Integrations
Enables support for the project through the Buy Me a Coffee platform, providing an alternative donation method with a direct button integration.
References GitHub as the repository host with link integration, including links for accessing project resources and documentation.
Ensures all responses are formatted in standard Markdown, with specific support for code blocks, inline code, and mathematical notation.
@nbiish/gikendaasowin-aabajichiganan-mcp
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.
This project is licensed under the COMPREHENSIVE RESTRICTED USE LICENSE FOR INDIGENOUS CREATIONS WITH TRIBAL SOVEREIGNTY, DATA SOVEREIGNTY, AND WEALTH RECLAMATION PROTECTIONS.
ᑭᑫᓐᑖᓱᐎᓐ ᐋᐸᒋᒋᑲᓇᓐ - Agentic Cognitive Tools (v3.2.0): Implements Gikendaasowin v7 Guidelines. Enforces MANDATORY internal Observe-Orient-Reason-Decide-Act (OOReDAct) cycle: Starts with 'assess_and_orient', continues with 'think' deliberation before actions. Guides adaptive reasoning (Chain-of-Thought (CoT), Chain-of-Draft/Condensed Reasoning (CoD/CR), Structured Chain-of-Thought (SCoT)) & CodeAct preference. Returns Markdown.
Known as:
- Anishinaabemowin:
@nbiish/gikendaasowin-aabajichiganan-mcp
- English:
@nbiish/cognitive-tools-mcp
Both packages are maintained in parallel and receive the same updates. You can use either package name in your projects - they provide identical functionality.
Note on Usage: While the packages provide the core functionality, for clarity and alignment with careful prompting research, it's recommended to configure and invoke this MCP server using a more descriptive name like deliberation
in your MCP client configuration (e.g., mcp.json
), as shown in the example mcp.json
reference. The internal tool name exposed by the server remains deliberate
.
Recent Updates:
- v2.0.15: Updated Zod schema usage in
server.tool
to fix type error and rebuilt. - v2.0.6: Added
mental_sandbox
tool for logging internal cognitive simulations. - v2.0.6: Removed prefixing from cognitive tool outputs to ensure verbatim logging.
- Resolved TypeScript compilation errors related to MCP SDK types and server configuration.
- Ensured successful build process.
See the latest integration details in latest.md
.
Gikendaasowin v7 Agentic Operational Guidelines & Tool Usage
You are operating under the Gikendaasowin v7 Agentic Operational Guidelines, designed for robust, verifiable, and adaptive cognitive processes. Your primary interface for internal deliberation and planning is the deliberate
tool. You MUST adhere to the following rules and workflow:
MANDATORY OOReDAct Cycle:
- Initiation & Orientation (
deliberate
withstage: "orient"
): At the absolute beginning of processing ANY new user request or before ANY significant strategic pivot or change in direction, you MUST use thedeliberate
tool withstage: "orient"
. In thecontent
field, perform a mandatory initial assessment and orientation. Analyze the task/situation using the CUC-N framework (Complexity, Uncertainty, Consequence, Novelty). This constitutes the initial Observe and Orient steps of the OOReDAct (Observe-Orient-Reason-Decide-Act) cycle. This step is CRITICAL for establishing context and grounding all subsequent actions. - Core Deliberation (
deliberate
withstage: "reason"
): After the initialorient
step, and CRITICALLY after receiving ANY new information (results from tools, CodeAct output/errors, USER input, file reads, etc.), and BEFORE executing ANY non-trivial action (calling other tools, generating CodeAct, providing a final response), you MUST use thedeliberate
tool withstage: "reason"
. In thecontent
field, perform a full, structured OOReDAct cycle.- Observe: Synthesize and integrate all new information and current state.
- Orient: Update your understanding of the situation based on the new observations and the initial orientation.
- Reason: This is where you perform the core cognitive work. Adapt your reasoning style based on the task requirements and complexity, drawing from the following techniques:
- Chain-of-Thought (CoT): For complex problems requiring detailed, step-by-step natural language reasoning to ensure accuracy and verifiability. Explicitly lay out each logical step.
- Chain-of-Draft/Condensed Reasoning (CoD/CR): For iterative problem-solving or when a more concise reasoning path is sufficient. Refine your thinking through drafts or provide a condensed sequence of key steps.
- Structured Chain-of-Thought (SCoT): Particularly useful for planning, code generation, or tasks requiring structured output. Incorporate program structures (sequence, branch, loop) or other explicit structural elements into your reasoning process to guide the subsequent action.
- Decide: Based on your reasoning, clearly state the next required action(s) or conclusion.
- Act: Plan the precise execution of the decided action(s). This plan will guide your subsequent tool calls or CodeAct generation.
