Back to MCP Catalog

Personal Intelligence Framework MCP Server

Knowledge & MemoryTypeScript
A structured framework for AI-human interaction with filesystem, reasoning, and journaling capabilities
Available Tools

pwd

Print the current working directory within the workspace

cd

Change the current working directory within the workspace

read

Read the contents of a file in the workspace

write

Write content to a file in the workspace

mkdir

Create a new directory in the workspace

delete

Delete a file or directory in the workspace

move

Move a file or directory to a new location in the workspace

rename

Rename a file or directory in the workspace

reason

Create a structured space for developing connected insights

think

Create temporal spaces for contemplation and analysis

journal_create

Create a new journal entry to document developments

journal_read

Read existing journal entries to explore patterns

The Personal Intelligence Framework (PIF) creates a structured environment for meaningful development of understanding between humans and AI. Through organized tools and progressive interaction patterns, it establishes spaces for collaborative thinking, reasoning, and knowledge management. This implementation provides core capabilities including filesystem operations for context management, reasoning tools for structured thought development, and a journal system to maintain continuity across interactions. The framework is designed to work seamlessly across Windows, macOS, and Linux environments with automatic configuration detection.

Installation

Prerequisites

  • Node.js 18+ and npm
  • TypeScript 5.0+
  • Claude Desktop Client configured for custom servers

Setup Instructions

  1. Clone the repository

    git clone https://github.com/hungryrobot1/MCP-PIF
    cd MCP-PIF
    
  2. Install dependencies

    npm install
    
  3. Build the server

    npm run build
    
  4. Configure Claude Desktop Client

    • Locate your Claude Desktop Client configuration directory
    • Create or modify claude_desktop_config.json with the server configuration (see Installation section below)
    • Replace the path placeholders with your actual repository path
    • Restart the Claude Desktop Client
    • Select "mcp-pif" as your custom server
    • Start a new chat to begin using the server

Configuration Options

The server offers several configuration methods:

  • Automatic detection: The server will attempt to detect the appropriate workspace location
  • Environment variables:
    • Set MCP_WORKSPACE_ROOT to specify a custom workspace location
    • Set MCP_CONFIG with a JSON string of configuration options
  • Manual configuration: Edit src/config.ts to modify the default settings

Directory Structure

The server creates and manages the following structure in your configured workspace:

workspace/
├── home/
│   ├── meta/
│   │   └── journal/     # For storing journal entries
│   └── projects/        # For user projects

Basic Usage Examples

Creating structured thought patterns:

reason: {
    thoughts: [
        { content: "Initial observation" },
        {
            content: "Building on previous thought",
            relationType: "sequence",
            relationTo: 0
        }
    ]
}

Documenting development:

journal_create: {
    title: "Implementation Pattern",
    content: "Insights about development...",
    tags: ["development", "patterns"]
}

Troubleshooting

  • If manually specifying paths, use platform-appropriate separators (backslashes on Windows, forward slashes on macOS/Linux)
  • Check the Claude Desktop Client logs if connection fails
  • Verify your workspace directory exists and is writable
  • Make sure Node.js and TypeScript versions meet requirements

Related MCPs

Knowledge Graph Memory
Knowledge & MemoryTypeScript

A persistent memory system using a local knowledge graph

MemoryMesh
Knowledge & MemoryTypeScript

A knowledge graph server for structured memory persistence in AI models

Cognee
Knowledge & MemoryPython

Knowledge management and retrieval system with code graph capabilities

About Model Context Protocol

Model Context Protocol (MCP) allows AI models to access external tools and services, extending their capabilities beyond their training data.

Generate Cursor Documentation

Save time on coding by generating custom documentation and prompts for Cursor IDE.