local-only server
The server can only run on the client’s local machine because it depends on local resources.
Integrations
Planned integration for accessing and potentially modifying Figma designs through the MCP server
Planned integration for accessing and managing Google Calendar events and schedules through the MCP server
Planned integration for interacting with Slack workspaces, likely enabling message sending and workspace management through the MCP server
MCP (Model Context Protocol) Tutorial
📚 Learning Steps
Step 0: Understanding MCP
- MCP Concept and Structure
- Understanding Resources, Tools, and Prompts
- Understanding MCP Server, Host, and Client
- MCP vs Traditional API
- Understanding Communication Protocols
Step 1: Using MCP Inspector
- Testing with Inspector
- Basic server implementation (examples/country_server/country_server.py)
- How to use Inspector
- Session management and communication methods
Step 2: External Service Integration
- Google Calendar integration (in progress)
- Slack integration (in progress)
- Figma integration (in progress)
🚀 Get started
- External libraries used are fastmcp and mcp-agent.
Preferences
Copy
Running the basic server
Copy
📁 Project Structure (Draft)
Copy
🔗 References
Official Document
Community Resources
- MCP made simple and easy to understand
- Awesome MCP Servers
- PyTorch KR Discussion
- https://www.dailydoseofds.com/p/visual-guide-to-model-context-protocol-mcp/
Additional Study Materials
This server cannot be installed
A tutorial MCP server implementation that provides country information, demonstrating the Model Context Protocol for building AI-powered applications with external service integration capabilities.