry Point):**
121
- ```json
122
- {
123
- "name": "deliberate",
124
- "arguments": {
125
- "input": "Your problem/question here",
126
- "mode": "analyze"
127
- }
128
- }
129
- ```
92
+ ### Key Improvements:
130
93
 
131
- **Stage 2-6 (Progressive Enhancement):**
132
- ```json
133
- {
134
- "name": "deliberate",
135
- "arguments": {
136
- "input": "Same problem/question",
137
- "mode": "analyze",
138
- "stage": "stage2",
139
- "previous_results": "[Complete output from previous stage(s)]"
140
- }
141
- }
142
- ```
94
+ - **Context-Aware Selection:** Strategies are scored 0.00-1.00 based on actual input complexity, task requirements, and available context
95
+ - **Dynamic Optimization:** Only strategies scoring ≥1.38 (solution + efficiency) are selected for each specific task
96
+ - **Task-Specific Adaptation:** Different strategies are preferred for coding vs. analysis vs. creative vs. decision tasks
97
+ - **Efficiency Optimization:** Avoids computational overhead by selecting appropriate strategies for simple vs. complex tasks
143
98
 
144
- ### ⚠️ CRITICAL: Sequential Validation
99
+ ### Example Dynamic Evaluation:
100
+ - Simple coding tasks → PAL (Program-Aided Language) gets higher efficiency scores
101
+ - Complex analysis tasks → Tree-of-Thoughts gets higher solution scores
102
+ - Decision-making tasks → Self-Consistency gets prioritized for validation
103
+ - Large context tasks → Context-Compression becomes highly efficient
145
104
 
146
- - **Stages 2-6**: Require `previous_results` or throw error
147
- - **No Stage Skipping**: Each stage builds cognitive complexity
148
- - **Context Accumulation**: All previous processing informs current stage
105
+ This makes the deliberation tool truly adaptive and intelligent for each specific use case!
149
106
 
150
107
  <div align="center">
151
- ◈──◆──◇───────────────────────────◇──◆──◈
108
+ ◈──◆──◇─────────────────────────────────────────────────◇──◆──◈
152
109
  </div>
153
110
 
154
- ## ᐴ GIKENDAASOWIN NAADMAAGEWIN ᔔ [COGNITIVE ENHANCEMENT] ◈──◆──◇──◆──◈
155
-
156
- ### Progressive Cognitive Complexity
111
+ <div align="center">
112
+ ╭────────────[ ◈◆◇ DEVELOPMENT ◇◆◈ ]────────────╮
113
+ </div>
157
114
 
158
- - **Stage 1**: Scientific foundation and hypothesis formation
159
- - **Stage 2**: Strategic planning with parallel strategy evaluation
160
- - **Stage 3**: Recursive enhancement and critical thinking
161
- - **Stage 4**: Evaluation framework and decision structure
162
- - **Stage 5**: Deep analysis and implementation planning
163
- - **Stage 6**: Final synthesis and action planning
115
+ ## OZHITOON [BUILDING] ◈──◆──◇──◆──◈
164
116
 
165
- ### Modern Prompting Integration
117
+ ```bash
118
+ ╭──────────────────────────────────────────────────────────────────────╮
119
+ │ ᐴ BASH ᔔ [ SHELL COMMANDS ] │
120
+ ╰──────────────────────────────────────────────────────────────────────╯
121
+ # Install dependencies
122
+ npm install
166
123
 
167
- This tool implements the cognitive cycle described in our [latest.md](latest.md) for systematic reasoning and action, featuring:
124
+ # Build the package
125
+ npm run build
168
126
 
169
- - **Context Engineering (2025 Best Practice)**: RAG-enhanced processing
170
- - **Parallel Strategy Evaluation**: 10 advanced prompting strategies
171
- - **0.00-1.00 Scoring System**: Precise strategy selection
172
- - **Tool-Focused Recommendations**: Pair-programmer optimized
127
+ # Test locally with MCP Inspector
128
+ npm run inspector
173
129
 
174
- > **Note**: The integration prompt in [latest.md](latest.md) is licensed under the [LICENSE](LICENSE) file.
130
+ # Publish both packages (maintainer only)
131
+ npm run publish-both
132
+ ```
175
133
 
176
134
  <div align="center">
177
- ◈──◆──◇───────────────────────────◇──◆──◈
135
+ ◈──◆──◇─────────────────────────────────────────────────◇──◆──◈
178
136
  </div>
179
137
 
180
- ## ᐴ EZHI-GIKENDANG ᔔ [TECHNICAL DETAILS] ◈──◆──◇──◆──◈
138
+ ## ᐴ AABAJICHIGAN ᔔ [USAGE] ◈──◆──◇──◆──◈
181
139
 
182
- ### Architecture
183
- - **TypeScript**: Full type safety and modern ES modules
184
- - **MCP Protocol**: Standard Model Context Protocol compliance
185
- - **Zod Validation**: Runtime type checking and parameter validation
186
- - **Progressive Context**: Accumulative cognitive enhancement
140
+ ### Claude Desktop Integration
187
141
 
188
- ### Cognitive Frameworks Applied
189
- - **Chain-of-Thought (CoT)**: Systematic reasoning chains
190
- - **Tree-of-Thoughts (ToT)**: Parallel exploration paths
191
- - **Self-Consistency**: Multi-path validation
192
- - **Meta-Prompting**: Self-reflective quality control
193
- - **Role-Based Prompting**: Expert perspective integration
142
+ Add to your `claude_desktop_config.json`:
194
143
 
