[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"category-tools-zh-devtools":3},{"items":4,"total":375,"page":376,"pageSize":377},[5,30,45,60,75,90,105,120,135,150,165,180,195,210,225,240,255,270,285,300,315,330,345,360],{"slug":6,"name":7,"categorySlug":8,"summary":9,"description":10,"categoryName":11,"sourceUrl":12,"homepageUrl":-1,"downloadUrl":13,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":14,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":17,"clients":20,"tags":27,"installCommand":-1,"configSnippet":-1,"useCases":28,"updatedAt":29},"metoro-io-mcp-golang","metoro-io\u002Fmcp-golang","devtools","Write Model Context Protocol servers in few lines of go code. Docs at https:\u002F\u002Fmcpgolang.com . Created by https:\u002F\u002Fmetoro.io","mcp-golang is an unofficial implementation of the Model Context Protocol in Go.\n\nWrite MCP servers and clients in golang with a few lines of code.\n\n- 🛡️** - Define your tool arguments as native go structs, have mcp-golang handle the rest. Automatic schema generation, deserialization, error handling etc. - 🚛 - Use the built-in transports (stdio for full feature support, HTTP for stateless communication) or write your own. - ⚡ - mcp-golang generates all the MCP endpoints for you apart from your tools, prompts and resources. - 🧩 - The library is split into three components: transport, protocol and server\u002Fclient. Use them all or take what you need. - 🔄 - Full support for both server and client implementations through stdio transport.\n\nInstall with go get github.com\u002Fmetoro-io\u002Fmcp-golang\n\nYou can also create an HTTP-based server using either the standard HTTP transport or Gin framework:\n\nNote: HTTP transports are stateless and don't support bidirectional features like notifications.","开发工具","https:\u002F\u002Fgithub.com\u002Fmetoro-io\u002Fmcp-golang","https:\u002F\u002Fgithub.com\u002Fmetoro-io\u002Fmcp-golang\u002Farchive\u002FHEAD.zip",1223,0,99,[18,19],"claude-desktop","cursor",[21,24],{"slug":18,"name":22,"summary":23,"count":15},"Claude Desktop","支持本地 MCP 配置的桌面客户端。",{"slug":19,"name":25,"summary":26,"count":15},"Cursor","常与开发类 MCP Server 搭配使用的 AI 代码编辑器。",[8],[],"2026-08-30T08:27:16.789006",{"slug":31,"name":32,"categorySlug":8,"summary":33,"description":34,"categoryName":11,"sourceUrl":35,"homepageUrl":-1,"downloadUrl":36,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":37,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":38,"clients":39,"tags":42,"installCommand":-1,"configSnippet":-1,"useCases":43,"updatedAt":44},"pimzino-spec-workflow-mcp","pimzino\u002Fspec-workflow-mcp","A Model Context Protocol (MCP) server that provides structured spec-driven development workflow tools for AI-assisted software development, featuring a real-time web dashboard and VSCode extension...","I HAVE TAKEN A SMALL BREAK FROM THIS REPO FOR PERSONAL REASONS BUT I WILL BE BACK WITH SOME UPDATES IN THE NEAR FUTURE THANK YOU FOR YOUR UNDERSTANDING\n\nA Model Context Protocol (MCP) server for structured spec-driven development with real-time dashboard and VSCode extension.\n\nSee how the approval system works: create documents, request approval through the dashboard, provide feedback, and track revisions.\n\nExplore the real-time dashboard: view specs, track progress, navigate documents, and monitor your development workflow.","https:\u002F\u002Fgithub.com\u002Fpimzino\u002Fspec-workflow-mcp","https:\u002F\u002Fgithub.com\u002Fpimzino\u002Fspec-workflow-mcp\u002Farchive\u002FHEAD.zip",4257,[18,19],[40,41],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T08:27:34.773071",{"slug":46,"name":47,"categorySlug":8,"summary":48,"description":49,"categoryName":11,"sourceUrl":50,"homepageUrl":-1,"downloadUrl":51,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":52,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":53,"clients":54,"tags":57,"installCommand":-1,"configSnippet":-1,"useCases":58,"updatedAt":59},"punitarani-fli","punitarani\u002Ffli","Google Flights MCP, CLI and Python Library","A powerful Python library that provides programmatic access to Google Flights data with an elegant CLI interface. Search flights, find the best deals, and filter results with ease.