Best of mcp — June 2025

  1. 1
    Article
    Avatar of dailydoseofdsDaily Dose of Data Science | Avi Chawla | Substack·44w

    9 MCP Projects for AI Engineers

    A comprehensive collection of 9 Model Control Protocol (MCP) projects designed for AI engineers, covering various applications from local MCP clients and agentic RAG systems to voice agents and synthetic data generators. The projects demonstrate how to integrate MCP with popular tools like Claude Desktop and Cursor IDE, enabling developers to build more sophisticated AI applications with enhanced tool connectivity and context sharing capabilities.

  2. 2
    Article
    Avatar of communityCommunity Picks·42w

    Your Ultimate MCP Server Hub

    MCPHub is a unified management platform that consolidates multiple Model Context Protocol (MCP) servers into a single Server-Sent Events (SSE) endpoint. It provides a dashboard for monitoring server status and simplifies infrastructure management for AI applications. The tool can be quickly deployed using Docker and allows customization through JSON configuration files.

  3. 3
    Article
    Avatar of dailydoseofdsDaily Dose of Data Science | Avi Chawla | Substack·43w

    10 MCP, RAG and AI Agents Projects

    A curated collection of 10 advanced AI engineering projects covering MCP-powered applications, RAG systems, and AI agents. Projects include video RAG with exact timestamp retrieval, corrective RAG with self-assessment, multi-agent flight booking systems, voice-enabled RAG agents, and local alternatives to ChatGPT's research features. The repository contains 70+ hands-on tutorials focusing on real-world implementations of LLMs, memory-enabled agents, multimodal document processing, and performance optimization techniques like binary quantization for 40x faster RAG systems.

  4. 4
    Article
    Avatar of uxplanetUX Planet·43w

    Figma MCP: Complete Guide

    Figma MCP (Model Context Protocol) enables AI code generators like Cursor to understand Figma designs at a semantic level, providing better design-to-code conversion than screenshot-based approaches. The guide covers setup requirements including Figma Desktop app and compatible code editors, configuration steps for both Figma and Cursor, and troubleshooting common issues like 'get_code' and 'get_image' errors. MCP offers design token awareness and semantic precision, allowing AI to access exact variable names, hierarchy, and constraints for better alignment with design systems.

  5. 5
    Article
    Avatar of dailydoseofdsDaily Dose of Data Science | Avi Chawla | Substack·45w

    An MCP-powered Voice Agent

    A technical demonstration of building a voice agent using Model Context Protocol (MCP) that can query databases and perform web searches. The system uses AssemblyAI for speech-to-text, Firecrawl for web search, Supabase as the database, LiveKit for orchestration, and Qwen3 as the LLM. The agent transcribes user speech, determines whether to query the database or search the web, and responds via text-to-speech.

  6. 6
    Article
    Avatar of itnextITNEXT·41w

    How to Start Your Own MCP Server with n8n

    n8n version 1.88.0+ includes built-in Model Context Protocol (MCP) support, allowing users to expose workflows as AI-usable tools through MCP Server Trigger nodes and connect to other MCP servers via MCP Client Tool nodes. The guide covers setting up MCP endpoints, configuring authentication, exposing tools, and connecting with AI agents, all without requiring additional installations or Docker images.

  7. 7
    Article
    Avatar of heidloffNiklas Heidloff·43w

    Building agentic Applications with Langflow and MCP

    Langflow is an open-source visual tool for building agentic applications using reusable UI components and Python code. The tutorial demonstrates creating an agent that uses watsonx.ai LLM to search news and generate charts by integrating MCP (Model Context Protocol) tools. It shows how to set up custom components, connect MCP servers for chart generation, and deploy Langflow applications as MCP servers for integration with other agentic systems.

  8. 8
    Article
    Avatar of dailydoseofdsDaily Dose of Data Science | Avi Chawla | Substack·43w

    Deploy any ML model, RAG or Agent as an MCP server

    LitServe now supports MCP (Model Context Protocol) integration through a dedicated endpoint, allowing any ML model, RAG system, or AI agent to be deployed as an MCP server. This eliminates the need for custom integration code for each application. The implementation involves defining input schemas, setup methods, and inference logic in a simple Python class structure. The article also covers a 4-part MCP crash course and demonstrates deploying a Qwen 3 Agentic RAG system using CrewAI, Firecrawl, and LitServe.

  9. 9
    Video
    Avatar of communityCommunity Picks·42w

    MCP Server Tutorial | Build your first MCP Server with TypeScript SDK

    Model Context Protocol (MCP) is a standardized way to connect AI applications with external data sources. Developed by Anthropic, MCP works like a universal connector that allows AI models to access structured context from databases, APIs, calendars, and files through custom-built servers. The tutorial demonstrates building an MCP server using TypeScript that integrates Google Calendar with AI assistants like Claude or Cursor, enabling natural language queries about meetings and schedules. MCP servers communicate via standard input/output and can be reused across different AI applications, creating new opportunities for developers to build AI-enabling infrastructure.

