Back to Directory/AI & ML

Learning Model Context Protocol

MCP server that can perform basic arithmetic operations and parse/evaluate arithmetic expressions.

AI & MLPythonv0.2.0
View on GitHub

Learning Model Context Protocol

This project explores the features and usage of Model Context Protocol (MCP) servers and clients, providing a hands-on learning environment for experimenting with MCP-based tools and workflows.

Documentation

Contributing

Please see CONTRIBUTING.md for development and contribution guidelines.

Links

License

This project is licensed under the GNU Affero General Public License v3.0 or later (AGPL-3.0-or-later).

Copyright (C) 2025 Anirban Ray

See the LICENSE file for details.

Learn More

How to Use MCP Servers With Ollama and Local LLMsOllama does not natively speak MCP, but bridge tools like MCPHost let local models call MCP tools over stdio. MCPFind indexes 832 servers in the ai-ml category. This guide covers which models support tool calling, how to wire MCPHost to any local model, and which server categories are worth running offline.Read articleMCP vs LangChain Tools: Which Should You Use?LangChain tools and MCP servers both give AI models access to external functions, but they work at different layers. This guide compares them on architecture, cross-client reuse, and long-term maintenance using adoption data from the MCPFind directory's 6,105 indexed servers.Read articleMCP vs Function Calling: Which Should You Build With?MCP and function calling solve different problems in AI agent architecture. Function calling is tight, in-process, and fast. MCP is modular, reusable across models, and designed for production tooling. We analyzed both patterns against real servers in the MCPFind directory to map out when each one wins.Read article