This MCP server provides a modular assistant platform that can function similarly to Siri, Alexa, or Google Assistant by wiring together a set of intelligent tools. It includes web search via DuckDuckGo (page-scraped without needing an API key), memory storage with time-stamped and persistent memories, time and date reporting, file system browsing and modification with safety safeguards, file type inspection, remote URL processing, a personal life organization system (notes, tasks, events, bookmarks, recipes) stored as a human-readable markdown database, device control (including screen locking), system diagnostics, and YouTube video transcription. When run, you can enable or disable individual modules to tailor the assistant to your needs, and the MCP backbone ensures the AI model can orchestrate multiple actions across these tools for complex tasks. To use it, run the server in your environment and connect your preferred UI or agent that supports MCP transport, usually via stdio or a configured transport channel. The AI model will then issue commands to the available tools to fulfill user requests, such as summarizing a YouTube video and saving the result to notes, or creating a recipe and storing it in your recipes database.

Prerequisites:

• Python 3.8+ installed on your system
• Access to a terminal/command prompt
• git installed to clone the repository

Installation steps:

1. Clone the repository git clone https://github.com/Rose22/mcp_tools_server.git cd mcp_tools_server

2. Create and activate a virtual environment (recommended) python -m venv venv

   On Windows

   venv\Scripts\activate

   On macOS/Linux

   source venv/bin/activate

3. Install Python dependencies pip install -r requirements.txt

4. Run the server (example using module entrypoint) python -m mcp_tools_server

5. Integrate with your UI:

   • Configure your MCP client to connect to the server's transport (default is stdio for local runs).
   • If needed, adjust main.py to enable the transport you want (stdio, socket, etc.).

Tips and notes:

• The server stores memories in a compact, fast msgpack format and only retains about 30 days of recent memory by default; you can request longer retention if needed.
• The project uses a markdown-based database for notes, tasks, and other objects, which makes backups and migrations straightforward.
• You can customize what modules are active via configuration (config.yaml in the repo or runtime environment) to minimize resource usage.
• If you run into transport issues, ensure the Python process can access the intended IO channels and that any required dependencies listed in requirements.txt are installed.
• For safety, file operations include automatic backups before modifications; review config.yaml for enabling/disabling safety features and backup behaviors.