  10. 10
    Article
    Avatar of dailydoseofdsDaily Dose of Data Science | Avi Chawla | Substack·44w

    The Full MCP Blueprint—Part 3

    Part 3 of an MCP crash course focuses on building a custom MCP client from scratch, moving beyond prebuilt solutions like Cursor or Claude. It explores the full MCP lifecycle, demonstrates the client-server architecture through practical implementation, and shows how MCP differs from traditional API and function calling approaches. The series addresses the M×N problem in tool integrations and presents MCP as a standardized protocol that enables dynamic tool discovery and invocation at runtime, facilitating plug-and-play interoperability between different AI systems.

  11. 11
    Article
    Avatar of dailydoseofdsDaily Dose of Data Science | Avi Chawla | Substack·43w

    Build a Full-Fledged MCP Workflow Using tools, Resources, and Prompts

    Part 4 of an MCP crash course that demonstrates building a complete workflow using tools, resources, and prompts. Covers implementing resources and prompts server-side, understanding their differences from tools, integrating with Claude Desktop, and creating real-world use cases. The series addresses the M×N problem in tool integrations and shows how MCP enables dynamic tool discovery and plug-and-play interoperability between AI systems.

  12. 12
    Video
    Avatar of dreamsofcodeDreams of Code·45w

    This is perhaps my favorite thing I've built with A.I. so far...

    A developer shares their experience building an AI-powered system to automatically convert video content into formatted blog posts. The solution uses Whisper CPP for local transcription, integrates with PostgreSQL via Neon's MCP (Model Context Protocol) server, and allows interactive refinement through Claude Desktop. The system saved approximately 120 hours of manual work by automating the conversion of 120 course lessons into written guides, while maintaining data safety through database branching.

  13. 13
    Article
    Avatar of dailydoseofdsDaily Dose of Data Science | Avi Chawla | Substack·42w

    Introduction to Sampling for MCP Workflows (With Implementation)

    Part 5 of an MCP crash course series focuses on integrating sampling into MCP workflows. It covers sampling concepts, FastMCP support, server-side implementation, client-side handlers, model preferences, use cases, and best practices. The series builds from foundational MCP concepts through hands-on implementation, covering tools, resources, prompts, custom client development, and real-world workflow integration.

  14. 14
    Article
    Avatar of github_updatesGitHub Changelog·44w

    Remote GitHub MCP Server is now in public preview

    GitHub has launched a Remote MCP Server in public preview that allows AI tools like GitHub Copilot and Claude Desktop to access live GitHub data including issues, pull requests, and code files. The remote server offers one-click setup, OAuth 2.0 authentication with SAML enforcement, and automatic updates without requiring local installation. It supports both OAuth and Personal Access Tokens for authentication, though OAuth is recommended for better security and scoped access. Organizations need to enable the Editor Preview Policy for GitHub Copilot integration during the preview period.

  15. 15
    Article
    Avatar of tinybirdTinybird·42w

    Introducing the Tinybird MCP Server: Your real-time data, LLM-ready

    Tinybird launches its MCP Server, a hosted solution that enables LLMs and AI agents to securely access real-time data from Tinybird workspaces. The server provides tools for data exploration, text-to-SQL conversion, and query execution, with token-based security and built-in observability. It supports various AI frameworks including Agno, Pydantic AI, and Vercel AI SDK, making real-time analytics accessible through natural language queries without infrastructure setup.

  16. 16
    Article
    Avatar of tinybirdTinybird·44w

    MCP vs APIs: When to Use Which for AI Agent Development

    Model Context Protocol (MCP) and traditional APIs serve different purposes in AI agent development. MCP excels at enabling dynamic tool selection, agent autonomy, and rapid prototyping by providing a standardized way for LLMs to discover and use tools conversationally. Traditional APIs are better for performance-critical applications, complex data operations, and deterministic workflows requiring strict security controls. The most effective approach often combines both: using MCP for flexible reasoning and natural language interactions, while leveraging direct API calls for bulk operations and enforcing constraints. MCP doesn't replace APIs but adds a conversational layer that makes them LLM-friendly.

  17. 17
    Article
    Avatar of cloudflareCloudflare·43w

    Connect any React application to an MCP server in three lines of code

    Cloudflare open-sourced use-mcp, a React library that connects to Model Context Protocol (MCP) servers with just 3 lines of code, handling transport protocols, authentication, and session management automatically. The library supports OAuth 2.1, connection retries, real-time state management, and both Server-Sent Events and Streamable HTTP transport methods. Additionally, Cloudflare released their AI Playground source code, a complete chat interface that demonstrates MCP integration with Workers AI and provides debugging capabilities for MCP connections.

  18. 18
    Article
    Avatar of dailydoseofdsDaily Dose of Data Science | Avi Chawla | Substack·45w

    Build a Shared Memory for Claude Desktop and Cursor

    Learn how to create a shared memory system between Claude Desktop and Cursor using Graphiti MCP server. The setup involves deploying a local Docker container with Neo4j database and configuring both AI tools to connect to the same MCP server, enabling context sharing and cross-operation between the two platforms.

  19. 19
    Article
    Avatar of hnHacker News·44w

    Mastra Course: Learn to Build AI Agents

    A hands-on course teaching developers how to build AI agents using Mastra framework. The course covers three main lessons: creating basic agents with tools and memory, integrating external services through MCP servers, and implementing memory systems for conversation history. Students learn through an interactive code editor with an AI agent as their guide, progressing from setup to production deployment over 12 hours of content.

See all mcp archives