\n\n🚀 Unlike other flight search libraries that rely on web scraping, Fli directly interacts with Google Flights' API through reverse engineering. This means: * : Direct API access means faster, more reliable results * : No HTML parsing, no browser automation, just pure API interaction * : Less prone to breaking from UI changes * : Extensible architecture for easy customization and integration\n\n: Replace with your actual username. You can also find the path to the MCP server by running which fli-mcp in your terminal.","https:\u002F\u002Fgithub.com\u002Fpunitarani\u002Ffli","https:\u002F\u002Fgithub.com\u002Fpunitarani\u002Ffli\u002Farchive\u002FHEAD.zip",2986,[18,19],[55,56],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T08:26:53.087555",{"slug":61,"name":62,"categorySlug":8,"summary":63,"description":64,"categoryName":11,"sourceUrl":65,"homepageUrl":-1,"downloadUrl":66,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":67,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":68,"clients":69,"tags":72,"installCommand":-1,"configSnippet":-1,"useCases":73,"updatedAt":74},"haris-musa-excel-mcp-server","haris-musa\u002Fexcel-mcp-server","A Model Context Protocol server for Excel file manipulation","A Model Context Protocol (MCP) server that lets you manipulate Excel files without needing Microsoft Excel installed. Create, read, and modify Excel workbooks with your AI agent.\n\n- 📊 : Create, read, update workbooks and worksheets - 📈 : Formulas, formatting, charts, pivot tables, and Excel tables - 🔍 : Built-in validation for ranges, formulas, and data integrity - 🎨 : Font styling, colors, borders, alignment, and conditional formatting - 📋 : Create and manage Excel tables with custom styling - 📊 : Generate various chart types (line, bar, pie, scatter, etc.) - 🔄 : Create dynamic pivot tables for data analysis - 🔧 : Copy, rename, delete worksheets with ease - 🔌 : stdio, SSE (deprecated), and streamable HTTP - 🌐 : Works both locally and as a remote service\n\nThe server supports three transport methods:\n\nWhen running the server with the , you . This variable tells the server where to read and write Excel files. - If not set, it defaults to .\u002Fexcel_files.","https:\u002F\u002Fgithub.com\u002Fharis-musa\u002Fexcel-mcp-server","https:\u002F\u002Fgithub.com\u002Fharis-musa\u002Fexcel-mcp-server\u002Farchive\u002FHEAD.zip",3985,[18,19],[70,71],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T04:32:25.907827",{"slug":76,"name":77,"categorySlug":8,"summary":78,"description":79,"categoryName":11,"sourceUrl":80,"homepageUrl":-1,"downloadUrl":81,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":82,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":83,"clients":84,"tags":87,"installCommand":-1,"configSnippet":-1,"useCases":88,"updatedAt":89},"jjsantos01-qgis-mcp","jjsantos01\u002Fqgis_mcp","Model Context Protocol (MCP) that allows LLMs to use QGIS Desktop","QGISMCP connects QGIS to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control QGIS. This integration enables prompt assisted project creation, layer loading, code execution and more.\n\nThis project is strongly based on the BlenderMCP project by Siddharth Ahuja\n\n- : Connect Claude AI to QGIS through a socket-based server. - : Create, load and save projects in QGIS. - : Add and remove vector or raster layers to a project. - : Execute processing algorithms (Processing Toolbox). - : Run arbitrary Python code in QGIS from Claude. Very powerful, but also be very cautious using this tool.\n\nThe system consists of two main components:\n\n1. : A QGIS plugin that creates a socket server within QGIS to receive and execute commands. 2. : A Python server that implements the Model Context Protocol and connects to the QGIS plugin.\n\n- QGIS 3.X (only tested on 3.22) - Claude desktop - Python 3.","https:\u002F\u002Fgithub.com\u002Fjjsantos01\u002Fqgis_mcp","https:\u002F\u002Fgithub.com\u002Fjjsantos01\u002Fqgis_mcp\u002Farchive\u002FHEAD.zip",1016,[18,19],[85,86],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T08:27:13.353395",{"slug":91,"name":92,"categorySlug":8,"summary":93,"description":94,"categoryName":11,"sourceUrl":95,"homepageUrl":-1,"downloadUrl":96,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":97,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":98,"clients":99,"tags":102,"installCommand":-1,"configSnippet":-1,"useCases":103,"updatedAt":104},"cjo4m06-mcp-shrimp-task-manager","cjo4m06\u002Fmcp-shrimp-task-manager","Shrimp Task Manager is a task tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency.","🦐 - Break down complex projects into manageable tasks, maintain context across sessions, and accelerate your development workflow.\n\n- Node.js 18+ - npm or yarn - MCP-compatible AI client (Claude Code, etc.)