Discover Awesome MCP Servers

Github Action Trigger Mcp

Un servidor de Protocolo de Contexto de Modelo que permite la integración con GitHub Actions, permitiendo a los usuarios obtener acciones disponibles, obtener información detallada sobre acciones específicas, activar eventos de envío de flujo de trabajo y obtener versiones del repositorio.

MCP Demo

Demonstrate an MCP server for fetching aviation weather data

NN-GitHubTestRepo

creado a partir de la demostración del servidor MCP

MCP Image Generation Server

Una implementación en Go de herramientas de servidor MCP (Protocolo de Contexto de Modelo).

Strava MCP Server

Un servidor de Protocolo de Contexto de Modelo que permite a los usuarios acceder a datos de fitness de Strava, incluyendo actividades del usuario, detalles de actividades, segmentos y tablas de clasificación a través de una interfaz API estructurada.

Selector Mcp Server

Un servidor de Protocolo de Contexto de Modelo (MCP) que permite un chat de IA interactivo y en tiempo real con Selector AI a través de un servidor con capacidad de transmisión y un cliente basado en Docker que se comunica a través de stdin/stdout.

Data.gov MCP Server

Espejo de

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.

MCP Server Playground

Un servidor MCP basado en TypeScript diseñado para la experimentación e integración con Calude Desktop y Cursor IDE, que ofrece un entorno de pruebas modular para extender las capacidades del servidor.

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.

repo-to-txt-mcp

Here are a few ways to translate "MCP server for analyzing and converting Git repositories to text files for LLM context" into Spanish, with slightly different nuances: * **Opción 1 (Más directa):** Servidor MCP para analizar y convertir repositorios Git a archivos de texto para el contexto de LLM. * **Opción 2 (Ligeramente más formal):** Servidor MCP para el análisis y la conversión de repositorios Git a archivos de texto para su uso en el contexto de LLM. * **Opción 3 (Enfatizando el propósito):** Servidor MCP para analizar repositorios Git y convertirlos en archivos de texto para proporcionar contexto a LLM. **Explanation of Choices:** * **MCP:** "MCP" is likely an acronym and should remain as is unless you know what it stands for and can translate that. * **LLM:** "LLM" (Large Language Model) is also an acronym and is often left as is in Spanish, especially in technical contexts. You *could* translate it to "MLG" (Modelo de Lenguaje Grande), but it's less common. * **"para":** This is the standard "for" in Spanish. * **"el análisis y la conversión":** Using the article "el/la" before the nouns makes it slightly more formal. * **"para su uso en el contexto de LLM":** This is a more verbose way of saying "for LLM context," emphasizing that the text files are *used* in that context. * **"para proporcionar contexto a LLM":** This option emphasizes the purpose of the conversion, which is to provide context to the LLM. **Recommendation:** I would recommend **Opción 1: Servidor MCP para analizar y convertir repositorios Git a archivos de texto para el contexto de LLM.** It's the most direct and commonly understood translation. If you want to be slightly more formal, use **Opción 2.**

Google Home MCP Server

Mirror of

mcp-server-restart

Mirror of

Semantic Scholar MCP Server

Espejo de

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

Fused MCP Agents: Setting up MCP Servers for Data

Un servidor MCP basado en Python que permite a Claude y otros LLM ejecutar código Python arbitrario directamente a través de tu aplicación de escritorio de Claude, permitiendo a los científicos de datos conectar LLM a APIs y código ejecutable.

