Discover Awesome MCP Servers

HISE MCP Server

Provides access to HISE documentation, including UI component properties, Scripting API methods, and module parameters. It features a searchable database of code snippets and best practices to assist in audio software development.

Mother MCP Skills

Automatically discovers and installs AI skills for your project's tech stack, supporting Claude, Copilot, Codex, and other MCP-compatible agents.

Orshot

Orshot's MCP Server lets you dynamically generate images from your templates from your prompts in Claude, Cursor or any app that supports MCP Servers. You can use the pre-designed templates and also AI Generate or design your own templates in Orshot, and then generate images from those templates

mcp-sqlserver

An MCP server for Microsoft SQL Server that enables executing read-only queries, listing tables, and describing database schemas. It offers specialized support for custom ports and multiple authentication methods including SQL credentials, NTLM, and Windows Integrated Auth.

kintone MCP Server

Official MCP server for kintone, enabling AI assistants to manage kintone apps, records, and settings through natural language.

memos-mcp-server

Enables AI assistants to create, read, update, delete, and list memos via the MCP protocol.

Black-Scholes MCP Server

Enables calculation of European option prices and Greeks (like Delta, Vega, Theta) using the Black-Scholes model through a Model Context Protocol implementation.

google_maps_mcp

Enables querying Google Maps and Places APIs for local businesses and tourist attractions in India through a simple MCP interface.

Plantos MCP Server

Enables AI assistants to analyze farm locations, retrieve soil and weather data, access commodity market prices, and chat with an agricultural advisor for farming recommendations.

Google Images Search MCP

MCP server for searching images with Google

Git Helper MCP

Enables Claude to interact with git repositories by providing real-time access to repository status, branch information, commit history, and file changes. Allows users to query their git workspace through natural language commands.

MCP Server Boilerplate

A TypeScript template for building Model Context Protocol servers with example tools, type-safe validation, and best practices for integrating custom functionality with AI assistants like Cursor and Claude.

cointelegraph-mcp

关于 一个MCP服务器，提供来自Cointelegraph的最新新闻的实时访问。

Second Brain MCP

Enables querying Tom Osborne's voice-cloned AI agent with a 21,000-article marketing knowledge base and his interview corpus to get answers in his voice.

Fabric Admin MCP Server

Provides MCP tools to manage Microsoft Fabric capacities, including listing, creating, updating, and deleting them, using Azure authentication.

Gramps MCP

Enables AI assistants to interact with Gramps genealogy databases for intelligent family tree research and management. Provides comprehensive tools for searching family data, creating records, analyzing relationships, and tracking genealogy research through natural language.

Logstash MCP Server

A Model Context Protocol server that provides comprehensive tools for monitoring and identifying performance bottlenecks in Logstash instances through an interactive web UI and JSON-RPC interface.