\n\nCreate a .mcp.json file in your project directory:\n\nThen start Claude Code with your custom MCP configuration:\n\n: A VS Code extension for AI-assisted coding. Add to VS Code settings.json under cline.mcpServers\n\n: Add to ~\u002FLibrary\u002FApplication Support\u002FClaude\u002Fclaude_desktop_config.json (macOS) or %APPDATA%\\Claude\\claude_desktop_config.json (Windows)\n\n1. : \"init project rules\" 2. : \"plan task: implement user authentication\" 3. : \"execute task\" or \"continuous mode\"\n\nShrimp Task Manager is an MCP (Model Context Protocol) server that transforms how AI agents approach software development. Instead of losing context or repeating work, Shrimp provides:","https:\u002F\u002Fgithub.com\u002Fcjo4m06\u002Fmcp-shrimp-task-manager","https:\u002F\u002Fgithub.com\u002Fcjo4m06\u002Fmcp-shrimp-task-manager\u002Farchive\u002FHEAD.zip",2126,[18,19],[100,101],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T08:27:07.322308",{"slug":106,"name":107,"categorySlug":8,"summary":108,"description":109,"categoryName":11,"sourceUrl":110,"homepageUrl":-1,"downloadUrl":111,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":112,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":113,"clients":114,"tags":117,"installCommand":-1,"configSnippet":-1,"useCases":118,"updatedAt":119},"tuanle96-mcp-odoo","tuanle96\u002Fmcp-odoo","Odoo MCP for AI agents — gated writes, multi-instance. Hosted product: https:\u002F\u002Ferpipe.com","The free AI layer for Odoo — any edition, any version. Odoo's built-in AI is Enterprise-only. Odoo MCP gives Community and Enterprise 16+ the same power for $0 with the LLM you already use (Claude, GPT, Gemini, DeepSeek, Ollama). Five-minute install. Zero Odoo-side setup. Safe writes, real diagnostics, JSON-2 ready years before the Odoo 22 XML-RPC removal.\n\nOdoo MCP turns any Odoo 16+ database into a Model Context Protocol server — using only your existing credentials. Built for local agents, IDEs, and automation tools that need real Odoo context without hand-rolled scripts or unsafe direct write access.\n\nIt speaks XML-RPC for Odoo 16-18 and External JSON-2 for Odoo 19+. It exposes a compact MCP surface with read tools, diagnostics, schema discovery, migration helpers, local addon scanning, and a gated write workflow. One server can serve multiple named Odoo instances at once.","https:\u002F\u002Fgithub.com\u002Ftuanle96\u002Fmcp-odoo","https:\u002F\u002Fgithub.com\u002Ftuanle96\u002Fmcp-odoo\u002Farchive\u002FHEAD.zip",359,[18,19],[115,116],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T04:32:28.623471",{"slug":121,"name":122,"categorySlug":8,"summary":123,"description":124,"categoryName":11,"sourceUrl":125,"homepageUrl":-1,"downloadUrl":126,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":127,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":128,"clients":129,"tags":132,"installCommand":-1,"configSnippet":-1,"useCases":133,"updatedAt":134},"blazickjp-arxiv-mcp-server","blazickjp\u002Farxiv-mcp-server","A local MCP server for agent literature work. Original-LaTeX section reads, BibTeX from arXiv metadata, and topic watches. Papers stay on disk. Search is optional.","🔍 Enable AI assistants to search and access arXiv papers through a simple MCP interface.\n\nThe ArXiv MCP Server provides a bridge between AI assistants and arXiv's research repository through the Model Context Protocol (MCP). It allows AI models to search for papers and access their content in a programmatic way.\n\n- 🔎 : Query arXiv papers with filters for date ranges and categories - 📄 : Download and read paper content - 📋 : View all downloaded papers - 🗃️ : Papers are saved locally for faster access - 📝 : A set of research prompts for paper analysis\n\nWhen an AI assistant downloads or reads a paper through this server, the paper's text is passed directly into the model's context. A maliciously crafted paper could embed adversarial instructions designed to hijack the AI's behavior — for example, instructing it to exfiltrate data, invoke other tools with unintended arguments, or override system-level instructions.","https:\u002F\u002Fgithub.com\u002Fblazickjp\u002Farxiv-mcp-server","https:\u002F\u002Fgithub.com\u002Fblazickjp\u002Farxiv-mcp-server\u002Farchive\u002FHEAD.zip",2930,[18,19],[130,131],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T08:26:48.918172",{"slug":136,"name":137,"categorySlug":8,"summary":138,"description":139,"categoryName":11,"sourceUrl":140,"homepageUrl":-1,"downloadUrl":141,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":142,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":143,"clients":144,"tags":147,"installCommand":-1,"configSnippet":-1,"useCases":148,"updatedAt":149},"coding-solo-godot-mcp","coding-solo\u002Fgodot-mcp","MCP server for interfacing with Godot game engine. Provides tools for launching the editor, running projects, and capturing debug output.","A Model Context Protocol (MCP) server for interacting with the Godot game engine.\n\nGodot MCP enables AI agents to launch the Godot editor, run projects, capture debug output, and control project execution. This direct feedback loop helps agents understand what works and what doesn't in real Godot projects, leading to better code generation and debugging assistance.