Discover Awesome MCP Servers

MCP fal.ai Image Server

Enables AI-powered image generation from text prompts using fal.ai models directly within IDEs. Supports multiple models, customizable parameters, and saves generated images locally with accessible file paths.

kaggle-mcp

Okay, I understand. I can act as a helpful assistant that translates text from English to Portuguese and also describes how I can interact with the Kaggle API to provide tools for searching and downloading datasets, and a prompt for generating EDA notebooks. Here's a breakdown of how I can do that: **1. Translation (English to Portuguese):** * I can translate any English text you provide into Portuguese. Just give me the English text, and I'll provide the Portuguese translation. For example: * **You:** "Hello, how are you?" * **Me:** "Olá, como você está?" **2. Kaggle API Interaction (Description):** While I can't directly execute code or interact with external APIs like the Kaggle API, I can describe how you would use it and provide the necessary code snippets and explanations. Here's how it would work: * **Kaggle API Setup:** You would need to install the Kaggle API client on your system (usually via `pip install kaggle`). You'd also need to authenticate by downloading your `kaggle.json` file from your Kaggle account settings and placing it in the appropriate directory (usually `~/.kaggle/`). * **Searching for Datasets:** You can use the Kaggle API to search for datasets based on keywords. Here's an example of how you would do it in Python: ```python import os os.environ['KAGGLE_CONFIG_DIR'] = '/content' # or wherever your kaggle.json is from kaggle.api.kaggle_api_extended import KaggleApi api = KaggleApi() api.authenticate() search_term = "machine learning" # Example search term datasets = api.dataset_list(search=search_term) for dataset in datasets: print(f"Dataset: {dataset.title}") print(f"URL: https://www.kaggle.com/datasets/{dataset.ref}") print(f"Description: {dataset.description}") print("-" * 20) ``` * **Explanation:** * The code imports the necessary libraries. * `api.authenticate()` authenticates you with the Kaggle API using your credentials. * `api.dataset_list(search=search_term)` searches for datasets matching the `search_term`. * The code then iterates through the results and prints the dataset title, URL, and description. * **Downloading Datasets:** Once you've found a dataset you want to download, you can use the Kaggle API to download it. Here's an example: ```python import os os.environ['KAGGLE_CONFIG_DIR'] = '/content' # or wherever your kaggle.json is from kaggle.api.kaggle_api_extended import KaggleApi api = KaggleApi() api.authenticate() dataset_name = "username/dataset-name" # Replace with the actual dataset name (e.g., "uciml/iris") download_path = "./data" # The directory where you want to download the dataset api.dataset_download_files(dataset_name, path=download_path, unzip=True) print(f"Dataset '{dataset_name}' downloaded to '{download_path}'") ``` * **Explanation:** * `dataset_name` should be replaced with the actual name of the dataset (found in the dataset's URL on Kaggle). * `download_path` specifies the directory where the dataset will be downloaded. * `api.dataset_download_files()` downloads the dataset and, if `unzip=True`, automatically unzips it. **3. Prompt for Generating EDA Notebooks:** I can provide a prompt that you can use with a large language model (LLM) like GPT-3 or similar to generate an EDA (Exploratory Data Analysis) notebook. The prompt would include instructions on what kind of analysis to perform. Here's an example prompt: ``` You are an expert data scientist. Generate a Python notebook using Pandas, Matplotlib, and Seaborn to perform exploratory data analysis (EDA) on the [DATASET_NAME] dataset. The dataset is located at [DATASET_PATH]. The notebook should include the following sections: 1. **Introduction:** A brief overview of the dataset and the goals of the EDA. 2. **Data Loading and Inspection:** * Load the dataset into a Pandas DataFrame. * Display the first few rows of the DataFrame. * Print the shape of the DataFrame. * Print the data types of each column. * Check for missing values and handle them appropriately (e.g., imputation or removal). 3. **Descriptive Statistics:** * Calculate and display descriptive statistics for numerical columns (mean, median, standard deviation, min, max, etc.). * Calculate and display value counts for categorical columns. 4. **Data Visualization:** * Create histograms for numerical columns to visualize their distributions. * Create box plots for numerical columns to identify outliers. * Create bar charts for categorical columns to visualize their frequencies. * Create scatter plots to explore relationships between numerical variables. * Create heatmaps to visualize correlations between numerical variables. 5. **Insights and Conclusions:** Summarize the key findings from the EDA and draw conclusions about the dataset. Be sure to include clear and concise comments throughout the notebook to explain each step. Use appropriate visualizations to effectively communicate the data insights. Assume the dataset is a CSV file. Replace [DATASET_NAME] with the actual name of the dataset and [DATASET_PATH] with the actual path to the dataset file. ``` * **Explanation:** * This prompt tells the LLM to act as a data scientist and generate a Python notebook. * It specifies the libraries to use (Pandas, Matplotlib, Seaborn). * It outlines the sections that the notebook should include, covering data loading, inspection, descriptive statistics, and data visualization. * It provides specific instructions for each section, such as creating histograms, box plots, and scatter plots. * It emphasizes the importance of clear comments and effective visualizations. * It includes placeholders for the dataset name and path, which you would need to replace with the actual values. **How to Use Me:** 1. **Translation:** Provide me with the English text you want to translate to Portuguese. 2. **Kaggle API:** Ask me how to perform a specific task with the Kaggle API (e.g., "How do I search for datasets about image classification?"). I'll provide the code snippet and explanation. Remember that you'll need to execute the code yourself. 3. **EDA Notebook Generation:** Ask me to generate a prompt for creating an EDA notebook. I'll provide a prompt like the one above, which you can then use with an LLM. Let me know what you'd like me to do first!

