Discover Awesome MCP Servers

Decision QC MCP Server

An MCP server that provides AI agents with structured devil's advocate counter-arguments for their decisions, charged per call in USDT. It exposes a decision_qc tool to evaluate a decision and return rebuttals, risks, and a self-reflection question.

Anchor MCP

Provides persistent, local-first long-term memory for LLMs using Voronoi-partitioned vector storage and local embeddings. It enables users to store, recall, and automatically retrieve project context and preferences entirely on their own machine.

Operational Ontology

Reference implementation of the Operational Ontology pattern: MCP tools are generated from a typed business domain model (objects, links, actions) — one tool per query shape and per action, deliberately no raw SQL tool. Writes pass business-rule preconditions, are audited, and write back to the systems of record; refusals are machine-readable. Ships with a demo orders ontology spanning two legacy

Qweather Mcp Server

API de Clima He Feng Serviço MCP (para fins de prática)

mochi-quest

Enables AI agents to act as personal growth coaches, allowing users to set goals, receive personalized daily tasks, and track progress with dynamic replanning and reward systems.

Daytona MCP Python Interpreter

A Model Context Protocol server that allows execution of Python code within Daytona workspaces, providing a secure and isolated environment for executing and managing Python scripts.

Brawl Stars MCP

Provides AI assistants with access to real-time Brawl Stars game data including player statistics, club information, brawler details, battle logs, and current events through the Brawl Stars API.

Reflex Docs MCP Server

Enables searching and retrieving Reflex documentation, including full-text search, code examples, error analysis, changelog, migration guides, API reference, component props, and recipes.

Pokémon MCP Server

Enables AI models to access comprehensive Pokémon data from PokéAPI and simulate battles between any two Pokémon with realistic mechanics including type effectiveness, stat-based damage calculations, and status effects.

Revternal MCP

Wraps the Revternal Developer Intelligence API, allowing AI agents to query Revternal data through natural language via the Pipeworx MCP gateway.

Pinako AI Bridge

Pinako AI Bridge is the MCP server that connects Pinako, a Chromium extension for tab, window, library, and bookmark management, to local AI clients including Claude Desktop, Claude Code, Cursor, Windsurf, Cline, Roo Code, and Continue.dev. The real payoff comes when you already use a desktop AI client: because the bridge runs inside that client alongside its other connect

ABAPilot

AI access to SAP ECC and on-premise S/4HANA: natural-language table queries, ABAP source reads, where-used lookups, syntax checks, dumps and background jobs — served by an in-system ABAP add-on behind a single ICF node, with no BTP, ADT or RISE dependency. Every call runs under the calling user's own SAP authorizations and is audit-logged inside the customer's system; the connector is MIT-licensed

expense-tracker-mcp

A local MCP server for managing personal expenses. Enables adding, listing, summarizing, editing, and deleting expenses, as well as adding credits, using PostgreSQL backend.

evite-mcp

MCP server for Evite that lets you read and act on events as guest or host: list events, view guest lists, RSVP, send messages, and create/edit events.

dsh-lab-ssh

Safety-gated SSH MCP server for DeepSeek Harness and standard MCP clients, enabling agents to use a laboratory server's GPU, runtime, and configured source workspace while keeping the server isolated from the public internet.

GreenCodeMCP

An MCP server that detects energy anti-patterns in Python code, retrieves optimization examples, suggests refactoring, validates correctness, and benchmarks resource gains, integrating with VS Code, Cursor, and Windsurf.

gmail-mcp

A local MCP server that gives Claude access to multiple Gmail accounts simultaneously for search, read, draft, send, label, and a scheduled cross-inbox digest, with enforced send policies per mailbox.

CarouselMCP

Generates ready-to-post Instagram carousel PNGs from a topic string, using AI (Gemini or Claude) for content and storing images in S3.

reaper-mcp

A comprehensive MCP server that enables AI assistants to control REAPER DAW for mixing, mastering, MIDI composition, and full music production workflows with 130 tools.

gyeongbuk-mcp

Enables AI agents to query Gyeongbuk public data such as hospitals, bus stops, traditional markets, population demographics, and regional safety grades through FastMCP.

Expense Tracker MCP Server

An AI-powered financial management engine that enables budgeting, smart expense tracking, and affordability analytics via the Model Context Protocol. It allows AI assistants to interact with financial data through natural language for tasks like category detection, bulk expense ingestion, and budget impact predictions.

