Mcp

Model Context Protocol is an open standard from Anthropic that defines how LLMs connect to external tools and data. One protocol - many sources. Architecture: ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │ LLM Client │ ←→ │ MCP Server │ ←→ │ Resource │ │ (Cursor, │ stdio/ │ (filesystem,│ │ (files, DB,│ │ Claude, │ HTTP │ github...) │ │ API...) │ │ OpenWebUI) │ │ │ │ │ └─────────────┘ └─────────────┘ └─────────────┘ Client - app with LLM (Cursor, Claude Desktop, Open WebUI) Server - wrapper around a resource (Node.js/Python process) Resource - data source or action (DB, API, filesystem) 💡 MCP defines a standard way to connect the model to external tools. The model doesn’t become “smarter” - it gains access to data and actions. ...

Ollama is a runtime for local execution of large language models. Installation and startup are performed with a single command; manual dependency setup and virtual environments are not required. Local machine → Ollama → Model (Llama, Qwen, Mistral...) Advantages: Data never leaves the local machine No internet connection required for inference No subscriptions or limits Works on CPU (with limited performance) Installation NixOS # configuration.nix services.ollama = { enable = true; # Optional: list of models for auto-loading # models = [ "qwen2.5:7b" ]; }; Apply: ...