Discover Awesome MCP Servers

quickchart-server MCP Server

Um servidor MCP para gerar visualizações de dados personalizáveis usando QuickChart.io, com suporte para múltiplos tipos de gráficos e configuração do Chart.js.

mcp-server-cli

Model Context Protocol server to run shell scripts or commands

G-Search MCP

Um servidor MCP poderoso que permite a pesquisa paralela no Google com múltiplas palavras-chave simultaneamente, fornecendo resultados estruturados enquanto lida com CAPTCHAs e simula padrões de navegação do usuário.

Kafka MCP Server

Permite que modelos de IA publiquem e consumam mensagens de tópicos do Apache Kafka por meio de uma interface padronizada, facilitando a integração de mensagens do Kafka com LLMs e aplicações de agentes.

Notion MCP Server

Um servidor de Protocolo de Contexto de Modelo que fornece uma interface padronizada para modelos de IA acessarem, consultarem e modificarem conteúdo em espaços de trabalho do Notion.

filesystem

Um servidor de Protocolo de Contexto de Modelo que estende as capacidades de IA, fornecendo acesso ao sistema de arquivos e funcionalidades de gerenciamento para o Claude ou outros assistentes de IA.

Mcp Server Chatsum

Please provide me with the WeChat messages you want me to summarize. I need the text of the messages to be able to summarize them for you.

