Best of mcp — July 2025

  1. 1
    Article
    Avatar of collectionsCollections·39w

    Building MCP Servers and Clients From Scratch: A Comprehensive Guide

    Model Context Protocol (MCP) is a communication framework for AI client-server interactions built around four components: tools, resources, prompts, and samplings. The guide covers building MCP servers and clients using TypeScript with Node.js, including integration with GitHub Copilot and debugging with MCP Inspector. It also explores .NET 10's native MCP support for creating AI assistant extensions, featuring weather and random number tools, with streamlined publishing to NuGet for community distribution and dependency management.

  2. 2
    Article
    Avatar of dockerDocker·41w

    Top 5 MCP Server Best Practices

    Five essential best practices for building MCP (Model Context Protocol) servers: manage tool budget by avoiding one-tool-per-endpoint patterns, design for AI agents rather than end users with proper error handling, document for both human users and AI agents, test user interactions beyond just functionality using MCP inspector, and package servers as Docker containers for portability. The guide emphasizes that AI agents are the actual consumers of MCP tools, requiring different design considerations than traditional user-facing APIs.

  3. 3
    Article
    Avatar of vercelVercel·39w

    Grep a million GitHub repositories via MCP

    Grep now supports the Model Context Protocol (MCP), allowing AI agents to search over a million public GitHub repositories through a standardized interface. The MCP server can be easily integrated with AI clients like Cursor and Claude, enabling agents to query code patterns and retrieve relevant snippets in real-time. Vercel built the MCP server quickly using their mcp-handler package, which simplifies the process of exposing existing APIs to AI clients.

  4. 4
    Article
    Avatar of dailydoseofdsDaily Dose of Data Science | Avi Chawla | Substack·39w

    MCP Integration with 4 Popular Agentic Frameworks

    Part 8 of an MCP crash course demonstrates how to integrate Model Context Protocol with four popular agentic frameworks: LangGraph, CrewAI, LlamaIndex, and PydanticAI. The tutorial provides step-by-step practical walkthroughs for connecting MCP to each framework, along with detailed implementations. This builds on previous parts covering MCP fundamentals, custom client development, tools/resources/prompts, sampling integration, and security considerations including testing and sandboxing.

  5. 5
    Article
    Avatar of devtoolsDev Tools·38w

    MCP Operations: Simplify Your AI Development Workflow

    MCP Operations is a desktop application that simplifies managing Model Context Protocol servers across AI-powered IDEs like Cursor, VS Code, and Claude Desktop. It features a visual configuration editor that eliminates manual JSON editing, an integrated marketplace for discovering community-contributed servers, and unified management of multiple MCP servers from one interface. The tool aims to reduce configuration complexity and save development time by providing one-click installation, built-in validation, and automatic synchronization between the app and IDE configuration files.

  6. 6
    Article
    Avatar of socketdevSocket·41w

    Official Go SDK for MCP in Development, Stable Release Expec...

    The Model Context Protocol is getting an official Go SDK, joining existing libraries for TypeScript, Python, Java, Rust, Kotlin, and C#. The SDK takes an opinionated approach with idiomatic Go APIs, uses generics for simplified tool implementation, and is built around a single core package. While feature-rich, it's not yet stable with breaking changes expected before the August 2025 release. The design emphasizes completeness, robustness, and future-proofing while maintaining clean separation of concerns between transports, sessions, clients, and servers.

  7. 7
    Article
    Avatar of dailydoseofdsDaily Dose of Data Science | Avi Chawla | Substack·38w

    Connect Any LLM to Any MCP server

    mcp-use is an open-source library that enables developers to connect any LLM to any MCP (Model Context Protocol) server in just 3 lines of code. Unlike being limited to Claude or Cursor, this tool allows building custom MCP agents with local LLMs like Ollama, supports multiple simultaneous MCP server connections, provides sandboxed execution, and includes debugging capabilities for 100% local MCP client development.

  8. 8
    Video
    Avatar of TechWithTimTech With Tim·38w

    Python Advanced MCP Server Tutorial (Authentication, Databases & More)

    A comprehensive tutorial covering advanced MCP (Model Context Protocol) server development in Python using FastMCP. The guide demonstrates implementing OAuth authentication with Stitch, setting up HTTP transport, creating custom tools and resources, and building a React frontend for user authentication. Key topics include MCP architecture, client-server communication, bearer token authentication, database integration with SQLAlchemy, and production-ready features beyond basic MCP server setup.