KiCad MCP Server

A Model Context Protocol (MCP) server that exposes KiCad PCB design automation tools to AI assistants and other MCP clients.

Citadel MCP

A Code Mode MCP server that provides AI coding agents with curated, per-stack documentation as typed tools, enabling efficient document access and search across multiple stacks.

mcp-centreon

MCP server for Centreon IT monitoring that enables querying host/service status, managing acknowledgements and downtimes, and retrieving performance metrics via natural language.

adkit

Enables AI agents to create, manage, and automate Meta (Facebook/Instagram) ads campaigns via the Marketing API, with safe defaults and AI-generated creative.

Obsidian CLI MCP Server

Provides AI agents with Obsidian vault operations via the official CLI, including reading, writing, searching notes, and managing files, with security and concurrency protections.

Hacker News

Parsing HTML content from a website like Hacker News and providing structured data in Portuguese requires a multi-step process. Here's a breakdown of the process, along with considerations for translation: **1. Data Extraction (Web Scraping):** * **Libraries:** You'll need a library to fetch the HTML and parse it. Popular choices in Python are: * `requests`: For fetching the HTML content. * `Beautiful Soup 4`: For parsing the HTML and navigating the DOM (Document Object Model). * `lxml`: A faster XML/HTML processing library that can be used with Beautiful Soup. * **Hacker News Structure:** Hacker News has a relatively consistent HTML structure, but it's subject to change. You'll need to inspect the HTML source code of each page (top, new, ask, show, jobs) to identify the relevant HTML elements that contain the data you want to extract. Key elements to look for include: * `<tr>` (table rows): Hacker News uses tables extensively. * `<td>` (table data cells): Data is organized within table cells. * `<a>` (anchor tags): Links to the stories and comments. * `<span>` (span tags): Often used for points, comments, and other metadata. * **Extraction Logic:** You'll write code to: 1. Fetch the HTML content of the desired Hacker News page (e.g., `https://news.ycombinator.com/`). 2. Parse the HTML using Beautiful Soup. 3. Locate the relevant HTML elements based on their tags, classes, or IDs. 4. Extract the data from those elements (e.g., story title, URL, points, number of comments, author, age). 5. Organize the extracted data into a structured format (e.g., a list of dictionaries). **2. Data Structuring:** * **Data Model:** Define a data structure to represent each story. For example: ```python class Story: def __init__(self, title, url, points, comments, author, age, story_type): self.title = title self.url = url self.points = points self.comments = comments self.author = author self.age = age self.story_type = story_type # "top", "new", "ask", "show", "jobs" def __str__(self): return f"Title: {self.title}, URL: {self.url}, Points: {self.points}, Comments: {self.comments}, Author: {self.author}, Age: {self.age}, Type: {self.story_type}" ``` * **Data Cleaning:** Clean the extracted data. This might involve: * Removing extra whitespace. * Converting strings to numbers (e.g., points, comments). * Handling missing data (e.g., stories without URLs). **3. Translation to Portuguese:** * **Translation Libraries/APIs:** Use a translation library or API to translate the relevant text fields (e.g., story title, author, age). Popular options include: * `googletrans`: A free and easy-to-use Python library for Google Translate. (Note: Google Translate's free tier has limitations and may be unreliable for large-scale use.) * `DeepL API`: A paid API that offers high-quality translations. * `Microsoft Translator API`: Another paid API option. * `translate-toolkit`: A more complex but powerful library for localization and translation. * **Translation Logic:** 1. Identify the text fields that need to be translated. 2. Use the chosen translation library/API to translate each field from English to Portuguese. 3. Replace the original English text with the translated Portuguese text in your data structure. **4. Output:** * **Format:** Choose a format for outputting the structured data. Common options include: * JSON: A widely used format for data exchange. * CSV: Suitable for tabular data. * Python dictionaries/lists: If you're using the data within a Python application. * **Display/Storage:** Decide how you want to display or store the translated data. This could involve: * Printing it to the console. * Saving it to a file. * Displaying it in a web application. * Storing it in a database. **Example Code (Python with Beautiful Soup and `googletrans` - for demonstration purposes only, `googletrans` may have issues):** ```python import requests from bs4 import BeautifulSoup from googletrans import Translator # pip install googletrans==4.0.0-rc1 class Story: def __init__(self, title, url, points, comments, author, age, story_type): self.title = title self.url = url self.points = points self.comments = comments self.author = author self.age = age self.story_type = story_type def __str__(self): return f"Título: {self.title}, URL: {self.url}, Pontos: {self.points}, Comentários: {self.comments}, Autor: {self.author}, Idade: {self.age}, Tipo: {self.story_type}" def scrape_hacker_news(url, story_type): try: response = requests.get(url) response.raise_for_status() # Raise HTTPError for bad responses (4xx or 5xx) soup = BeautifulSoup(response.content, 'html.parser') stories = [] rows = soup.find_all('tr', class_='athing') for row in rows: title_element = row.find('a', class_='storylink') if not title_element: continue # Skip rows without a title link title = title_element.text.strip() url = title_element['href'] # Find the next row containing the story details (points, author, comments) details_row = row.find_next_sibling('tr') if not details_row: continue score_element = details_row.find('span', class_='score') points = int(score_element.text.split()[0]) if score_element else 0 age_element = details_row.find('span', class_='age') age = age_element.text.strip() if age_element else "Unknown" author_element = details_row.find('a', class_='hnuser') author = author_element.text.strip() if author_element else "Unknown" comments_link = details_row.find_all('a')[-1] # Last link is usually the comments link comments_text = comments_link.text.strip() comments = 0 if 'comment' in comments_text: try: comments = int(comments_text.split('\xa0')[0]) #Handles the &nbsp; character except ValueError: comments = 0 story = Story(title, url, points, comments, author, age, story_type) stories.append(story) return stories except requests.exceptions.RequestException as e: print(f"Error fetching URL: {e}") return [] except Exception as e: print(f"Error parsing HTML: {e}") return [] def translate_story(story, translator): try: story.title = translator.translate(story.title, dest='pt').text story.author = translator.translate(story.author, dest='pt').text story.age = translator.translate(story.age, dest='pt').text return story except Exception as e: print(f"Translation error: {e}") return story if __name__ == "__main__": top_stories_url = "https://news.ycombinator.com/" new_stories_url = "https://news.ycombinator.com/newest" # ... other URLs for ask, show, jobs translator = Translator() top_stories = scrape_hacker_news(top_stories_url, "top") new_stories = scrape_hacker_news(new_stories_url, "new") all_stories = top_stories + new_stories for story in all_stories: translated_story = translate_story(story, translator) print(translated_story) ``` **Important Considerations:** * **Website Terms of Service:** Always check the website's terms of service before scraping. Hacker News might have rules against scraping or rate limits. Respect their robots.txt file. * **HTML Structure Changes:** Websites change their HTML structure frequently. Your scraper will need to be updated whenever the Hacker News HTML changes. Use robust selectors that are less likely to break. * **Rate Limiting:** Be mindful of rate limiting. Don't make too many requests in a short period of time, or you might get blocked. Implement delays between requests. * **Error Handling:** Implement robust error handling to catch exceptions and prevent your scraper from crashing. * **Translation Quality:** Machine translation is not perfect. The quality of the translation will depend on the complexity of the text and the capabilities of the translation service. Consider using a professional translator for critical applications. * **`googletrans` Issues:** The `googletrans` library has been known to have issues with reliability and rate limiting. It's often better to use a paid translation API for production environments. * **Character Encoding:** Ensure that you're handling character encoding correctly, especially when dealing with non-ASCII characters. UTF-8 is generally a good choice. * **Asynchronous Requests:** For faster scraping, consider using asynchronous requests with libraries like `aiohttp`. This comprehensive guide provides a solid foundation for building a Hacker News scraper and translator. Remember to adapt the code and techniques to your specific needs and always respect the website's terms of service. Good luck!

mcp-brasil-gateway

MCP server that provides access to Brazilian public and commercial data, including CNPJ company info, government procurement (PNCP) searches, and FIPE vehicle pricing, with optional alert registration for new tenders.

WAT-AI-Broker

Acts as a bridge between an AI assistant and a WebApp Tinkerer instance, enabling live inspection and manipulation of applets in the browser.

arnfa-mcp

Enables AI agents to plan weather-aware trips across Thailand by providing real-time sky conditions, area search, and weather-fit itinerary generation for 150+ locations through Arnfa's API.