Discover Awesome MCP Servers

PlainlyVideosMCP

MCP server for Plainly Videos that allows browsing designs and projects, as well as rendering videos.

Remote MCP Server

A Cloudflare-deployable server that implements Model Context Protocol (MCP) capabilities, allowing AI assistants like Claude to access custom tools via OAuth authentication flows.

SVG Maker MCP Server

Enables creation, validation, rendering, and optimization of SVG images with conversion capabilities to PNG, React components, React Native components, and Data URIs.

Local Stock Analyst MCP

Provides comprehensive stock analysis tools for real-time market data, technical indicators, and portfolio evaluations using Finnhub and Alpha Vantage. It supports both stdio and Render-compatible HTTP transport modes for flexible integration across environments.

lake-dayz

An MCP server that pre-flights DayZ Enforce mods, catching boot-crashing mistakes before packing PBO files.

MCP Performance Analyzer

Monitors and analyzes mobile application performance data to detect severe issues such as excessive memory usage and view count growth. Provides intelligent analysis with customizable rules and integrates seamlessly with development workflows.

LeBonFoin MCP

French marketplace MCP server for artisanal hemp/CBD products. Exposes 10 tools (product search, personalized recommendations, comparison, producer info with geolocation, stock availability, market prices "Bloomberg CBD", complete CBD guides, news, wiki search, full wiki article) + 4 resources (catalog, producers map, CBD reference covering France + 12 EU countries, wiki catalog).

zencontrol-cloud-mcp

Enables AI assistants to discover and control ZenControl DALI-2 lighting systems through natural language via the ZenControl Cloud API.

HederaOracle

9 MCP tools for DeFi risk & compliance on Hedera

stats-compass-mcp

Stats Compass provides various analysis and modelling tools for AI-automated data science workflows

spicelib-mcp

A thin MCP server that wraps spicelib for circuit simulation. Exposes tools for running AC, transient, DC op, and parameter sweep analyses, enabling behavioral model fitting through iterative simulation and measurement comparison.

Wolfram Alpha

To connect your chat repl to Wolfram Alpha's computational intelligence, you'll typically use the Wolfram Alpha API. Here's a breakdown of the process and code examples in Python (since that's a common language for repl.it): **1. Get a Wolfram Alpha API Key:** * Go to the Wolfram Alpha Developer Portal: [https://developer.wolframalpha.com/](https://developer.wolframalpha.com/) * Create an account (if you don't have one). * Create a new App. Give it a name and description. * You'll receive an App ID. This is your API key. **Keep this key secret!** Don't commit it directly to your repl.it code. We'll use environment variables to store it securely. **2. Set up your repl.it environment:** * Create a new repl.it project (choose Python). * **Set up Environment Variables:** This is crucial for security. * In your repl.it project, look for the "Secrets" (or "Tools" -> "Secrets") section in the left sidebar. * Add a new secret with the key `WOLFRAM_ALPHA_APP_ID` and the value being your actual Wolfram Alpha App ID. **3. Install the Wolfram Alpha Python Library:** * In your repl.it project, open the "Shell" (or "Terminal"). * Run the following command to install the library: ```bash pip install wolframalpha ``` **4. Python Code Example:** ```python import wolframalpha import os # Get the Wolfram Alpha App ID from the environment variable app_id = os.environ.get("WOLFRAM_ALPHA_APP_ID") if not app_id: print("Error: WOLFRAM_ALPHA_APP_ID environment variable not set. Please configure it in repl.it Secrets.") exit() client = wolframalpha.Client(app_id) def ask_wolfram(query): """ Sends a query to Wolfram Alpha and returns the result. """ try: res = client.query(query) # Check if there are any results if res.results: # Get the first result (usually the most relevant) result = next(res.results).text return result else: return "Wolfram Alpha couldn't find an answer." except Exception as e: return f"Error communicating with Wolfram Alpha: {e}" # Example usage (replace with your chat logic) while True: user_input = input("Ask Wolfram Alpha: ") if user_input.lower() == "exit": break answer = ask_wolfram(user_input) print(answer) ``` **Explanation:** * **`import wolframalpha`:** Imports the necessary library. * **`import os`:** Imports the `os` module to access environment variables. * **`app_id = os.environ.get("WOLFRAM_ALPHA_APP_ID")`:** Retrieves the API key from the environment variable. This is the secure way to store your key. * **`client = wolframalpha.Client(app_id)`:** Creates a Wolfram Alpha client object, using your API key. * **`ask_wolfram(query)` function:** * Takes a query string as input. * Uses `client.query(query)` to send the query to Wolfram Alpha. * Iterates through the results (`res.results`). Wolfram Alpha can return multiple results, but we usually want the first one. * `next(res.results).text` extracts the text from the first result. * Error handling: Includes a `try...except` block to catch potential errors (like network issues or invalid queries). * **Example Usage:** * A simple `while` loop allows you to repeatedly ask Wolfram Alpha questions. * `input()` gets the user's question. * `ask_wolfram()` sends the question to Wolfram Alpha. * The answer is printed to the console. **How to Use it in a Chatbot:** 1. **Integrate with a Chat Framework:** You'll need a chatbot framework (e.g., Flask, Django, or a simpler library like `telepot` for Telegram bots) to handle user input and send responses. 2. **Receive User Input:** Your chatbot framework will provide a way to receive messages from the user. 3. **Pass the Input to `ask_wolfram()`:** Take the user's message and pass it as the `query` to the `ask_wolfram()` function. 4. **Send the Response:** Take the result returned by `ask_wolfram()` and send it back to the user through your chatbot framework. **Example with Flask (very basic):** ```python from flask import Flask, request import wolframalpha import os app = Flask(__name__) app_id = os.environ.get("WOLFRAM_ALPHA_APP_ID") if not app_id: print("Error: WOLFRAM_ALPHA_APP_ID environment variable not set.") exit() client = wolframalpha.Client(app_id) def ask_wolfram(query): try: res = client.query(query) if res.results: result = next(res.results).text return result else: return "Wolfram Alpha couldn't find an answer." except Exception as e: return f"Error: {e}" @app.route('/', methods=['POST']) def chat(): message = request.form['message'] # Assuming you're sending the message in a form answer = ask_wolfram(message) return answer # Returns the answer as the response if __name__ == '__main__': app.run(debug=True, host='0.0.0.0', port=8080) ``` **Important Considerations:** * **Error Handling:** The code includes basic error handling, but you should add more robust error handling for production environments. Consider logging errors to a file or service. * **Rate Limiting:** The Wolfram Alpha API has rate limits. Be mindful of how many requests you're making per second/minute/day. Implement caching or other strategies to reduce the number of API calls if necessary. Check the Wolfram Alpha Developer Portal for the specific rate limits for your API key. * **API Key Security:** **Never** hardcode your API key directly into your code. Always use environment variables or a secure configuration management system. * **User Input Sanitization:** If you're taking user input and directly passing it to Wolfram Alpha, be aware of potential security risks (e.g., code injection). Sanitize the input to prevent malicious code from being executed. However, Wolfram Alpha is generally good at handling potentially harmful input, but it's still a good practice. * **Result Parsing:** Wolfram Alpha can return complex results. The `next(res.results).text` approach gets the first text result, but you might need to parse the results more carefully to extract specific information (e.g., images, tables, etc.). The `wolframalpha` library provides access to the full result structure. * **Asynchronous Operations:** For more complex chatbots, consider using asynchronous operations (e.g., `asyncio` in Python) to avoid blocking the main thread while waiting for Wolfram Alpha to respond. This will improve the responsiveness of your chatbot. This comprehensive guide should get you started with connecting your repl.it project to Wolfram Alpha. Remember to replace `"YOUR_WOLFRAM_ALPHA_APP_ID"` with your actual App ID and adapt the code to fit your specific chatbot needs. Good luck!

