
pct-mcp-server
Personal Context Technology for AI Personalization MCP server
3 years
Works with Finder
1
Github Watches
0
Github Forks
0
Github Stars
Personal Context Technology MCP Server
This repository implements a server for Personal Context Technology (PCT) using the Model Context Protocol (MCP). It enables AI assistants like Claude to access and update your personalized context data, creating persistent memory between sessions.
What is Personal Context Technology?
Personal Context Technology allows you to structure and manage personal data that AI assistants can use to provide more personalized and relevant responses. With PCT:
- Your context is preserved between AI sessions
- You control where your data is stored (locally, cloud, etc.)
- You define explicit instructions for how AI systems should use your data
- You can update context as your preferences and situation change
Features
- Persistent Context Storage: Store your preferences, goals, learning style, and other personal information
- Privacy Controls: Instruction block defines which information is private/public
- Section-based Access: Access full context or individual sections
- Context Updates: Update specific fields via the updateContext tool
- Version Tracking: Maintain history of context changes
Demo
Watch the Personal Context Technology MCP Server in action:
The demo shows how to:
- Access personal context data using the MCP tool
- Update context information using the updateContext tool
- See how Claude's responses improve with personalized context
Installation
Prerequisites
- Node.js (v16+)
- npm (included with Node.js)
Setup Instructions
- Clone the repository
git clone https://github.com/mikhashev/pct-mcp-server.git
cd pct-mcp-server
- Install dependencies
npm install
- Build the server
npm run build
- Start the server
npm start
Connecting to Claude Desktop
To use this server with Claude Desktop:
Windows
- Open Claude Desktop
- Navigate to Settings > Developer > Edit Config
- This will open
%AppData%\Claude Desktop\
directory - Create or edit
claude_desktop_config.json
with the following content:
{
"mcpServers": {
"personal-context-server": {
"command": "node",
"args": ["PATH_TO_YOUR_PROJECT/pct-mcp-server/dist/index.js"],
"env": {}
}
}
}
Replace PATH_TO_YOUR_PROJECT
with the actual path to your project.
macOS
- Open Claude Desktop
- Navigate to Settings > Developer > Edit Config
- This will open
~/Library/Application Support/Claude Desktop/
directory - Create or edit
claude_desktop_config.json
with the following content:
{
"mcpServers": {
"personal-context-server": {
"command": "node",
"args": ["/path/to/your/project/pct-mcp-server/dist/index.js"],
"env": {}
}
}
}
Linux
- Open Claude Desktop
- Navigate to Settings > Developer > Edit Config
- This will open
~/.config/Claude Desktop/
directory - Create or edit
claude_desktop_config.json
with the following content:
{
"mcpServers": {
"personal-context-server": {
"command": "node",
"args": ["/path/to/your/project/pct-mcp-server/dist/index.js"],
"env": {}
}
}
}
Using the Personal Context Server
With Claude Desktop
- Start your PCT MCP server using
npm start
- Restart Claude Desktop (if needed)
- In Claude, click the MCP tool icon (wrench/tool icon) in the input field
- You'll see "personal-context-server" with available tools and resources:
- Resources: Access your context data (full context or by section)
- Tools: Update specific fields in your context
Accessing Context Data
Claude can access your personal context data in two ways:
- Full Context: Select "All Sections" to give Claude access to your entire personal context
- Section-based: Select specific sections (basic_info, preferences, etc.) to share only certain parts of your context
Example prompt: "Using my context data, recommend some learning resources that would match my learning style."
Updating Context Data
You can update your personal context using the updateContext tool:
Example prompt: "Update my learning_style in preferences to 'visual and hands-on' because I've found I learn better with practical examples."
Customizing Your Context
The default personal context includes:
- basic_info: Name, location, etc.
- preferences: Communication style, learning preferences, etc.
- instruction: Rules for how AI should use and update your context
- metadata: Version tracking, update history
You can modify the default structure by editing the DEFAULT_CONTEXT
object in src/storage/contextStorage.ts
.
Or just replace update file data [PATH_TO_YOUR_PROJECT/pct-mcp-server/data/personal_context.json] from template data in repo (https://github.com/mikhashev/personal-context-manager/blob/main/use-cases/self-education/personal_context_self_education_template.json) or another one.
Project Structure
pct-mcp-server/
├── .git/ # Git repository data
├── .gitignore # Git ignore rules
├── LICENSE # License file
├── README.md # Project documentation
├── package-lock.json # Lock file for npm dependencies
├── package.json # Project configuration and dependencies
├── tsconfig.json # TypeScript configuration
└── src/ # Source code
├── index.ts # Main application entry point
├── resources/ # MCP resources implementation
│ └── personalContext.ts # Personal context resource
├── storage/ # Storage implementation
│ └── contextStorage.ts # Context storage functionality
├── tools/ # MCP tools implementation
│ ├── contextSuggestion.ts # Context suggestion tool
│ └── updateContext.ts # Update context tool
└── utils/ # Utility functions
└── instructionHandler.ts # Instruction handling logic
# Generated directories (not in repository)
# ----------------------------------------
# dist/ # Compiled JavaScript files (gitignored)
# node_modules/ # Dependencies (gitignored)
# data/ # User data (gitignored or contains only samples)
# └── personal_context.json # Personal context data (sample only) (don't change filename personal_context.json, update data if need)
Advanced Configuration
Using HTTP Transport
The default implementation uses stdio transport for development. For production use, you can switch to HTTP transport:
- Edit
src/index.ts
- Uncomment the HTTP transport section
- Configure your desired port and CORS settings
- Rebuild and restart the server
! I reccomend use stdio transport for development locally on your machine always.
Multi-User Support
To support multiple users, modify the contextStorage.js
file to store contexts in user-specific files based on user IDs.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
This project is released under the MIT License - See LICENSE that covers the project.
Acknowledgments
This project is based on the Personal Context Technology concept and implements the Model Context Protocol (MCP) developed by Anthropic to enable AI systems to access external context.
相关推荐
I find academic articles and books for research and literature reviews.
Confidential guide on numerology and astrology, based of GG33 Public information
Embark on a thrilling diplomatic quest across a galaxy on the brink of war. Navigate complex politics and alien cultures to forge peace and avert catastrophe in this immersive interstellar adventure.
Converts Figma frames into front-end code for various mobile frameworks.
Advanced software engineer GPT that excels through nailing the basics.
Delivers concise Python code and interprets non-English comments
💬 MaxKB is a ready-to-use AI chatbot that integrates Retrieval-Augmented Generation (RAG) pipelines, supports robust workflows, and provides advanced MCP tool-use capabilities.
Micropython I2C-based manipulation of the MCP series GPIO expander, derived from Adafruit_MCP230xx
MCP server to provide Figma layout information to AI coding agents like Cursor
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
Reviews

user_8GGlUpGv
As an avid user of pct-mcp-server by mikhashev, I am thoroughly impressed with its performance and reliability. This server application ensures seamless communication and robust functionality, making it an essential part of my tech stack. Its intuitive setup and comprehensive documentation available on its GitHub page (https://github.com/mikhashev/pct-mcp-server) make it accessible for both beginners and experienced developers. Highly recommended for anyone seeking a dependable server solution.