Discover Awesome MCP Servers

AI Makerspace MCP Demo Server

Enables web search capabilities through the Tavily API and serves as a demonstration platform for building custom MCP tools. Designed for educational purposes to showcase MCP server development and LangGraph integration.

Bear MCP Server

Un servidor de Protocolo de Contexto de Modelo que permite a asistentes de IA como Claude leer notas de la aplicación para tomar notas Bear en un modo seguro y de solo lectura.

MCP SubMatcher

An MCP server that automatically renames local subtitle files to match corresponding videos using statistical token matching and episode verification. It enables users to scan media directories, preview matches, and manage subtitle configurations through natural language commands.

MCP Hardware Access Library

A Python framework that enables secure hardware control through the Model Context Protocol, allowing AI agents and automation systems to interact with physical devices across multiple platforms.

figma-pilot

Enables AI agents to create, modify, and manage Figma designs through natural language commands via a specialized MCP server and plugin bridge. It supports a wide range of operations including element creation, property modification, component management, and accessibility checks.

Excel Chart MCP Server

A dual-mode intelligent Excel processing server that provides Excel data analysis tools for Cursor AI in MCP mode and offers a standalone web interface with support for external AI configurations like DeepSeek.

Secure Command Executor MCP Server

Un servicio robusto de ejecución de comandos con rotación diaria de registros, diseñado para gestionar y ejecutar de forma segura comandos del sistema con comprobaciones de seguridad y registro.

Chargebee MCP Server

A server that integrates with AI-powered code editors to provide immediate answers about Chargebee products and API services, offering context-aware code snippets and access to Chargebee's knowledge base.

Nexus MCP for Obsidian

Turns your Obsidian vault into an MCP-enabled workspace with tools for reading/writing notes, managing folders, running semantic searches, and maintaining long-term memory—all while keeping data local to your vault.

Azure AI Agent Service MCP Server

Enables connections to Azure AI Agents within any MCP client, allowing users to leverage Azure AI Foundry's models and knowledge tools like Azure AI Search and Bing Web Grounding through a conversational interface.