Japanese Text Analyzer MCP Server

Okay, I understand. I can't directly *execute* code or interact with files on your system. However, I can provide you with a Python script that accomplishes this task. I'll explain the code thoroughly so you can understand how it works and adapt it if needed. Here's the Python script: ```python import os import re import argparse import mojimoji # For normalizing Japanese text import subprocess # For calling MeCab def count_characters_and_words(filepath, language): """ Counts characters (excluding spaces and line breaks) and words in a text file. Args: filepath (str): The path to the text file. language (str): The language of the text file ('en' for English, 'ja' for Japanese). Returns: tuple: A tuple containing (character_count, word_count). Returns (None, None) on error. """ try: with open(filepath, 'r', encoding='utf-8') as f: text = f.read() except FileNotFoundError: print(f"Error: File not found: {filepath}") return None, None except UnicodeDecodeError: print(f"Error: Could not decode file {filepath} with UTF-8. Try a different encoding.") return None, None if language == 'en': # English: Simple word splitting and character counting text = text.strip() # Remove leading/trailing whitespace character_count = len(re.sub(r'\s', '', text)) # Remove all whitespace characters words = text.split() word_count = len(words) elif language == 'ja': # Japanese: Use MeCab for morphological analysis try: # Normalize text to full-width katakana for better MeCab performance normalized_text = mojimoji.zen_to_han(text, kana=False, ascii=False) normalized_text = mojimoji.han_to_zen(normalized_text, kana=True, ascii=False) # Call MeCab mecab_process = subprocess.Popen(['mecab'], stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True) mecab_output, mecab_error = mecab_process.communicate(normalized_text) if mecab_error: print(f"MeCab Error: {mecab_error}") return None, None # Count words based on MeCab output (first column of each line before the comma) words = [line.split(',')[0].split('\t')[0] for line in mecab_output.splitlines() if line.strip() != 'EOS'] word_count = len(words) # Count characters (excluding spaces and line breaks) character_count = len(re.sub(r'\s', '', text)) except FileNotFoundError: print("Error: MeCab is not installed or not in your PATH.") print("Please install MeCab and ensure it's accessible from the command line.") return None, None except Exception as e: print(f"An error occurred during Japanese processing: {e}") return None, None else: print("Error: Invalid language specified. Use 'en' or 'ja'.") return None, None return character_count, word_count def main(): parser = argparse.ArgumentParser(description="Counts characters and words in text files.") parser.add_argument("filepath", help="The path to the text file.") parser.add_argument("language", help="The language of the text file ('en' for English, 'ja' for Japanese).") args = parser.parse_args() filepath = args.filepath language = args.language char_count, word_count = count_characters_and_words(filepath, language) if char_count is not None and word_count is not None: print(f"File: {filepath}") print(f"Language: {language}") print(f"Character Count (excluding spaces): {char_count}") print(f"Word Count: {word_count}") if __name__ == "__main__": main() ``` **How to Use the Script:** 1. **Save the Code:** Save the code above as a Python file (e.g., `count_text.py`). 2. **Install Dependencies:** You'll need to install the `mojimoji` library and MeCab. Open your terminal or command prompt and run: ```bash pip install mojimoji ``` * **MeCab Installation:** MeCab is a morphological analyzer for Japanese. The installation process varies depending on your operating system: * **Linux (Debian/Ubuntu):** ```bash sudo apt-get update sudo apt-get install mecab libmecab-dev mecab-ipadic-utf8 ``` * **macOS (using Homebrew):** ```bash brew install mecab brew install mecab-ipadic ``` * **Windows:** The installation on Windows is more involved. I recommend following a tutorial like this one: [https://medium.com/@denis.akhapkin/installing-mecab-on-windows-10-8e318304985](https://medium.com/@denis.akhapkin/installing-mecab-on-windows-10-8e318304985). Make sure MeCab is added to your system's PATH environment variable. 3. **Run the Script:** Open your terminal or command prompt, navigate to the directory where you saved `count_text.py`, and run the script with the following command: ```bash python count_text.py <filepath> <language> ``` * Replace `<filepath>` with the actual path to your text file (e.g., `my_english_text.txt` or `my_japanese_text.txt`). * Replace `<language>` with either `en` for English or `ja` for Japanese. **Example:** ```bash python count_text.py my_english_text.txt en python count_text.py my_japanese_text.txt ja ``` **Explanation of the Code:** * **`import` Statements:** * `os`: (Not directly used in the current version, but good practice to include for potential file system operations). * `re`: For regular expressions (used to remove spaces). * `argparse`: For parsing command-line arguments (filepath and language). * `mojimoji`: For normalizing Japanese text (converting between full-width and half-width characters). This is important for MeCab's accuracy. * `subprocess`: For running the MeCab command-line tool. * **`count_characters_and_words(filepath, language)` Function:** * Takes the file path and language as input. * **File Handling:** Opens the file in UTF-8 encoding (important for handling Japanese characters). Includes error handling for `FileNotFoundError` and `UnicodeDecodeError`. * **English Processing (`language == 'en'`):** * Removes leading/trailing whitespace using `text.strip()`. * Counts characters by removing all whitespace characters (using `re.sub(r'\s', '', text)`) and then getting the length of the resulting string. * Splits the text into words using `text.split()`. * Counts the number of words. * **Japanese Processing (`language == 'ja'`):** * **Normalization:** Uses `mojimoji` to normalize the text. It converts half-width characters to full-width katakana and full-width characters to half-width ascii. This improves MeCab's performance. * **MeCab Integration:** * Uses `subprocess.Popen` to run the `mecab` command. * Passes the text to MeCab via standard input (`stdin`). * Captures MeCab's output from standard output (`stdout`). * Captures any errors from standard error (`stderr`). * **Error Handling:** Checks for MeCab errors and prints them if any occur. Also includes a `FileNotFoundError` check to see if MeCab is installed. * **Word Counting:** Parses the MeCab output. MeCab outputs each word on a separate line, with the word itself in the first column (before the first tab character). The code extracts these words and counts them. It skips the "EOS" (End of Sentence) marker. * **Character Counting:** Counts characters in the original text (excluding spaces and line breaks) using `len(re.sub(r'\s', '', text))`. * **Error Handling:** Handles invalid language input. * **Returns:** Returns the character count and word count as a tuple. * **`main()` Function:** * Uses `argparse` to handle command-line arguments. * Calls `count_characters_and_words()` to do the actual counting. * Prints the results. * **`if __name__ == "__main__":` Block:** * Ensures that the `main()` function is only called when the script is run directly (not when it's imported as a module). **Key Improvements and Considerations:** * **Japanese Morphological Analysis (MeCab):** The script now uses MeCab for Japanese word counting. This is *essential* for accurate word counts in Japanese because Japanese doesn't use spaces to separate words. * **Character Counting (Excluding Spaces):** The script correctly counts characters by removing spaces and line breaks using regular expressions. * **UTF-8 Encoding:** The script opens the files with UTF-8 encoding to handle Japanese characters correctly. * **Error Handling:** The script includes error handling for file not found, Unicode decoding errors, and MeCab errors. * **Command-Line Arguments:** The script uses `argparse` to make it easy to specify the file path and language from the command line. * **MeCab Installation:** The script provides instructions for installing MeCab on different operating systems. This is a crucial step. * **Normalization:** The script normalizes the Japanese text before passing it to MeCab. This can improve MeCab's accuracy. * **MeCab PATH:** Make sure MeCab is in your system's PATH environment variable so the script can find it. * **Alternative Japanese Tokenizers:** While MeCab is a good choice, other Japanese tokenizers exist (e.g., SudachiPy, Juman++). You could adapt the script to use a different tokenizer if you prefer. * **Large Files:** For very large files, you might want to consider reading the file in chunks to avoid loading the entire file into memory at once. **Example Usage (with sample files):** 1. **Create `my_english_text.txt`:** ``` This is a sample English text file. It has multiple lines. ``` 2. **Create `my_japanese_text.txt`:** ``` これは日本語のサンプルテキストファイルです。 複数の行があります。 ``` 3. **Run the script:** ```bash python count_text.py my_english_text.txt en python count_text.py my_japanese_text.txt ja ``` The script will print the character and word counts for each file. Remember to install MeCab *before* running the script with a Japanese file.

