MCP Server on Raspi
A simple note storage system with a custom note:// URI scheme, allowing users to add and summarize notes.
mcp-server-on-raspi MCP server
A MCP server project
Components
Resources
The server implements a simple note storage system with:
- Custom note:// URI scheme for accessing individual notes
- Each note resource has a name, description and text/plain mimetype
Prompts
The server provides a single prompt:
- summarize-notes: Creates summaries of all stored notes
- Optional "style" argument to control detail level (brief/detailed)
- Generates prompt combining all current notes with style preference
Tools
The server implements one tool:
- add-note: Adds a new note to the server
- Takes "name" and "content" as required string arguments
- Updates server state and notifies clients of resource changes
Configuration
[TODO: Add configuration details specific to your implementation]
Quickstart
Install
Claude Desktop
On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
Development/Unpublished Servers Configuration
``` "mcpServers": { "mcp-server-on-raspi": { "command": "uv", "args": [ "--directory", "/Users/daikiwatanabe/ghq/github.com/daikw/mcp-server-on-raspi", "run", "mcp-server-on-raspi" ] } } ```Published Servers Configuration
``` "mcpServers": { "mcp-server-on-raspi": { "command": "uvx", "args": [ "mcp-server-on-raspi" ] } } ```Development
Building and Publishing
To prepare the package for distribution:
- Sync dependencies and update lockfile:
uv sync
- Build package distributions:
uv build
This will create source and wheel distributions in the dist/ directory.
- Publish to PyPI:
uv publish
Note: You'll need to set PyPI credentials via environment variables or command flags:
- Token:
--tokenorUV_PUBLISH_TOKEN - Or username/password:
--username/UV_PUBLISH_USERNAMEand--password/UV_PUBLISH_PASSWORD
Debugging
Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.
You can launch the MCP Inspector via npm with this command:
npx @modelcontextprotocol/inspector uv --directory /Users/daikiwatanabe/ghq/github.com/daikw/mcp-server-on-raspi run mcp-server-on-raspi
Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
관련 서버
Kone.vc
스폰서Monetize your AI agent with contextual product recommendations
Dooray MCP Server
Manage schedules using the Dooray API. Requires API key, member ID, and calendar ID to be configured.
Mautic
Integrates with the Mautic marketing automation platform.
HubSpot
Interact with the HubSpot CRM API to manage contacts, companies, and deals.
DaVinci Resolve
Enables AI assistants to interact with DaVinci Resolve Studio for advanced control over video editing, color grading, and audio.
Reply.io
Control Reply.io sequences and contacts directly from your AI model. Manage outreach, pull stats, and enroll prospects — without leaving your AI chat.
@mcp-z/mcp-pdf
Create PDFs without leaving your workflow. Perfect for documentation, reports, and creative projects. Productive PDF generation with full Unicode and emoji support.
UnifAI
Dynamically search and call tools using UnifAI Network
Attio
Connect your Attio workspace to large language models.
Busibee
Easily query & find Belgian company finances
AutoWP
Connects Claude to WordPress sites to create posts and manage sites using the WordPress REST API.