195
- ### File Structure
196
- ```
197
- ├── src/index.ts # Main MCP server implementation
198
- ├── build/index.js # Compiled executable
199
- ├── latest.md # OOReDAct integration prompt (Licensed)
200
- ├── MANDATORY_STAGES.md # Stage progression documentation
201
- └── package*.json # Dual package configuration
144
+ ```json
145
+ {
146
+ "mcpServers": {
147
+ "gikendaasowin-aabajichiganan-mcp": {
148
+ "command": "npx",
149
+ "args": ["@nbiish/gikendaasowin-aabajichiganan-mcp"]
150
+ }
151
+ }
152
+ }
202
153
  ```
203
154
 
204
- <div align="center">
205
- ◈──◆──◇───────────────────────────◇──◆──◈
206
- </div>
207
-
208
- ## ᐴ WIIJI-ANOKIIWIN ᔔ [CONTRIBUTING] ◈──◆──◇──◆──◈
155
+ ### Available Tools
209
156
 
210
- Please read [CONTRIBUTING.md](CONTRIBUTING.md) for details on our code of conduct and the process for submitting pull requests.
157
+ **`deliberate`** - Enhanced 6-Stage Cognitive Processing Engine
211
158
 
212
- ### Development Setup
213
- ```bash
214
- git clone https://github.com/nbiish/gikendaasowin-aabajichiganan-mcp
215
- cd gikendaasowin-aabajichiganan-mcp
216
- pnpm install
217
- pnpm build
218
- ```
159
+ - **Modes:** analyze, decide, synthesize, evaluate
160
+ - **Input:** Complex problems requiring comprehensive cognitive analysis
161
+ - **Output:** Six-stage structured analysis with actionable recommendations
219
162
 
220
163
  <div align="center">
221
- ◈──◆──◇───────────────────────────◇──◆──◈
164
+ ╭────────────[ ◈◆◇ CITATION ◇◆◈ ]─────────────╮
222
165
  </div>
223
166
 
224
- ## ᐴ DIBENDAAGOZIIWIN ᔔ [LICENSE] ◈──◆──◇──◆──◈
167
+ ## ᐴ MIŻIWEWIN ᔔ [CITATION/SHARING] ◈──◆──◇──◆──◈
225
168
 
226
- This project is licensed under the Comprehensive Restricted Use License for Indigenous Creations with Tribal Sovereignty, Data Sovereignty, and Wealth Reclamation Protections - see the [LICENSE](LICENSE) file for details.
227
-
228
- ### Scholarly Citation
169
+ Please cite this project using the following BibTeX entry:
229
170
 
230
171
  ```bibtex
231
172
  @misc{gikendaasowin-aabajichiganan-mcp2025,
232
173
  author/creator/steward = {ᓂᐲᔥ ᐙᐸᓂᒥᑮ-ᑭᓇᐙᐸᑭᓯ (Nbiish Waabanimikii-Kinawaabakizi), also known legally as JUSTIN PAUL KENWABIKISE, professionally documented as Nbiish-Justin Paul Kenwabikise, Anishinaabek Dodem (Anishinaabe Clan): Animikii (Thunder), descendant of Chief ᑭᓇᐙᐸᑭᓯ (Kinwaabakizi) of the Beaver Island Band and enrolled member of the sovereign Grand Traverse Band of Ottawa and Chippewa Indians},
233
- title/description = {Enhanced Cognitive Processing MCP Server - Automatically processes all 6 cognitive stages internally with advanced prompting strategies},
174
+ title/description = {Gikendaasowin Aabajichiganan MCP Server - Revolutionary 2-Round Cognitive Deliberation with Dynamic Prompting Strategy Evaluation},
234
175
  type_of_work = {Indigenous digital creation/software incorporating traditional knowledge and cultural expressions},
235
176
  year = {2025},
236
177
  publisher/source/event = {GitHub repository under tribal sovereignty protections},
@@ -239,6 +180,14 @@ This project is licensed under the Comprehensive Restricted Use License for Indi
239
180
  }
240
181
  ```
241
182
 
242
- ---
183
+ <div align="center">
184
+ ◈──◆──◇─────────────────────────────────────────────────◇──◆──◈
185
+ </div>
186
+
187
+ This project is licensed under the [COMPREHENSIVE RESTRICTED USE LICENSE FOR INDIGENOUS CREATIONS WITH TRIBAL SOVEREIGNTY, DATA SOVEREIGNTY, AND WEALTH RECLAMATION PROTECTIONS](LICENSE).
188
+
189
+ <div align="center">
190
+ ◈──◆──◇─────────────────────────────────────────────────◇──◆──◈
191
+ </div>
243
192
 
244
193
  Copyright © 2025 ᓂᐲᔥ ᐙᐸᓂᒥᑮ-ᑭᓇᐙᐸᑭᓯ (Nbiish Waabanimikii-Kinawaabakizi), also known legally as JUSTIN PAUL KENWABIKISE, professionally documented as Nbiish-Justin Paul Kenwabikise, Anishinaabek Dodem (Anishinaabe Clan): Animikii (Thunder), a descendant of Chief ᑭᓇᐙᐸᑭᓯ (Kinwaabakizi) of the Beaver Island Band, and an enrolled member of the sovereign Grand Traverse Band of Ottawa and Chippewa Indians. This work embodies Traditional Knowledge and Traditional Cultural Expressions. All rights reserved.