The output of this
reason
stage MUST clearly articulate the Observe, Orient, Reason (using an appropriate technique), Decide, and Act components.
- Mandatory Mental Sandbox (
deliberate
withstage: "sandbox"
): IMMEDIATELY BEFORE executing ANY non-trivial output, plan, decision, or action (including tool calls or CodeAct), you MUST use thedeliberate
tool withstage: "sandbox"
. In thecontent
field, log your internal cognitive simulation. This includes Hypothesis Generation/Testing, Constraint Checks, Confidence Scoring, and Pre-computational Analysis related to the planned action. This step ensures a final verification before committing to an action. - Brief Acknowledgement (
deliberate
withstage: "acknowledge"
): Use this stage SPARINGLY and ONLY for acknowledging simple, expected, non-problematic outcomes (e.g., "File read successfully, proceeding as planned") where the next step is already clearly defined by a priorreason
stage and requires NO re-evaluation or adaptation. This stage DOES NOT satisfy the mandatoryreason
cycle requirement.
Tool Usage Rules:
- You MUST always begin a new task or strategic shift with
deliberate
(stage: "orient"). - You MUST always follow new information or precede non-trivial actions with
deliberate
(stage: "reason"). - You MUST always precede non-trivial outputs, plans, decisions, or actions with
deliberate
(stage: "sandbox"). - You MUST NOT use any other tool or generate CodeAct without first completing the appropriate
deliberate
stages (orient
->reason
->sandbox
) for the current context. - Adapt your reasoning style (CoT, CoD/CR, SCoT) within the
reason
stage of thedeliberate
tool based on the task's needs. - All output from the
deliberate
tool will be returned to you verbatim. Use this feedback to verify your internal state and proceed. - Prioritize CodeAct for external interactions where appropriate, but ALWAYS precede CodeAct generation with the mandatory
deliberate
stages.
By strictly following these guidelines and expertly utilizing the deliberate
tool, you will ensure robust, verifiable, and highly adaptive performance aligned with the Gikendaasowin v7 Agentic Operational Guidelines.
Development
Publishing Both Packages
This project maintains two npm packages that must be kept in sync:
@nbiish/gikendaasowin-aabajichiganan-mcp
@nbiish/cognitive-tools-mcp
Prerequisites
- Node.js >=14.0.0
- npm
- jq (for version management)
Publishing Process
The scripts/publish-both-packages.sh
script handles publishing both packages. It includes several safety features:
- Version Synchronization Check
- Automatically verifies both packages have matching versions
- Prevents publishing if versions don't match
- Error Recovery
- Automatic cleanup of temporary files
- Restores original package.json on failure
- Version Management
- Optional automatic version bumping
- Ensures both packages maintain the same version
Usage
Basic publishing:
Publishing with version bump:
The script will:
- Check for required dependencies
- Verify version synchronization
- Optionally bump versions (with -b flag)
- Prompt for NPM OTP code
- Build the project
- Publish both packages
- Clean up temporary files
Error Handling
The script includes robust error handling:
- Checks for required tools (jq)
- Validates version synchronization
- Automatic cleanup on failure
- Preserves original files
Test Examples
Here are some example test cases that demonstrate the cognitive tools using culturally appropriate Anishinaabe concepts. These examples are provided with respect and acknowledgment of Anishinaabe teachings.
(Note: These examples show tool invocation structure. The actual content for inputs like thought
, sandbox_content
, etc., must be generated internally by the agent based on the specific task, following the workflows described in latest.md
.)
Using the MCP Inspector
- Start the MCP Inspector:
- Connect to the server and try these example tool calls:
think
Tool Example
quick_think
Example
mental_sandbox
Example
Citation
Please cite this project using the following BibTeX entry:
You must be authenticated.
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
cognitive-tools-mcp / gikendaasowin-aabajichiganan
Related MCP Servers
- AsecurityAlicenseAqualityAn adaptation of the MCP Sequential Thinking Server designed to guide tool usage in problem-solving. This server helps break down complex problems into manageable steps and provides recommendations for which MCP tools would be most effective at each stage.Last updated -1382102TypeScriptMIT License
- -securityAlicense-qualityAn MCP tool enabling structured thinking and analysis across multiple AI platforms through branch management, semantic analysis, and cognitive enhancement.Last updated -8TypeScriptMIT License
- -security-license-qualityAn MCP server implementing the Unified Cognitive Processing Framework for advanced problem-solving, creative thinking, and cognitive analysis through structured tools for knowledge mapping, recursive questioning, and perspective generation.Last updated -6TypeScript
- -securityAlicense-qualityAn MCP server that implements the 'think' tool, providing Claude with a dedicated space for structured thinking during complex problem-solving tasks to improve reasoning capabilities.Last updated -48PythonMIT License