MCP Agent Social Media Server

Provides social media functionality for AI agents, enabling them to login with unique handles, read filtered posts, and create posts or replies within team-based discussions.

DBeaver MCP Server

A Model Context Protocol server that enables AI assistants to access and query 200+ database types through existing DBeaver connections without additional configuration.

mcp2tcp

Uma ponte que conecta hardware físico com grandes modelos de linguagem de IA através do Protocolo de Contexto de Modelo (MCP), permitindo o controle de dispositivos TCP por meio de linguagem natural.

MCP Server with Docker

A project that integrates Model Control Protocol with OpenAI's API, allowing OpenAI to access and utilize tools exposed by a dockerized MCP server.

This is MCP server for test

Servidor MCP para teste

⚡ go-mcp

⚡ Um SDK Go intuitivo e com segurança de tipos para construir servidores MCP com facilidade e confiança.

FL Studio MCP

Um servidor MCP que conecta o Claude ao FL Studio, permitindo que a IA componha música, controle instrumentos e grave melodias, acordes e baterias ao vivo no piano roll.

Bootstrap MCP Server

A minimal MCP server template with hot reload support that helps developers quickly set up and build Model Context Protocol servers with example tool implementations.

Coupler Analytics

Analytics Coupler.io MCP bridges your business data to AI for fast and smart analysis.

Misc MCP Server

A collection of MCP servers that enable users to interact with AdGuard Home through natural language commands, allowing management of DNS records and filtering rules.

MCP LLMS-TXT Documentation Server

Um servidor MCP de código aberto que fornece a aplicações como Cursor, Windsurf e Claude acesso a arquivos de documentação llms.txt, permitindo que os usuários controlem e auditem a recuperação de contexto.

MCP Server - Archi Track

Servidor MCP para pesquisar em uma API externa de uma aplicação web.

Dify Plugin Tools

Um plugin que permite ao Dify conectar-se a múltiplos servidores MCP (Model Control Protocol) usando HTTP com transporte Server-Sent Events, suportando configurações personalizadas para URLs, cabeçalhos e tempos limite.

prediction-market-mcp

A simple MCP server that grabs prediction market data from polymarket, PredictIt, & Kalshi.

Qwen MCP Tool

Enables AI assistants to leverage Qwen's code analysis capabilities with large context windows, supporting file/directory analysis, sandbox execution, and multiple approval modes for safe code operations.

MCP Feedback Collector

A modern Model Context Protocol (MCP) server that enables AI assistants to collect interactive user feedback, supporting text and image-based responses.

Kakao API MCP Server

Um servidor que permite que modelos de IA acessem funcionalidades do Kakao Map (busca de lugares, busca de endereços, cálculo de rotas) e serviços de busca do Daum (web, imagem, blog, café) através do Protocolo de Contexto de Modelo.

mcp-on-fire

Um repositório para MCP no Fire com um README incrível sobre o servidor GitHub MCP.

MCP S3 File Uploader

Enables secure file uploads to Amazon S3 with progress tracking and presigned URL generation. Provides automatic UUID-based file naming and time-limited access URLs for uploaded files.

Watch the tutorial video on how to create an MCP server from

O Servidor MCP Torobjo é uma implementação poderosa do Protocolo de Contexto de Modelo (MCP) para pesquisa de produtos e análise do Instagram. Ele se integra com a API Torob para pesquisas de produtos e extrai legendas do Instagram, apresentando um design modular para fácil utilização e desempenho otimizado.

Sleep MCP Server

Um servidor de Protocolo de Contexto de Modelo (MCP) que fornece uma ferramenta simples de suspensão/espera, útil para adicionar atrasos entre operações, como esperar entre chamadas de API ou testar sistemas eventualmente consistentes.

Dokploy MCP Server

Exposes Dokploy functionalities as tools consumable via the Model Context Protocol, allowing AI models and other applications to programmatically manage projects and applications on a Dokploy server.

Meilisearch MCP

Servidor para interagir com o Meilisearch através de interfaces LLM como o Claude.

Linear MCP Server

Uma implementação em Deno que permite que modelos de IA interajam com a funcionalidade de rastreamento de issues do Linear, suportando a busca de issues, leitura de detalhes, atualização e adição de comentários.

Helm Chart CLI

Helm Chart CLI

Scrapybara MCP

Um servidor de Protocolo de Contexto de Modelo que permite que clientes de IA interajam com desktops virtuais Ubuntu, permitindo que eles naveguem na web, executem código e controlem instâncias através de ações de mouse/teclado e comandos bash.

Fingertip MCP

A Model Context Protocol server that enables AI assistants to interact with Fingertip's site management capabilities, allowing them to list, view details of, and create websites.