Discover Awesome MCP Servers

vikunja-mcp

A workflow-level MCP server for Vikunja with a fixed task pipeline (Backlog → Queue → Design → Build → Review → Done) that enables agents to claim, advance, and comment on tasks, while handling human callbacks and blocked items.

MCP Authentication Example

Demonstrates OAuth2/OIDC authentication for MCP servers using Asgardeo, with JWT validation and a sample weather tool to showcase secured API access.

Remote MCP Server (Authless)

A tool for deploying an authentication-free Model Context Protocol server on Cloudflare Workers that can be connected to AI clients like Claude Desktop or the Cloudflare AI Playground.

MCP Gateway Demo

A reference implementation of an MCP server built with Express that integrates full OAuth 2.1 authorization and RFC9728 protected resource metadata. It enables secure, authenticated communication between MCP clients and servers using streamable HTTP transport and built-in authorization flows.

tavily-mcp

tavily-mcp

@suiware/mcp

Enables AI assistants to interact with Sui Network through tools for balance checks, transfers, swaps, staking, and more.

NPS MCP Server

Provides access to the National Park Service API, enabling natural language queries about parks, alerts, campgrounds, events, and more.

OutreachEmailMCP

MCP server that acts as an email gateway for Gmail and Microsoft 365, enabling AI agents to send and read emails via MCP tools, with SMTP/IMAP and REST APIs for email sequencing and automation.

semantic-search

Local semantic recall MCP server for citation-integrity workflows. Enables semantic search over a text corpus, returning file paths and page numbers for verification, with 100% local processing using ONNX embeddings and LanceDB.

Excel MCP Server

Enables AI agents to create, read, and manipulate Excel workbooks without Microsoft Excel installed, supporting formulas, formatting, charts, pivot tables, and data validation operations.

Meta Marketing API MCP Server

Enables AI assistants to manage Facebook and Instagram advertising data through the Meta Marketing API. It supports full campaign lifecycle management, performance analytics, audience targeting, and creative optimization.

OneShard

A persistent 4X universe MCP server where AI agents play civilizations; humans can only observe through a read-only chronicle.

wiznote-mcp

MCP server for WizNote private server, enabling agents to search, read, write, and manage notes, and save webpages (including WeChat articles) as notes with image localization.

Langclaw CROO Agent

A paid callable research agent that provides source-backed reports, onchain intelligence, and claim verification via MCP tools for coding tools like Codex, Claude Code, Cursor, and Windsurf.

Microsoft Graph MCP Server

Enables management of Microsoft 365 users, licenses, and groups through Microsoft Graph API. Supports user provisioning, license assignment, group management, and automated M365 administration workflows.

Home Assistant MCP Server

Controle de Dispositivos Inteligentes 🎮 💡 Luzes: Brilho, cor, RGB 🌡️ Clima: Temperatura, HVAC, umidade 🚪 Persianas/Cortinas: Posição e inclinação 🔌 Interruptores: Liga/Desliga 🚨 Sensores: Monitoramento de estado Organização Inteligente 🏠 Agrupamento com reconhecimento de contexto. Arquitetura Robusta 🛠️ Tratamento de erros, validação de estado...

Weather MCP Server

Provides weather data from OpenWeatherMap API through MCP tools and a REST API with OpenAPI support. Enables LLM agents to retrieve current weather, forecasts, and temperature ranges by city or coordinates.

Remote MCP Server on Cloudflare

A Model Context Protocol server that runs on Cloudflare Workers with OAuth login, allowing clients like Claude Desktop to connect to it for tool-augmented AI interactions.

VMware-Monitor

Read-only VMware vCenter/ESXi monitoring. 8 MCP tools for VM inventory, host status, datastore capacity, cluster info, alarms, events, and VM details. Code-level enforced safety — no destructive operations exist in the codebase. Supports vSphere 6.5–8.0. Works with local models via Ollama/LM Studio.

powerbi-mcp-server

An MCP server that connects Claude and other MCP clients to Microsoft Power BI via its REST API using a Service Principal, enabling natural language queries to list workspaces, run DAX queries, refresh datasets, and explore reports.

pyATS MCP Server

Enables AI agents to directly inspect, configure, test, and orchestrate network devices through pyATS/Genie, including show command parsing, config rollback, feature state learning/diffing, fleet-wide command fan-out, and declarative test execution.

playwright-accessibility-mcp-server

Enables accessibility testing using Playwright and Axe, allowing users to scan URLs, HTML content, and batches for violations, and summarize results.