MCP Demo

使用 Python 构建 Slack 的 MCP（管理控制面板）服务器。

Local Mcp Server Tutorial

好的，以下是一个创建本地 MCP 服务器（stdio）的教程： **创建本地 MCP 服务器 (stdio) 教程** **什么是 MCP？** MCP (Minecraft Coder Pack) 是一个用于反编译、反混淆和重新编译 Minecraft 代码的工具。它允许开发者更容易地理解和修改 Minecraft 的内部工作原理。 **什么是 stdio？** stdio (standard input/output) 是一种通信方式，允许程序通过标准输入和标准输出流进行交互。在这种情况下，本地 MCP 服务器将通过 stdio 与客户端进行通信。 **步骤：** **1. 安装 Java Development Kit (JDK)** 确保你的系统上安装了 Java Development Kit (JDK)。你需要 JDK 8 或更高版本。你可以从 Oracle 网站或你的发行版的包管理器下载并安装 JDK。 **2. 下载 MCP** 从 MCP 的官方网站或 GitHub 仓库下载最新版本的 MCP。 **3. 解压 MCP** 将下载的 MCP 压缩包解压到你选择的目录。 **4. 配置 MCP** * **`conf/mcp.cfg`:** 打开 `conf/mcp.cfg` 文件并根据你的需要进行配置。重要的配置项包括： * `MCP_LOC`: MCP 的根目录。 * `SRG_DIR`: SRG (Searge) 映射文件的目录。 * `BIN_DIR`: Minecraft 客户端和服务器 jar 文件的目录。 * `PATCHES_DIR`: 补丁文件的目录。 * `REOBF_PATCHES_DIR`: 反混淆补丁文件的目录。 * `DOCS_DIR`: 文档文件的目录。 * `VERSION`: Minecraft 的版本。 * **`conf/versions.cfg`:** 确保 `conf/versions.cfg` 文件包含你想要使用的 Minecraft 版本的配置。 **5. 获取 Minecraft 客户端和服务器 jar 文件** 你需要获取与你想要使用的 Minecraft 版本相对应的客户端和服务器 jar 文件。你可以从 Minecraft 启动器或 Minecraft 官方网站下载这些文件。将这些文件放置在 `jars/` 目录下。 **6. 反编译 Minecraft** 打开命令行终端，导航到 MCP 的根目录，并运行以下命令： ```bash ./decompile.sh ``` 或者，在 Windows 上： ```batch decompile.bat ``` 这将反编译 Minecraft 客户端和服务器代码。这个过程可能需要一些时间。 **7. 创建 stdio 服务器** 创建一个 Java 程序，该程序将作为本地 MCP 服务器运行。以下是一个简单的示例： ```java import java.io.BufferedReader; import java.io.IOException; import java.io.InputStreamReader; import java.io.PrintWriter; public class MCPStdioServer { public static void main(String[] args) throws IOException { BufferedReader reader = new BufferedReader(new InputStreamReader(System.in)); PrintWriter writer = new PrintWriter(System.out, true); String line; while ((line = reader.readLine()) != null) { // 在这里处理来自客户端的请求 // 例如，你可以执行 MCP 命令并返回结果 // 示例：将收到的消息回显给客户端 writer.println("Server received: " + line); } } } ``` **8. 编译 stdio 服务器** 使用 JDK 编译你的 Java 程序。 ```bash javac MCPStdioServer.java ``` **9. 运行 stdio 服务器** 运行编译后的 Java 程序。 ```bash java MCPStdioServer ``` **10. 创建客户端** 创建一个客户端程序，该程序将通过 stdio 与本地 MCP 服务器进行通信。你可以使用任何编程语言来创建客户端。 **11. 与服务器通信** 客户端程序需要通过标准输入向服务器发送请求，并通过标准输出接收响应。 **示例客户端 (Python):** ```python import sys def send_command(command): print(command, flush=True) # 发送命令并刷新输出 response = sys.stdin.readline().strip() # 读取服务器的响应 return response if __name__ == "__main__": response = send_command("Hello from client!") print("Server response:", response) response = send_command("Another command") print("Server response:", response) ``` **运行客户端:** ```bash python your_client.py ``` **重要提示：** * 你需要根据你的具体需求修改服务器和客户端代码。 * 你需要实现 MCP 命令的处理逻辑，以便服务器能够执行客户端请求的操作。 * 确保你的服务器和客户端使用相同的协议进行通信。 **总结：** 这个教程提供了一个创建本地 MCP 服务器 (stdio) 的基本框架。你需要根据你的具体需求进行修改和扩展。记住，理解 MCP 的工作原理以及 Minecraft 的代码结构对于成功创建本地 MCP 服务器至关重要。 希望这个教程对你有所帮助！

academic-mcp

Unified academic search MCP server that searches open literature (arXiv, bioRxiv, medRxiv, PMC), CNKI, and Web of Science, with browser-backed authentication, local paper library, and export to multiple formats.

Open Food Facts MCP Server

Enables AI assistants to access the Open Food Facts database to query detailed food product information, nutritional data, and environmental scores. Supports product lookup by barcode, smart search with filtering, nutritional analysis, product comparison, and dietary recommendations to help users make informed food choices.

AnalyticDB for MySQL MCP Server

镜子 (jìng zi)

MCP Gemini Server

镜子 (jìng zi)

Optimization MCP

Provides nine specialized production-ready solvers for advanced resource allocation, network flow, and multi-objective optimization with native Monte Carlo integration. It enables users to perform constraint-based decision-making and performance analysis directly through Claude Code.

OpenWebGAL Assistant

MCP server that automates WebGAL game development tasks such as resource management, script editing, documentation lookup, and AI-powered voice generation using LLMs.

MCP Smart Searcher

A smart MCP server for multi-engine web search with AI-powered results, supporting 6 search engines and web content extraction.

Agent Factory MCP

A universal MCP server that automatically discovers and registers CLI tools as AI-powered agents with persona configuration, enabling any CLI tool to be used as an MCP tool.

VMware Fusion MCP Server

A Model Context Protocol server that allows managing VMware Fusion virtual machines through natural language, enabling users to list VMs, retrieve VM information, and perform power operations via the Fusion REST API.

Remote MCP Server on Cloudflare

A template for deploying secure Model Context Protocol servers to Cloudflare Workers with built-in OAuth authentication. It enables hosting and connecting remote tools to Claude Desktop using SSE transport and a local proxy.

MaxKB

💬 MaxKB is a ready-to-use RAG chatbot that features robust workflow and MCP tool-use capabilities. It supports a wide range of mainstream large language models (LLMs), including DeepSeek-R1, Llama 3.3, OpenAI, among others.