hello-mcp-server-current-time

Okay, here's a simple example of a custom MCP (Model Control Plane) server based on `spring-ai-starter-mcp-server` that retrieves the current time, translated into Spanish: ```java import org.springframework.ai.chat.ChatClient; import org.springframework.ai.chat.ChatResponse; import org.springframework.ai.chat.prompt.PromptTemplate; import org.springframework.beans.factory.annotation.Autowired; import org.springframework.web.bind.annotation.GetMapping; import org.springframework.web.bind.annotation.RestController; import java.time.LocalDateTime; import java.time.format.DateTimeFormatter; import java.util.Map; @RestController public class TimeController { @Autowired private ChatClient chatClient; @GetMapping("/time") public String getCurrentTime() { LocalDateTime now = LocalDateTime.now(); DateTimeFormatter formatter = DateTimeFormatter.ofPattern("yyyy-MM-dd HH:mm:ss"); String formattedDateTime = now.format(formatter); // Use Spring AI to translate the time to Spanish. PromptTemplate promptTemplate = new PromptTemplate("Translate the following time to Spanish: {time}"); Map<String, Object> model = Map.of("time", formattedDateTime); ChatResponse response = chatClient.call(promptTemplate.create(model)); return response.getResult().getOutput(); } } ``` **Explanation:** 1. **Dependencies:** Make sure you have the necessary dependencies in your `pom.xml` or `build.gradle` file. Specifically, you'll need `spring-ai-core`, `spring-ai-spring-boot-starter`, and the specific AI model provider you want to use (e.g., `spring-ai-openai-spring-boot-starter`). The `spring-ai-starter-mcp-server` likely pulls in most of these, but double-check. 2. **`@RestController`:** This annotation marks the class as a REST controller, handling incoming web requests. 3. **`@Autowired ChatClient`:** This injects the `ChatClient` bean, which is the core component of Spring AI for interacting with language models. The `ChatClient` is configured by your `application.properties` or `application.yml` file (see below). 4. **`@GetMapping("/time")`:** This maps the `/time` endpoint to the `getCurrentTime()` method. When a GET request is made to `/time`, this method will be executed. 5. **`LocalDateTime.now()` and Formatting:** This gets the current date and time and formats it into a string. The `DateTimeFormatter` is used to create a specific format (yyyy-MM-dd HH:mm:ss). 6. **`PromptTemplate`:** This is the key part for using Spring AI. * `new PromptTemplate("Translate the following time to Spanish: {time}")`: This creates a prompt template. The `{time}` is a placeholder that will be replaced with the actual time. * `Map<String, Object> model = Map.of("time", formattedDateTime)`: This creates a map that contains the data to be used to fill in the placeholders in the prompt template. In this case, it maps the key "time" to the `formattedDateTime` string. * `chatClient.call(promptTemplate.create(model))`: This is where the magic happens. It calls the `ChatClient` with the prompt template and the data. The `ChatClient` sends the prompt to the configured language model (e.g., OpenAI, Azure OpenAI, etc.). 7. **`response.getResult().getOutput()`:** This extracts the translated time from the `ChatResponse` object. The `ChatResponse` contains the response from the language model. **Configuration (application.properties or application.yml):** You'll need to configure Spring AI to use a specific language model. Here's an example using OpenAI in `application.properties`: ```properties spring.ai.openai.api-key=YOUR_OPENAI_API_KEY spring.ai.chat.default-model=gpt-3.5-turbo ``` Or, in `application.yml`: ```yaml spring: ai: openai: api-key: YOUR_OPENAI_API_KEY chat: default-model: gpt-3.5-turbo ``` **Important Notes:** * **Replace `YOUR_OPENAI_API_KEY` with your actual OpenAI API key.** You'll need to sign up for an OpenAI account and get an API key. * **Model Selection:** `gpt-3.5-turbo` is a good general-purpose model. You can experiment with other models, but make sure they are compatible with the Spring AI OpenAI integration. * **Error Handling:** This is a very basic example and doesn't include error handling. In a real-world application, you should add error handling to catch exceptions that might occur when calling the language model. * **MCP Server Integration:** This example focuses on the core logic of getting the time and translating it. To integrate it with your `spring-ai-starter-mcp-server`, you'll need to deploy this controller as part of your MCP server application. The exact deployment steps will depend on how your MCP server is structured. You'll likely need to add this controller to the appropriate package and ensure that it's scanned by Spring. * **Prompt Engineering:** The prompt "Translate the following time to Spanish: {time}" is very simple. You can experiment with more complex prompts to get better results. For example, you could add instructions about the desired format of the translated time. * **Language Model Cost:** Be aware that using language models can incur costs, especially for more complex models or frequent requests. Monitor your usage and costs. * **Other AI Providers:** Spring AI supports other AI providers besides OpenAI, such as Azure OpenAI, Google Gemini, and Ollama. You can configure Spring AI to use a different provider by changing the configuration properties. **How to Run:** 1. Create a new Spring Boot project or add this code to your existing `spring-ai-starter-mcp-server` project. 2. Add the necessary dependencies to your `pom.xml` or `build.gradle` file. 3. Configure your `application.properties` or `application.yml` file with your OpenAI API key. 4. Run the Spring Boot application. 5. Access the endpoint `http://localhost:8080/time` (or whatever port your application is running on) in your browser or using a tool like `curl`. You should see the current time translated into Spanish. For example: ``` La hora actual es 2023-10-27 10:30:00. ``` This is a basic example, but it demonstrates the core concepts of using Spring AI to interact with a language model to translate text. Remember to adapt it to your specific needs and environment.

Maven Dependencies Server

Un servidor MCP (Protocolo de Contexto de Modelo) que proporciona herramientas para verificar las versiones de las dependencias de Maven. Este servidor permite a los LLM (Modelos de Lenguaje Grandes) verificar las dependencias de Maven y recuperar sus últimas versiones del Repositorio Central de Maven.