Clean-Cut-MCP

Enables users to create professional React-powered videos through Claude Desktop using natural language and the Remotion framework. It provides a persistent studio environment for generating animations, managing video assets, and rendering high-quality content.

Obsidian iCloud MCP

Kết nối các vault Obsidian được lưu trữ trong iCloud Drive với các mô hình AI thông qua Giao thức Ngữ cảnh Mô hình (Model Context Protocol), cho phép các trợ lý AI truy cập và tương tác với các ghi chú Obsidian của bạn.

MCP Linux Deployment

Enables management of Windows servers from Linux through an MCP server with per-user installation. Provides tools to control Windows systems via API with secure credential management.

Medical MCP Server

Enables medical information retrieval and drug interaction checking via MCP, integrating a local knowledge base with Grok AI for fallback queries.

Excel MCP Server

Gương của

OpenAPI MCP Server

A generic MCP server that dynamically converts OpenAPI-defined REST APIs into tools for LLMs like Claude. It supports multiple authentication methods and transport protocols, enabling seamless interaction with any OpenAPI-compliant API.

Microsoft 365 MCP

Enables LLMs to manage your Microsoft 365 calendar, tasks, and email via Microsoft Graph API, acting as a personal secretary.

dynatrace-mcp

This remote MCP server allows interaction with the Dynatrace observability platform. Bring real-time observability data directly into your development workflow.

crawl-mcp

MCP server for web crawling, searching, and AI-powered content extraction, supporting single-page, batch, and full-site crawling along with text, news, image, book, and video search.

local-mysql

Provides read-only access to a local MySQL database, enabling SQL queries, database and table listings, and table schema descriptions.

Happy MCP Server

A metadata-driven MCP server that auto-generates 480+ tools across 160+ ServiceNow tables, with multi-instance support, natural language search, and local script development.

mcp-archimate

Enables querying and modifying ArchiMate enterprise architecture models from XML or Archi Tool files via REST API and MCP server, supporting multiple simultaneous data sources.

Open Primitive

26 US federal data domains as 23 MCP tools. Ed25519 signed responses. Free, no API key.

Oplink

Enables creating no-code agent workflows by combining multiple MCP servers into unified YAML-defined tools. Supports parameterized prompts and scripted steps, exposing a single MCP endpoint that orchestrates external servers like Chrome DevTools and shadcn.

unofficial-solaredge-mcp

A lean Model Context Protocol (MCP) server that gives AI assistants like Claude structured access to a SolarEdge PV installation via the official SolarEdge Monitoring API.

Kaggle Dataset Analyst

Enables exploratory data analysis and machine learning on CSV datasets with tools for profiling, missing values, correlation, plotting, model training, and prediction.

MCP Debugger

Enables debugging of Python, JavaScript/TypeScript, Go, and Rust code using real debuggers with breakpoints, stepping, variable inspection, and stack trace navigation through the Debug Adapter Protocol.