\n\n- : Open the Godot editor for a specific project - : Execute Godot projects in debug mode - : Retrieve console output and error messages - : Start and stop Godot projects programmatically - : Retrieve the installed Godot version - : Find Godot projects in a specified directory - : Get detailed information about project structure - : - Create new scenes with specified root node types - Add nodes to existing scenes with customizable properties - Load sprites and textures into Sprite2D nodes - Export 3D scenes as MeshLibrary resources for GridMap - Save scenes with options for creating variants - (for Godot 4.","https:\u002F\u002Fgithub.com\u002Fcoding-solo\u002Fgodot-mcp","https:\u002F\u002Fgithub.com\u002Fcoding-solo\u002Fgodot-mcp\u002Farchive\u002FHEAD.zip",4515,[18,19],[145,146],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T04:32:04.630518",{"slug":151,"name":152,"categorySlug":8,"summary":153,"description":154,"categoryName":11,"sourceUrl":155,"homepageUrl":-1,"downloadUrl":156,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":157,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":158,"clients":159,"tags":162,"installCommand":-1,"configSnippet":-1,"useCases":163,"updatedAt":164},"agentdeskai-browser-tools-mcp","agentdeskai\u002Fbrowser-tools-mcp","Monitor browser logs directly from Cursor and other MCP compatible IDEs.","THIS PROJECT IS NO LONGER ACTIVE PLEASE USE A DIFFERENT SOLUTION FOR THIS.\n\nMake your AI tools 10x more aware and capable of interacting with your browser\n\nThis application is a powerful browser monitoring and interaction tool that enables AI-powered applications via Anthropic's Model Context Protocol (MCP) to capture and analyze browser data through a Chrome extension.\n\nRead our docs for the full installation, quickstart and contribution guides.\n\nCheck out our project roadmap here: Github Roadmap \u002F Project Board\n\nv1.2.0 is out! Here's a quick breakdown of the update: - You can now enable \"Allow Auto-Paste into Cursor\" within the DevTools panel. Screenshots will be automatically pasted into Cursor (just make sure to focus\u002Fclick into the Agent input field in Cursor, otherwise it won't work!","https:\u002F\u002Fgithub.com\u002Fagentdeskai\u002Fbrowser-tools-mcp","https:\u002F\u002Fgithub.com\u002Fagentdeskai\u002Fbrowser-tools-mcp\u002Farchive\u002FHEAD.zip",7261,[18,19],[160,161],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T04:32:01.469749",{"slug":166,"name":167,"categorySlug":8,"summary":168,"description":169,"categoryName":11,"sourceUrl":170,"homepageUrl":-1,"downloadUrl":171,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":172,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":173,"clients":174,"tags":177,"installCommand":-1,"configSnippet":-1,"useCases":178,"updatedAt":179},"antvis-mcp-server-chart","antvis\u002Fmcp-server-chart","🤖 A visualization mcp & skills contains 25+ visual charts using @antvis. Using for chart generation and data analysis.","A Model Context Protocol server for generating charts using AntV. We can use this mcp server for chart generation and data analysis.\n\nThis is a TypeScript-based MCP server that provides chart generation capabilities. It allows you to create various types of charts through MCP tools. You can also use it in Dify.\n\n1. generate_area_chart: Generate an area chart, used to display the trend of data under a continuous independent variable, allowing observation of overall data trends. 1. generate_bar_chart: Generate a bar chart, used to compare values across different categories, suitable for horizontal comparisons. 1. generate_boxplot_chart: Generate a boxplot, used to display the distribution of data, including the median, quartiles, and outliers. 1. generate_column_chart: Generate a column chart, used to compare values across different categories, suitable for vertical comparisons. 1.","https:\u002F\u002Fgithub.com\u002Fantvis\u002Fmcp-server-chart","https:\u002F\u002Fgithub.com\u002Fantvis\u002Fmcp-server-chart\u002Farchive\u002FHEAD.zip",4212,[18,19],[175,176],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T08:26:51.919558",{"slug":181,"name":182,"categorySlug":8,"summary":183,"description":184,"categoryName":11,"sourceUrl":185,"homepageUrl":-1,"downloadUrl":186,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":187,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":188,"clients":189,"tags":192,"installCommand":-1,"configSnippet":-1,"useCases":193,"updatedAt":194},"mobile-next-mobile-mcp","mobile-next\u002Fmobile-mcp","Model Context Protocol Server for Mobile Automation and Scraping (iOS, Android, Emulators, Simulators and Real Devices)","This is a Model Context Protocol (MCP) server that enables scalable mobile automation, development through a platform-agnostic interface, eliminating the need for distinct iOS or Android knowledge. You can run it on emulators, simulators, and real devices (iOS and Android). This server allows Agents and LLMs to interact with native iOS\u002FAndroid applications and devices through structured accessibility snapshots or coordinate-based taps based on screenshots.