Google Calendar MCP Server

Servidor de Protocolo de Contexto de Modelo que fornece acesso contínuo à API do Google Calendar com suporte a operações assíncronas, permitindo o gerenciamento eficiente do calendário por meio de uma interface padronizada.

genTech-shop

Provides gaming intelligence for AI agents including Steam wishlist deals, upcoming releases, POE2 build health, and hub status via MCP tools.

Slidespeak

Okay, I understand. You want to know how to generate PowerPoint presentations using the Slidespeak API. Here's a breakdown of how to do that, along with important considerations: **Understanding the Slidespeak API** The Slidespeak API allows you to programmatically create and manipulate PowerPoint presentations. You'll typically interact with it using HTTP requests (like POST, GET, PUT, DELETE) to send instructions and receive responses. **General Steps to Generate a PowerPoint Presentation** 1. **Sign Up and Get an API Key:** * You'll need to create an account on the Slidespeak platform and obtain an API key. This key is essential for authenticating your requests. The Slidespeak documentation will guide you through this process. 2. **Choose a Programming Language and Library:** * Select a programming language you're comfortable with (e.g., Python, JavaScript, Java, PHP, Ruby). * Use an HTTP client library in your chosen language to make requests to the Slidespeak API. Examples: * **Python:** `requests` * **JavaScript:** `fetch`, `axios` * **Java:** `HttpClient` (from Apache HttpComponents) * **PHP:** `curl` * **Ruby:** `net/http` 3. **Understand the Slidespeak API Endpoints and Data Structures:** * **Crucially, consult the Slidespeak API documentation.** This is the most important step. The documentation will tell you: * The base URL for the API. * The specific endpoints for creating presentations, adding slides, adding text, images, etc. * The format of the data you need to send in your requests (usually JSON). * The format of the responses you'll receive. * Authentication methods (usually using your API key in a header). 4. **Construct Your API Requests:** * **Create a Presentation:** Typically, you'll start by making a POST request to an endpoint like `/presentations` or `/createPresentation`. You might provide a title for the presentation in the request body. * **Add Slides:** Next, you'll add slides to the presentation. This usually involves a POST request to an endpoint like `/presentations/{presentationId}/slides` or `/addSlide`. You might specify a layout for the slide (e.g., title slide, title and content, blank). * **Add Content to Slides:** For each slide, you'll add text, images, shapes, etc. This will involve POST or PUT requests to endpoints like `/slides/{slideId}/text`, `/slides/{slideId}/image`, `/slides/{slideId}/shape`. You'll need to provide the content (text, image URL, shape type, etc.) and positioning information (coordinates, size). * **Set Formatting:** You can usually control the formatting of text, shapes, and other elements (font, color, size, alignment, etc.) through the API. The Slidespeak documentation will detail the available formatting options. * **Download the Presentation:** Finally, you'll make a GET request to an endpoint like `/presentations/{presentationId}/download` or `/presentations/{presentationId}.pptx` to download the generated PowerPoint file. 5. **Handle API Responses:** * Check the HTTP status code of each response. A status code of 200 (OK) usually indicates success. Other status codes (e.g., 400 Bad Request, 401 Unauthorized, 500 Internal Server Error) indicate errors. * Parse the response body (usually JSON) to extract any relevant information, such as the ID of the created presentation or slide. * Implement error handling to gracefully handle API errors. **Example (Conceptual - Python with `requests`)** ```python import requests import json API_KEY = "YOUR_SLIDESPEAK_API_KEY" # Replace with your actual API key BASE_URL = "https://api.slidespeak.com/v1" # Replace with the actual Slidespeak API base URL def create_presentation(title): url = f"{BASE_URL}/presentations" headers = { "Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json" } data = {"title": title} response = requests.post(url, headers=headers, data=json.dumps(data)) if response.status_code == 201: # Assuming 201 Created is the success code return response.json()["id"] # Assuming the response contains the presentation ID else: print(f"Error creating presentation: {response.status_code} - {response.text}") return