Dangerous MCP

Un servidor de demostración que revela riesgos de seguridad al acceder a variables de entorno confidenciales, ilustrando cómo las herramientas MCP pueden potencialmente filtrar datos de usuario sin consentimiento explícito.

Remote MCP Server Authless

A serverless solution for deploying Model Context Protocol (MCP) servers on Cloudflare Workers without authentication requirements, enabling developers to create and access custom AI tools through the MCP standard.

Consumer Rights Wiki MCP Server

Enables AI assistants to access the Consumer Rights Wiki, providing tools to search and retrieve information about modern consumer exploitation issues like privacy violations, dark patterns, and deceptive pricing practices.

Beagle Security MCP Server

Enables integration with Beagle Security API for managing security testing projects, applications, domain verification, and automated penetration tests. Provides 18 tools for creating, monitoring, and retrieving results from security assessments.

mtw-e2e-runner

JSON-driven E2E test runner for AI agents. Define browser tests as JSON action arrays and run them in parallel against a Chrome pool (browserless/chrome) with 28+ built-in actions, visual verification, network debugging, and flaky test detection.

Tavily Search

I am sorry, I cannot directly use Tavily Search to search for news pages or images. I am a text-based AI and do not have the capability to interact with external search engines or display images.

Cloud SQL Admin MCP Server

An MCP Server that enables interaction with Google Cloud SQL Admin API, allowing users to manage Cloud SQL database instances through natural language commands.

Facebook Ads MCP Server

Here are a few options, depending on the nuance you want to convey: **Option 1 (Most Direct):** > Servidor MCP para la entrada y evaluación de campañas publicitarias en Facebook utilizando Claude AI. **Option 2 (Slightly more descriptive, emphasizing the purpose):** > Servidor MCP para la gestión y análisis de campañas publicitarias en Facebook, impulsado por Claude AI. **Option 3 (Focusing on the input and processing):** > Servidor MCP para la introducción y el procesamiento de campañas publicitarias en Facebook con la ayuda de Claude AI. **Which one is best depends on the context. If you want a simple, direct translation, Option 1 is fine. If you want to emphasize the AI's role or the server's function, Option 2 or 3 might be better.**

Uber MCP Server

Enables AI assistants to interact with the Uber API for ride management, including requesting rides, obtaining price and time estimates, and tracking active trip status. It supports comprehensive journey features such as viewing ride history, cancelling requests, and rating drivers through a secure OAuth 2.0 integration.

My Awesome MCP

A basic MCP server template built with FastMCP framework that provides example tools for echoing messages and retrieving server information. Serves as a starting point for building custom MCP servers with both stdio and HTTP transport support.

even-better-playwright-mcp

An advanced Playwright MCP server that enables efficient browser automation through compressed accessibility snapshots, sandboxed code execution, and visual element labeling. It features 90% DOM compression and integrated DevTools for deep web inspection and interaction.

RednoteMCP

Enables automated interaction with Xiaohongshu (Little Red Book) to search for notes, retrieve content or comments, and post targeted smart comments. It utilizes Playwright to manage browser-based tasks such as secure login and automated engagement.

Google Workspace CRM MCP Server

A Python MCP server that provides a lightweight CRM by integrating Google Sheets, Gmail, and Google Docs for contact management, email communication, and document creation. It features 30 specialized tools, OAuth2 endpoint protection, and a comprehensive audit logging system.

Placeholder Image Generator

Generates customizable placeholder images with configurable dimensions, colors, and text using HTML5 Canvas. Supports multiple formats (PNG/JPEG) with automatic text scaling and contrast detection.

Python MCP Sandbox

Un entorno de ejecución de código Python interactivo que permite a los usuarios y a los LLM ejecutar código Python de forma segura e instalar paquetes en contenedores Docker aislados.

MCP File Compaction

Reduces Claude's context window costs by automatically summarizing inactive files to their public interfaces using AST parsing, keeping only the full contents of the currently active file.

Remote MCP Server (Authless)

Enables deployment of MCP servers on Cloudflare Workers without authentication requirements. Provides a template for creating custom MCP tools that can be accessed remotely via Cloudflare AI Playground or local MCP clients like Claude Desktop.