\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fbb084777-beb3-4930-ae6f-8d3fe694ddde\n\nJoin us on our journey as we continuously enhance Mobile MCP! Check out our detailed roadmap to see upcoming features, improvements, and milestones. Your feedback is invaluable in shaping the future of mobile automation.\n\n- 📲 Native app automation (iOS and Android) for testing or data-entry scenarios.","https:\u002F\u002Fgithub.com\u002Fmobile-next\u002Fmobile-mcp","https:\u002F\u002Fgithub.com\u002Fmobile-next\u002Fmobile-mcp\u002Farchive\u002FHEAD.zip",5352,[18,19],[190,191],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T04:31:50.678276",{"slug":196,"name":197,"categorySlug":8,"summary":198,"description":199,"categoryName":11,"sourceUrl":200,"homepageUrl":-1,"downloadUrl":201,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":202,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":203,"clients":204,"tags":207,"installCommand":-1,"configSnippet":-1,"useCases":208,"updatedAt":209},"lharries-whatsapp-mcp","lharries\u002Fwhatsapp-mcp","WhatsApp MCP server","This is a Model Context Protocol (MCP) server for WhatsApp.\n\nWith this you can search and read your personal Whatsapp messages (including images, videos, documents, and audio messages), search your contacts and send messages to either individuals or groups. You can also send media files including images, videos, documents, and audio messages.\n\nIt connects to your directly via the Whatsapp web multidevice API (using the whatsmeow library). All your messages are stored locally in a SQLite database and only sent to an LLM (such as Claude) when the agent accesses them through tools (which you control).\n\nHere's an example of what you can do when it's connected to Claude.\n\nTo get updates on this and other projects I work on enter your email here\n\nCaution: as with many MCP servers, the WhatsApp MCP is subject to the lethal trifecta. This means that project injection could lead to private data exfiltration.\n\n- Go - Python 3.","https:\u002F\u002Fgithub.com\u002Flharries\u002Fwhatsapp-mcp","https:\u002F\u002Fgithub.com\u002Flharries\u002Fwhatsapp-mcp\u002Farchive\u002FHEAD.zip",5865,[18,19],[205,206],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T04:31:40.987436",{"slug":211,"name":212,"categorySlug":8,"summary":213,"description":214,"categoryName":11,"sourceUrl":215,"homepageUrl":-1,"downloadUrl":216,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":217,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":218,"clients":219,"tags":222,"installCommand":-1,"configSnippet":-1,"useCases":223,"updatedAt":224},"microsoft-playwright-mcp","microsoft\u002Fplaywright-mcp","Playwright MCP server","A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. This server enables LLMs to interact with web pages through structured accessibility snapshots, bypassing the need for screenshots or visually-tuned models.\n\nThis package provides MCP interface into Playwright. If you are using a , you might benefit from using the CLI+SKILLS instead.\n\n- : Modern increasingly favor CLI–based workflows exposed as SKILLs over MCP because CLI invocations are more token-efficient: they avoid loading large tool schemas and verbose accessibility trees into the model context, allowing agents to act through concise, purpose-built commands. This makes CLI + SKILLs better suited for high-throughput coding agents that must balance browser automation with large codebases, tests, and reasoning within limited context windows. .","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fplaywright-mcp","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fplaywright-mcp\u002Farchive\u002FHEAD.zip",34581,[18,19],[220,221],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T04:31:02.803732",{"slug":226,"name":227,"categorySlug":8,"summary":228,"description":229,"categoryName":11,"sourceUrl":230,"homepageUrl":-1,"downloadUrl":231,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":232,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":233,"clients":234,"tags":237,"installCommand":-1,"configSnippet":-1,"useCases":238,"updatedAt":239},"liaokongvfx-mcp-chinese-getting-started-guide","liaokongvfx\u002Fmcp-chinese-getting-started-guide","Model Context Protocol(MCP) 编程极速入门","模型上下文协议（MCP）是一个创新的开源协议，它重新定义了大语言模型（LLM）与外部世界的互动方式。MCP 提供了一种标准化方法，使任意大语言模型能够轻松连接各种数据源和工具，实现信息的无缝访问和处理。MCP 就像是 AI 应用程序的 USB-C 接口，为 AI 模型提供了一种标准化的方式来连接不同的数据源和工具。\n\n- Resources 资源 - Prompts 提示词 - Tools 工具 - Sampling 采样 - Roots 根目录 - Transports 传输层\n\n因为大部分功能其实都是服务于 Claude 客户端的，本文更希望编写的 MCP 服务器服务与通用大语言模型，所以本文将会主要以“工具”为重点，其他功能会放到最后进行简单讲解。\n\n其中 MCP 的传输层支持了 2 种协议的实现：stdio（标准输入\u002F输出）和 SSE（服务器发送事件），因为 stdio 更为常用，所以本文会以 stdio 为例进行讲解。\n\n本文将会使用 3.11 的 Python 版本，并使用 uv 来管理 Python 项目。同时代码将会在文末放到 Github 上，废话不多说，我们这就开始吧~\n\n在这一小节中，我们将会实现一个用于网络搜索的服务器。