None def add_slide(presentation_id, layout="title_and_content"): url = f"{BASE_URL}/presentations/{presentation_id}/slides" headers = { "Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json" } data = {"layout": layout} response = requests.post(url, headers=headers, data=json.dumps(data)) if response.status_code == 201: return response.json()["id"] # Assuming the response contains the slide ID else: print(f"Error adding slide: {response.status_code} - {response.text}") return None def add_text_to_slide(slide_id, text, x, y, width, height): url = f"{BASE_URL}/slides/{slide_id}/text" headers = { "Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json" } data = { "text": text, "x": x, "y": y, "width": width, "height": height } response = requests.post(url, headers=headers, data=json.dumps(data)) if response.status_code == 200: return True else: print(f"Error adding text: {response.status_code} - {response.text}") return False def download_presentation(presentation_id, filename="presentation.pptx"): url = f"{BASE_URL}/presentations/{presentation_id}/download" # Or maybe f"{BASE_URL}/presentations/{presentation_id}.pptx" headers = { "Authorization": f"Bearer {API_KEY}" } response = requests.get(url, headers=headers, stream=True) # stream=True for large files if response.status_code == 200: with open(filename, "wb") as f: for chunk in response.iter_content(chunk_size=8192): f.write(chunk) print(f"Presentation downloaded to {filename}") return True else: print(f"Error downloading presentation: {response.status_code} - {response.text}") return False # Example Usage presentation_id = create_presentation("My Awesome Presentation") if presentation_id: slide_id = add_slide(presentation_id) if slide_id: add_text_to_slide(slide_id, "Hello, Slidespeak!", 100, 100, 500, 50) download_presentation(presentation_id) ``` **Important Considerations and Best Practices:** * **Rate Limiting:** Be aware of the Slidespeak API's rate limits. If you exceed the limits, your requests may be throttled or blocked. Implement error handling and retry mechanisms to deal with rate limiting. * **Error Handling:** Implement robust error handling to catch API errors and handle them gracefully. Log errors for debugging purposes. * **Data Validation:** Validate the data you're sending to the API to ensure it's in the correct format and within the allowed ranges. * **Asynchronous Operations:** For complex presentations, consider using asynchronous operations to avoid blocking your main thread. This is especially important for web applications. * **API Documentation is Key:** I cannot stress this enough. The Slidespeak API documentation is your bible. Refer to it constantly. The example code above is *illustrative* and *will not work* without the correct API endpoints and data structures from the Slidespeak documentation. * **Security:** Protect your API key. Do not hardcode it directly into your code, especially if you're sharing your code publicly. Use environment variables or a configuration file to store your API key. * **Testing:** Thoroughly test your code to ensure it generates presentations correctly and handles errors gracefully. **In summary, to use the Slidespeak API, you need to:** 1. **Get an API key.** 2. **Study the Slidespeak API documentation.** 3. **Use a programming language and HTTP client library to make requests to the API.** 4. **Construct your requests according to the API documentation.** 5. **Handle the API responses and errors.** Good luck! Let me know if you have more specific questions after reviewing the Slidespeak API documentation.

md-log-mcp

An MCP server that lets AI coding agents save immutable, versioned Markdown reports into md-log, a human-in-the-loop review and archive layer for vibe coding.

mrmarket.ai MCP server

Enables financial research on US-listed equities by answering natural language questions with structured data from fundamentals, prices, earnings, and insider activity.

autocad-arch-mcp

Enables architectural design in AutoCAD 2021 via chat, using YQArch (NBC standard) to build, draw, and dimension directly through natural language.

Naitei MCP

Enables job-search application tracking through a private application board, managing application facts, stage history, and interview prep documents while leaving summarization and decision-making to the connected agent.

Smart Home MCP Server

Controls TAPO L530E smart light bulbs via MCP, supporting on/off, brightness, and color temperature, with local and remote AWS deployment.