  9. 9
    Article
    Avatar of hnHacker News·37w

    mcp-use/mcp-use: mcp-use is the easiest way to interact with mcp servers with custom agents

    MCP-Use is an open-source Python library that enables developers to connect any LLM to any MCP (Model Context Protocol) server and build custom agents with tool access. The library supports multiple LLM providers through LangChain, offers HTTP connections, multi-server support, tool access control, and sandboxed execution. It provides a simple 6-line setup for basic agents and includes features like streaming output, dynamic server selection, and debugging capabilities. The project includes examples for web browsing with Playwright, Airbnb search, and Blender 3D creation.

  10. 10
    Article
    Avatar of platformaticPlatformatic·38w

    Platformatic MCP Overview

    Platformatic introduces @platformatic/mcp, a production-ready Fastify adapter for the Model Context Protocol that enables horizontal scaling, type safety, and enterprise-grade reliability. The package supports multiple transports (HTTP/SSE and stdio), Redis-backed session management, automatic reconnection with message replay, and complete TypeScript definitions. It addresses the gap between development-focused MCP implementations and production requirements by providing high availability, session persistence, and cross-instance message broadcasting for scalable AI applications.

  11. 11
    Article
    Avatar of kodekloudKodeKloud's Squad·39w

    MCP (Model Context Protocol) Simplified – But Let's Go Deeper!

    Model Context Protocol (MCP) is a shared communication language that enables AI agents to work together in modular, scalable systems. Unlike traditional API gateways, MCP allows context-aware agents to communicate with specialized services and delegate tasks to other agents through protocols like Agent2Agent. This creates composable, decentralized AI systems where multiple specialized agents collaborate rather than relying on a single large model.

  12. 12
    Article
    Avatar of lnLaravel News·39w

    Tinkerwell v5 is now released

    Tinkerwell v5 introduces AI-powered development features including an MCP server for connecting AI tools like Claude and Cursor, conversational mode with chat sidebar for AI-assisted coding, improved AI code completion, and enhanced UI with fuzzy search and command palette improvements.

  13. 13
    Article
    Avatar of huggingfaceHugging Face·40w

    Upskill your LLMs with Gradio MCP Servers

    The Model Context Protocol (MCP) enables developers to extend Large Language Models with specialized tools and capabilities. Gradio apps on Hugging Face Spaces now support MCP, creating an "app store" of thousands of AI-powered tools that can be connected to LLMs. The post demonstrates how to integrate the Flux.1 Kontext image editing model as an MCP server with Cursor, allowing the LLM to edit images from text prompts. This approach transforms LLMs from simple question-answering systems into powerful assistants with diverse capabilities like image editing, web browsing, and data processing.

  14. 14
    Article
    Avatar of dailydoseofdsDaily Dose of Data Science | Avi Chawla | Substack·38w

    Build the Ultimate MCP Server for Multimodal AI

    A comprehensive guide to building an MCP (Model Context Protocol) server that enables multimodal AI capabilities across text, images, audio, and video. The tutorial demonstrates using Pixeltable as the multimodal AI infrastructure and CrewAI for orchestrating agent workflows. The system includes specialized agents for different modalities, a router agent for query classification, and a synthesis agent for response generation. The implementation supports RAG (Retrieval-Augmented Generation) operations across all media types through Docker-deployed MCP servers.

  15. 15
    Article
    Avatar of phProduct Hunt·40w

    xmcp: The framework for building & shipping MCP applications

    xmcp is a TypeScript framework designed to simplify building and deploying Model Context Protocol (MCP) applications. It features file system routing for auto-registering tools, hot reloading for instant development feedback, middleware support for authentication, extensible configuration options, and built-in Vercel deployment support. The framework includes a CLI tool called create-xmcp-app for quick project scaffolding and aims to lower the barrier to entry for developers working with the MCP ecosystem.

  16. 16
    Article
    Avatar of dailydoseofdsDaily Dose of Data Science | Avi Chawla | Substack·37w

    Build an Ultimate AI Assistant using 6 MCP servers

    A comprehensive guide to building a local AI assistant using 6 MCP (Model Context Protocol) servers integrated through the mcp-use framework. The assistant combines browser automation (Stagehand), web scraping (Firecrawl), memory management (Graphiti), multimodal RAG (Ragie), GitHub repository analysis (GitIngest), and terminal control capabilities. The solution runs entirely locally using Ollama and LangChain, wrapped in a Streamlit interface for dynamic configuration.

  17. 17
    Article
    Avatar of tdsTowards Data Science·38w

    MCP Client Development with Streamlit: Build Your AI-Powered Web App

    A comprehensive guide to building an MCP (Model Context Protocol) client using Streamlit that connects to remote MCP servers like DeepWiki and HuggingFace. Covers setting up the development environment, securing API keys, creating user interfaces with Streamlit components, connecting to MCP servers, and generating AI-powered responses. Includes practical code examples and deployment considerations for creating interactive web applications that leverage external AI tools and resources.

See all mcp archives