首先，我们先来通过 uv 初始化我们的项目。\n\n然后我们来创建一个叫 web_search.py 文件，来实现我们的服务。MCP 为我们提供了2个对象：mcp.server.FastMCP 和 mcp.server.Server，mcp.server.FastMCP 是更高层的封装，我们这里就来使用它。\n\n实现执行的方法非常简单，MCP 为我们提供了一个 @mcp.tool() 我们只需要将实现函数用这个装饰器装饰即可。函数名称将作为工具名称，参数将作为工具参数，并通过注释来描述工具与参数，以及返回值。","https:\u002F\u002Fgithub.com\u002Fliaokongvfx\u002Fmcp-chinese-getting-started-guide","https:\u002F\u002Fgithub.com\u002Fliaokongvfx\u002Fmcp-chinese-getting-started-guide\u002Farchive\u002FHEAD.zip",3536,[18,19],[235,236],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T04:30:38.131225",{"slug":241,"name":242,"categorySlug":8,"summary":243,"description":244,"categoryName":11,"sourceUrl":245,"homepageUrl":-1,"downloadUrl":246,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":247,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":248,"clients":249,"tags":252,"installCommand":-1,"configSnippet":-1,"useCases":253,"updatedAt":254},"mark3labs-mcp-go","mark3labs\u002Fmcp-go","A Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.","A Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.\n\nMCP Go handles all the complex protocol details and server management, so you can focus on building great tools. It aims to be high-level and easy to use.\n\n* : High-level interface means less code and faster development * : Build MCP servers with minimal boilerplate * ***: MCP Go aims to provide a full implementation of the core MCP specification\n\n🚨 🚧 🏗️ MCP Go is under active development, as is the MCP specification itself. Core features are working but some advanced capabilities are still in progress.\n\nLet's create a simple MCP server that exposes a calculator tool and some data:\n\nThe Model Context Protocol (MCP) lets you build servers that expose data and functionality to LLM applications in a secure, standardized way. Think of it like a web API, but specifically designed for LLM interactions.","https:\u002F\u002Fgithub.com\u002Fmark3labs\u002Fmcp-go","https:\u002F\u002Fgithub.com\u002Fmark3labs\u002Fmcp-go\u002Farchive\u002FHEAD.zip",8852,[18,19],[250,251],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T04:31:25.789422",{"slug":256,"name":257,"categorySlug":8,"summary":258,"description":259,"categoryName":11,"sourceUrl":260,"homepageUrl":-1,"downloadUrl":261,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":262,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":263,"clients":264,"tags":267,"installCommand":-1,"configSnippet":-1,"useCases":268,"updatedAt":269},"lauriewired-ghidramcp","lauriewired\u002Fghidramcp","MCP Server for Ghidra","ghidraMCP is an Model Context Protocol server for allowing LLMs to autonomously reverse engineer applications. It exposes numerous tools from core Ghidra functionality to MCP clients.\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F36080514-f227-44bd-af84-78e29ee1d7f9\n\n- Decompile and analyze binaries in Ghidra - Automatically rename methods and data - List methods, classes, imports, and exports\n\nFirst, download the latest release from this repository. This contains the Ghidra plugin and Python MCP client. Then, you can directly import the plugin into Ghidra.\n\n1. Run Ghidra 2. Select File -> Install Extensions 3. Click the + button 4. Select the GhidraMCP-1-2.zip (or your chosen version) from the downloaded release 5. Restart Ghidra 6. Make sure the GhidraMCPPlugin is enabled in File -> Configure -> Developer 7. Optional: Configure the port in Ghidra with Edit -> Tool Options -> GhidraMCP HTTP Server\n\nhttps:\u002F\u002Fgithub.","https:\u002F\u002Fgithub.com\u002Flauriewired\u002Fghidramcp","https:\u002F\u002Fgithub.com\u002Flauriewired\u002Fghidramcp\u002Farchive\u002FHEAD.zip",9386,[18,19],[265,266],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T04:31:38.642792",{"slug":271,"name":272,"categorySlug":8,"summary":273,"description":274,"categoryName":11,"sourceUrl":275,"homepageUrl":-1,"downloadUrl":276,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":277,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":278,"clients":279,"tags":282,"installCommand":-1,"configSnippet":-1,"useCases":283,"updatedAt":284},"yzfly-awesome-mcp-zh","yzfly\u002Fawesome-mcp-zh","MCP 资源精选， MCP指南，Claude MCP，MCP Servers, MCP Clients","欢迎来到 Awesome-MCP-ZH，一个专为中文用户打造的 MCP（模型上下文协议）资源合集！ 这里有 MCP 的基础介绍、玩法、客户端、服务器和社区资源，帮你快速上手这个 AI 界的“万能插头”。\n\n- 如果国内的朋友想免费快速的体验MCP能力，推荐 Cherry Studio（客户端） + 阿里 Qwen (大模型）的组合，优势是免费、操作简单、LLM无需魔法、无需充值。\n\n- LLM 选型我的使用体感是： Claude4.5 > GPT-5 > Gemini-2.5 > Qwen3-Max > DeepSeek\n\n分析文章： - 10分钟搞定高德地图MCP！我用AI解决了约会地点选择难题 - 因为Manus爆火的 Claude MCP，90%人的认知可能都是错的 - 刚官宣支持MCP，就发布自家Agent协议（A2A），扒一扒Google暗藏的小心思 - 阿里云拥抱 MCP 这步棋，太多人都没有真正看懂 - 详解 MCP 传输机制\n\nMCP 全称 ，由 Anthropic 在 2024 年 11 月推出，是个开源通信标准。简单说，它给 AI 装了个“超级网线”，让 AI 能跟外部工具、数据、系统无缝对接。\n\n- ：AI 是个聪明但宅家的书呆子，MCP 就是它的“外卖员”，能帮它拿数据、干活儿。 - ：让 AI 不只聊天，还能真动手，比如查数据库、发邮件、写代码。