OpenAPI MCP Server

Esta ferramenta cria um servidor de Protocolo de Contexto de Modelo (MCP) que atua como um proxy para qualquer API que tenha uma especificação OpenAPI v3.1. Isso permite que você use o Claude Desktop para interagir facilmente com APIs de servidor locais e remotas.

EVM MCP Server

Um servidor abrangente que permite que agentes de IA interajam com múltiplas redes blockchain compatíveis com EVM através de uma interface unificada, suportando resolução ENS, operações com tokens e interações com contratos inteligentes.

openpyxl_mcp_server

Um wrapper fino em torno da biblioteca Python OpenPyXl que expõe operações de arquivos Excel como um servidor Model Context Protocol (MCP), permitindo que Claude e outros clientes MCP busquem e analisem dados de arquivos Excel.

Fused MCP Agents: Setting up MCP Servers for Data

Um servidor MCP baseado em Python que permite que Claude e outros LLMs executem código Python arbitrário diretamente através do seu aplicativo Claude para desktop, permitindo que cientistas de dados conectem LLMs a APIs e código executável.

Legion MCP (Model Context Protocol) Server

Um servidor que ajuda as pessoas a acessar e consultar dados em bancos de dados usando o Query Runner com integração do SDK Python do Protocolo de Contexto de Modelo (MCP). Suporta bancos de dados, incluindo: PostgreSQL Redshift MySQL Microsoft SQL Server APIs do Google Amazon Web Services (via boto3) CockroachDB SQLite

MCP GO Tools

A Go-focused Model Context Protocol (MCP) server that provides idiomatic Go code generation, style guidelines, and best practices. This tool helps Language Models understand and generate high-quality Go code following established patterns and conventions.

Math-MCP

Um servidor de Protocolo de Contexto de Modelo que fornece funções matemáticas e estatísticas básicas para LLMs, permitindo que eles realizem cálculos numéricos precisos através de uma API simples.

Linear MCP Server

Um servidor que permite que assistentes de IA acessem e recuperem dados de tickets do Linear através do padrão Model Context Protocol (MCP), atualmente focado em buscar os tickets "a fazer" de um usuário.

Github Action Trigger Mcp

Um servidor de Protocolo de Contexto de Modelo que permite a integração com o GitHub Actions, permitindo que os usuários busquem ações disponíveis, obtenham informações detalhadas sobre ações específicas, disparem eventos de despacho de fluxo de trabalho e busquem lançamentos de repositório.

➡️ browser-use mcp server

Um servidor MCP que permite que assistentes de IA controlem um navegador web através de comandos em linguagem natural, permitindo-lhes navegar em websites e extrair informações via transporte SSE.

MCP Image Generation Server

Uma implementação em Go de ferramentas de servidor MCP (Model Context Protocol).

Strava MCP Server

Um servidor de Protocolo de Contexto de Modelo que permite aos usuários acessar dados de condicionamento físico do Strava, incluindo atividades do usuário, detalhes das atividades, segmentos e placares de líderes por meio de uma interface de API estruturada.

Selector Mcp Server

Um servidor de Protocolo de Contexto de Modelo (MCP) que permite bate-papo de IA interativo e em tempo real com o Selector AI através de um servidor com capacidade de streaming e um cliente baseado em Docker que se comunica via stdin/stdout.

For the GitHub MCP

A LangGraph incorporating the Selector MCP Server and other MCP Servers as an example of a modern solution

Data.gov MCP Server

Espelho de

NN-GitHubTestRepo

criado a partir da demonstração do servidor MCP

Model Context Protocol (MCP)

The Model Context Protocol is an open standard that enables developers to build secure, two-way connections between their data sources and AI-powered tools. The architecture is straightforward: developers can either expose their data through MCP servers or build AI applications (MCP clients) that connect to these servers.

PHP MCP Protocol Server

Servidor MCP para PHP Universal - integra PHP com o protocolo Model Context Protocol

perplexity-server MCP Server

Perplexity MCP Server for Cline