HANA Cloud MCP Server

Espejo de

better-auth-mcp-server MCP Server

Mirror of

MCP Mistral OCR

Okay, I understand. You want to use the Mistral OCR API (paid) to extract text from images or PDFs, either from local files or from URLs, and you need help with the translation from English to Spanish. To give you the best assistance, I need a little more information. Specifically, I need to know: 1. **What kind of help do you need?** Are you looking for: * **Code examples?** (e.g., Python, JavaScript, etc.) * **Guidance on how to use the Mistral OCR API?** * **Help with structuring the API requests?** * **Help with handling the API responses?** * **Help with the translation process itself (after the OCR)?** * **Something else?** 2. **What programming language are you using (if any)?** This will help me provide relevant code examples. 3. **Do you have any existing code or have you already tried anything?** Sharing what you've already done will help me understand where you're stuck. 4. **Do you have the API key and know how to authenticate with the Mistral OCR API?** Once I have this information, I can provide more specific and helpful guidance. In the meantime, here's a general outline of the steps involved, along with some considerations for translation: **General Steps:** 1. **Authentication:** Authenticate with the Mistral OCR API using your API key. This usually involves including the key in the request headers. 2. **Prepare the Input:** * **Local Files:** Read the image or PDF file into memory. You might need libraries like `PIL` (Pillow) for images or `PyPDF2` or `pdfminer.six` for PDFs in Python. * **URLs:** Fetch the image or PDF from the URL using a library like `requests` in Python. 3. **Make the API Request:** Construct the API request according to the Mistral OCR API documentation. This will likely involve: * Specifying the file data (either as a base64 encoded string or using multipart/form-data). * Setting any other relevant parameters (e.g., language hints, output format). 4. **Handle the API Response:** * Check the response status code to ensure the request was successful (usually a 200 OK). * Parse the JSON response to extract the OCRed text. 5. **Translate the Text:** Use a translation API (like Google Translate API, DeepL API, or others) to translate the extracted text from English to Spanish. 6. **Handle Errors:** Implement error handling to gracefully manage potential issues like network errors, API errors, or invalid file formats. **Translation Considerations:** * **Translation API Choice:** Research and choose a translation API that meets your needs in terms of accuracy, cost, and features. * **API Limits:** Be aware of the rate limits and usage quotas of both the Mistral OCR API and the translation API. * **Error Handling:** Implement error handling for the translation API as well. * **Text Segmentation:** For large documents, you might want to break the text into smaller segments before translating to avoid exceeding API limits or encountering performance issues. * **Context:** Keep in mind that machine translation is not perfect. The accuracy of the translation can depend on the complexity of the text and the context. **Example (Conceptual - Python):** ```python import requests import base64 import json # Replace with your actual API keys and URLs MISTRAL_OCR_API_URL = "YOUR_MISTRAL_OCR_API_URL" MISTRAL_OCR_API_KEY = "YOUR_MISTRAL_OCR_API_KEY" TRANSLATION_API_URL = "YOUR_TRANSLATION_API_URL" # e.g., Google Translate API TRANSLATION_API_KEY = "YOUR_TRANSLATION_API_KEY" def ocr_and_translate(image_path): """ Performs OCR on an image and translates the extracted text to Spanish. """ try: # 1. Read the image file with open(image_path, "rb") as image_file: encoded_string = base64.b64encode(image_file.read()).decode("utf-8") # 2. Prepare the OCR API request headers = { "Authorization": f"Bearer {MISTRAL_OCR_API_KEY}", # Or however Mistral requires authentication "Content-Type": "application/json" # Adjust if needed } payload = { "image": encoded_string, "language": "eng" # English } # 3. Make the OCR API request response = requests.post(MISTRAL_OCR_API_URL, headers=headers, data=json.dumps(payload)) response.raise_for_status() # Raise HTTPError for bad responses (4xx or 5xx) # 4. Parse the OCR response ocr_data = response.json() extracted_text = ocr_data.get("text", "") # Adjust based on the actual response format # 5. Translate the text (using a placeholder translation function) translated_text = translate_text(extracted_text, "en", "es") # English to Spanish return translated_text except requests.exceptions.RequestException as e: print(f"Error during API request: {e}") return None except FileNotFoundError: print(f"Error: File not found at {image_path}") return None except Exception as e: print(f"An unexpected error occurred: {e}") return None def translate_text(text, source_language, target_language): """ Placeholder function for translating text using a translation API. Replace this with your actual translation API call. """ # Example using a hypothetical translation API # This is just an example; you'll need to adapt it to your chosen API. # You'll need to install the appropriate library (e.g., googletrans, deepl) # and handle authentication. # Example using Google Translate API (requires googletrans library) # from googletrans import Translator # translator = Translator() # translation = translator.translate(text, src=source_language, dest=target_language) # return translation.text # Example using DeepL API (requires deepl library) # import deepl # translator = deepl.Translator(TRANSLATION_API_KEY) # result = translator.translate_text(text, target_lang=target_language.upper()) # return result.text # For now, just return a placeholder return f"Translated text (from {source_language} to {target_language}): {text}" # Example usage image_file_path = "path/to/your/image.jpg" # Replace with the actual path translated_text = ocr_and_translate(image_file_path) if translated_text: print("Translated Text:\n", translated_text) else: print("Translation failed.") ``` **Important Notes:** * **Replace Placeholders:** Remember to replace the placeholder API URLs and keys with your actual credentials. * **Adapt to Mistral OCR API:** The code above is a general example. You'll need to carefully adapt it to the specific requirements of the Mistral OCR API, including the request format, authentication method, and response structure. Consult the Mistral OCR API documentation for details. * **Translation API Integration:** The `translate_text` function is a placeholder. You'll need to replace it with the actual code to call your chosen translation API. * **Error Handling:** The error handling in the example is basic. You should enhance it to handle different types of errors and provide more informative messages. * **PDF Handling:** If you're working with PDFs, you'll need to use a PDF library (like `PyPDF2` or `pdfminer.six`) to extract the images from the PDF before sending them to the OCR API. Alternatively, some OCR APIs might accept PDFs directly. Let me know the details I asked for above, and I'll be happy to provide more tailored assistance!

Clover MCP (Model Context Protocol) Server

Permite que los agentes de IA accedan e interactúen con los datos de comerciantes, el inventario y los pedidos de Clover a través de un servidor MCP seguro autenticado por OAuth.

GraphQL MCP Server

Un servidor TypeScript que proporciona a Claude AI acceso continuo a cualquier API GraphQL a través del Protocolo de Contexto de Modelo.

beeper_mcp MCP server

Un servidor MCP sencillo para crear y gestionar notas con soporte para la funcionalidad de resumen.

MCP with Gemini Tutorial

Construyendo servidores MCP con Google Gemini

Filesystem MCP Server

Servidor MCP de sistema de archivos mejorado