\n\n微软出的面向初学者的 Model Context Protocol (MCP) 课程也不错，推荐一下： - mcp-for-beginners\n\n1. ：用 Slack 发消息、用 GitHub 管代码、用 Blender 建 3D 模型。 2. ：直接看你电脑文件、数据库记录，甚至网上实时信息。 3. ：写网页时，AI 能查代码、生成图片、调试页面，一条龙搞定。 4. ：AI 干一半问你意见，你点头它再继续。","https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-mcp-zh","https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-mcp-zh\u002Farchive\u002FHEAD.zip",7381,[18,19],[280,281],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T04:31:20.847612",{"slug":286,"name":287,"categorySlug":8,"summary":288,"description":289,"categoryName":11,"sourceUrl":290,"homepageUrl":-1,"downloadUrl":291,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":292,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":293,"clients":294,"tags":297,"installCommand":-1,"configSnippet":-1,"useCases":298,"updatedAt":299},"sansan0-trendradar","sansan0\u002Ftrendradar","⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。","- 感谢** 的观众们， 你所欲也， 我所欲也，两者得兼😍是对开源精神最好的支持\n\n💡 ： 1. ：下方表格记录了项目起步阶段（天使轮）的支持者。因早期人工统计繁琐，。 2. ：为了将有限的精力回归代码与功能迭代，。 无论名字是否上榜，你们的每一份支持都是 TrendRadar 能够走到今天的基石。🙏\n\n本项目使用 newsnow 项目的 API 获取多平台数据，特别感谢作者提供的服务。\n\n经联系，作者表示无需担心服务器压力，但这是基于他的善意和信任。请大家： - - Docker 部署时，请合理控制推送频率，勿竭泽而渔\n\n感谢**的朋友们，你们的慷慨已化身为键盘旁的零食饮料，陪伴着项目的每一次迭代。 ： 随着 v5.0.0 版本的发布，项目迈入了一个新的阶段。为了支持日益增长的 API 成本和咖啡因消耗，\"一元点赞\"通道现已重新开启。你的每一份心意，都将转化为代码世界里的 Token 和动力。🚀 前往支持\n\n若 TrendRadar 曾为你捕捉价值，不妨为它注入动力，助其持续进化 金额随意，1 元也是对开源的鼓励。欢迎在赞赏时备注留言 (´▽`ʃ♡ƪ)\n\n如果你在项目中使用或借鉴了本项目的思路、核心代码，**在 README 或文档中注明来源并附上本仓库链接。\n\n- ：适合具体的技术问题。提问时请提供完整信息（截图、错误日志等），有助于快速定位。 - ：建议优先在相关文章下的留言区交流。若需后台提问，**文章是最好的\"敲门砖\"，我在后台都能感受到这份心意哟 (´▽`ʃ♡ƪ)。 - ：关注公众号，回复「」即可加入。无论你是 AI 小白还是硬核开发者，想求助技术问题还是分享折腾心得，这里都欢迎你。群里主打互助交流和灵感碰撞，入群请先看群公告；提问时描述清楚问题、附上截图，群友有空就会帮忙，大家的实战经验往往比我一个人更快更全面 🤝","https:\u002F\u002Fgithub.com\u002Fsansan0\u002Ftrendradar","https:\u002F\u002Fgithub.com\u002Fsansan0\u002Ftrendradar\u002Farchive\u002FHEAD.zip",60418,[18,19],[295,296],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T04:31:10.12732",{"slug":301,"name":302,"categorySlug":8,"summary":303,"description":304,"categoryName":11,"sourceUrl":305,"homepageUrl":-1,"downloadUrl":306,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":307,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":308,"clients":309,"tags":312,"installCommand":-1,"configSnippet":-1,"useCases":313,"updatedAt":314},"supabase-mcp","supabase\u002Fmcp","Connect Supabase to your AI assistants","Connect your Supabase projects to Cursor, Claude, Windsurf, and other AI assistants.\n\nThe Model Context Protocol (MCP) standardizes how Large Language Models (LLMs) talk to external services like Supabase. It connects AI assistants directly with your Supabase project and allows them to perform tasks like managing tables, fetching config, and querying data. See the full list of tools.\n\nBefore setting up the MCP server, we recommend you read our security best practices to understand the risks of connecting an LLM to your Supabase projects and how to mitigate them.\n\nTo configure the Supabase MCP server on your client, visit our setup documentation. You can also generate a custom MCP URL for your project by visiting the MCP connection tab in the Supabase dashboard.\n\nYour MCP client will automatically prompt you to log in to Supabase during setup. Be sure to choose the organization that contains the project you wish to work with.","https:\u002F\u002Fgithub.com\u002Fsupabase\u002Fmcp","https:\u002F\u002Fgithub.com\u002Fsupabase\u002Fmcp\u002Farchive\u002FHEAD.zip",2777,[18,19],[310,311],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T04:30:41.054294",{"slug":316,"name":317,"categorySlug":8,"summary":318,"description":319,"categoryName":11,"sourceUrl":320,"homepageUrl":-1,"downloadUrl":321,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":322,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":323,"clients":324,"tags":327,"installCommand":-1,"configSnippet":-1,"useCases":328,"updatedAt":329},"xpzouying-xiaohongshu-mcp","xpzouying\u002Fxiaohongshu-mcp","MCP for xiaohongshu.com","MCP for 小红书 \u002F xiaohongshu.com。让你的 AI 助手直接访问小红书数据。\n\n- - xiaohongshu-mcp-skills（适用于已部署完本项目的用户） - xiaohongshu-skills（开箱即用版）\n\n- - ：安装插件即用，无需任何代码、代理或复杂的环境配置。 - ：直接在常用浏览器 (Chrome\u002FEdge) 及本地网络运行，无服务器 IP 风险，且能解决 90% 的部署报错。\n\n- ：haha.ai\u002Fxiaohongshu-mcp - ：Contributing Guide\n\n本项目所有的赞赏都会用于慈善捐赠。所有的慈善捐赠记录，请参考 DONATIONS.md。\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F8b05eb42-d437-41b7-9235-e2143f19e8b7\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fbd9a9a4a-58cb-4421-b8f3-015f703ce1f9\n\n- ✅ 稳定性更好，不依赖网络 - ✅ 上传速度更快 - ✅ 避免图片链接失效问题 - ✅ 支持更多图片格式","https:\u002F\u002Fgithub.com\u002Fxpzouying\u002Fxiaohongshu-mcp","https:\u002F\u002Fgithub.com\u002Fxpzouying\u002Fxiaohongshu-mcp\u002Farchive\u002FHEAD.zip",14473,[18,19],[325,326],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T04:31:32.445173",{"slug":331,"name":332,"categorySlug":8,"summary":333,"description":334,"categoryName":11,"sourceUrl":335,"homepageUrl":-1,"downloadUrl":336,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":337,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":338,"clients":339,"tags":342,"installCommand":-1,"configSnippet":-1,"useCases":343,"updatedAt":344},"kyopark2014-mcp","kyopark2014\u002Fmcp","It shows how to use model-context-protocol.","MCP(Model Context Protocol)은 생성형 AI application이 외부 데이터를 활용하는 주요한 인터페이스로 빠르게 확산되고 있습니다. 2024년 11월에 Anthropic의 오픈소스 프로젝트로 시작되었고, 현재 Cursor뿐 아니라 OpenAI에서도 지원하고 있습니다. 여기에서는 MCP with LangChain을 이용하여 LangGraph로 만든 application이 MCP를 활용하는 방법에 대해 설명합니다. 여기서 구현한 RAG는 Amazon의 완전관리형 RAG 서비스인 Knowledge base로 구현되었으므로, 문서의 텍스트 추출, 동기화, chunking과 같은 작업을 손쉽게 수행할 수 있으며, 멀티모달을 이용해 이미지\u002F표를 분석할 수 있습니다. 여기에서는 MCP server에서 RAG에 손쉽게 접근할 수 있도록 AWS Lambda를 이용해 API를 구성하였습니다.\n\n아래 architecture는 AWS 환경에서 MCP를 포함한 Agent를 구성하는것을 보여줍니다. Agent는 MCP server\u002Fclient 구조를 활용하여 외부의 데이터 소스를 활용할 수 있습니다. MCP client는 MCP server와 JSON-RPC 프로토콜에 기반하여 stdio\u002FSSE로 통신을 수행합니다. Stdio 사용시 MCP Server는 python, java와 같은 코드로 구성이 되고, client에서 요청이 오면 RAG나 인터넷등을 이용해 데이터를 수집하거나 전달하는 역할을 수행합니다. SSE로 할 경우에 MCP client와 server는 IP로 통신을 하게 됩니다. 여기서는 Streamlit을 이용해 application의 UI를 구성하고, 사용자는 ALB - CloudFront를 이용해 HTTPS 방식으로 브라우저를 통해 application을 이용합니다. 또한, 여기에서는 커스터마이징이 유리한 LangGraph를 이용해 MCP 기반의 application을 개발하는것을 설명합니다.","https:\u002F\u002Fgithub.com\u002Fkyopark2014\u002Fmcp","https:\u002F\u002Fgithub.com\u002Fkyopark2014\u002Fmcp\u002Farchive\u002FHEAD.zip",40,[18,19],[340,341],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T04:31:29.078586",{"slug":346,"name":347,"categorySlug":8,"summary":348,"description":349,"categoryName":11,"sourceUrl":350,"homepageUrl":-1,"downloadUrl":351,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":352,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":353,"clients":354,"tags":357,"installCommand":-1,"configSnippet":-1,"useCases":358,"updatedAt":359},"akash-network-mcp","akash-network\u002Fmcp","is a TypeScript implementation of a Model Context Protocol (MCP) server for interacting with the Akash Network.","is a TypeScript implementation of a Model Context Protocol (MCP) server for interacting with the Akash Network.\n\nThis project is still under development and not all tools are available. We are working on adding more tools and improving the server. We are open to contributions! See CONTRIBUTING.md for more details.\n\nThis server provides a bridge between AI agents and the Akash Network, allowing AI models to deploy applications, create leases, manage deployments, and interact with other Akash services directly through typed tools. It implements the Model Context Protocol, making it compatible with various AI platforms and tools.\n\n- : Handles Akash wallet authentication and client initialization - : Manages Akash certificates - : - Account address retrieval - Deployment creation, querying, updating, and termination - SDL (Stack Definition Language) operations - Bid management - Lease creation - Manifest deployment\n\n- Node.","https:\u002F\u002Fgithub.com\u002Fakash-network\u002Fmcp","https:\u002F\u002Fgithub.com\u002Fakash-network\u002Fmcp\u002Farchive\u002FHEAD.zip",12,[18,19],[355,356],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T04:31:47.791666",{"slug":361,"name":362,"categorySlug":8,"summary":363,"description":364,"categoryName":11,"sourceUrl":365,"homepageUrl":-1,"downloadUrl":366,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":367,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":368,"clients":369,"tags":372,"installCommand":-1,"configSnippet":-1,"useCases":373,"updatedAt":374},"tavily-ai-tavily-mcp","tavily-ai\u002Ftavily-mcp","Production ready MCP server with real-time search, extract, map & crawl.","The Tavily MCP server provides: - search, extract, map, crawl tools - Real-time web search capabilities through the tavily-search tool - Intelligent data extraction from web pages via the tavily-extract tool - Powerful web mapping tool that creates a structured map of website - Web crawler that systematically explores websites\n\n- Tutorial on combining Tavily MCP with Neo4j MCP server - Tutorial on integrating Tavily MCP with Cline in VS Code\n\nConnect directly to Tavily's remote MCP server instead of running it locally. This provides a seamless experience without requiring local installation or configuration.\n\nSimply use the remote MCP server URL with your Tavily API key:\n\nGet your Tavily API key from tavily.com.","https:\u002F\u002Fgithub.com\u002Ftavily-ai\u002Ftavily-mcp","https:\u002F\u002Fgithub.com\u002Ftavily-ai\u002Ftavily-mcp\u002Farchive\u002FHEAD.zip",2179,[18,19],[370,371],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T08:27:35.996642",4490,1,24]