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

스마트 기기 제어 🎮 💡 조명: 밝기, 색상, RGB 🌡️ 실내 온도: 온도, HVAC, 습도 🚪 커버: 위치 및 기울기 🔌 스위치: 켜기/끄기 🚨 센서: 상태 모니터링 지능형 구성 🏠 상황 인식을 통한 그룹화 견고한 아키텍처 🛠️ 오류 처리, 상태 유효성 검사 ...

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

비동기 작업 지원을 통해 효율적인 캘린더 관리를 가능하게 하는 표준화된 인터페이스를 제공하며, Google Calendar API에 대한 원활한 접근을 제공하는 Model Context Protocol 서버.

genTech-shop

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

Slidespeak

Slidespeak API를 사용하여 PowerPoint 프레젠테이션을 생성하는 방법에 대한 설명입니다. **(Note: Since I cannot directly execute code or interact with external APIs, I will provide a conceptual explanation and code examples. You will need to adapt these examples to your specific environment and API key.)** **1. Understanding the Slidespeak API** * **What is it?** Slidespeak is an API that allows you to programmatically create and modify PowerPoint presentations. It likely uses a JSON-based request/response format. * **Key Features (Based on typical presentation APIs):** * Creating new presentations * Adding slides * Setting slide layouts (title slide, content slide, etc.) * Adding text, images, shapes, and tables * Formatting text (font, size, color, alignment) * Positioning elements on the slide * Saving the presentation in various formats (PPTX, PDF, etc.) * **Authentication:** You'll need an API key or other authentication credentials to use the Slidespeak API. This is usually obtained from their website after signing up for an account. **2. Prerequisites** * **API Key:** Obtain your Slidespeak API key from their website. * **Programming Language:** Choose a programming language (e.g., Python, JavaScript, Java, C#) that you are comfortable with. Python is often a good choice for API interactions due to its simplicity and libraries like `requests`. * **HTTP Client Library:** You'll need an HTTP client library to make requests to the Slidespeak API. In Python, this is typically the `requests` library. In JavaScript, you might use `fetch` or `axios`. * **Slidespeak API Documentation:** The most important resource is the official Slidespeak API documentation. This will tell you the exact endpoints, request formats, and response formats you need to use. **Refer to their documentation for the most accurate and up-to-date information.** **3. Conceptual Steps** 1. **Authentication:** Include your API key in the request headers or as a query parameter, as required by the Slidespeak API. 2. **Create a New Presentation:** Send a request to the "create presentation" endpoint. This will likely return a presentation ID. 3. **Add Slides:** For each slide you want to add: * Send a request to the "add slide" endpoint. * Specify the slide layout (e.g., "title slide," "title and content," "blank"). 4. **Add Content to Slides:** For each element on a slide (text, image, shape, table): * Send a request to the appropriate endpoint (e.g., "add text," "add image"). * Specify the element's properties: * Text content (for text elements) * Image URL or file path (for image elements) * Position (x, y coordinates) * Size (width, height) * Formatting (font, color, alignment) 5. **Save the Presentation:** Send a request to the "save presentation" endpoint. Specify the desired file format (e.g., PPTX, PDF) and the file name. **4. Python Example (Illustrative - Adapt to Slidespeak API)** ```python import requests import json # Replace with your actual Slidespeak API key API_KEY = "YOUR_SLIDESPEAK_API_KEY" BASE_URL = "https://api.slidespeak.com/v1" # Replace with the actual base URL def create_presentation(title): """Creates a new presentation.""" url = f"{BASE_URL}/presentations" headers = { "Authorization": f"Bearer {API_KEY}", # Or however authentication is done "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 presentation_data = response.json() return presentation_data["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"): """Adds a slide to the presentation.""" 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: slide_data = response.json() return slide_data["id"] # Assuming the response contains the slide ID else: print(f"Error adding slide: {response.status_code} - {response.text}") return None def add_text(presentation_id, slide_id, text, x, y, width, height, font_size=12, color="black"): """Adds text to a slide.""" url = f"{BASE_URL}/presentations/{presentation_id}/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, "font_size": font_size, "color": color } response = requests.post(url, headers=headers, data=json.dumps(data)) if response.status_code == 201: return True else: print(f"Error adding text: {response.status_code} - {response.text}") return False def save_presentation(presentation_id, filename="presentation.pptx", format="pptx"): """Saves the presentation.""" url = f"{BASE_URL}/presentations/{presentation_id}/save" headers = { "Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json" } data = { "filename": filename, "format": format } response = requests.post(url, headers=headers, data=json.dumps(data)) if response.status_code == 200: # Assuming 200 OK is the success code # The response might contain the file data or a download URL print(f"Presentation saved successfully as {filename}") return True else: print(f"Error saving presentation: {response.status_code} - {response.text}") return False # Example Usage if __name__ == "__main__": presentation_id = create_presentation("My Awesome Presentation") if presentation_id: slide_id1 = add_slide(presentation_id, layout="title_slide") if slide_id1: add_text(presentation_id, slide_id1, "My Presentation Title", 100, 100, 600, 50, font_size=36) add_text(presentation_id, slide_id1, "By Your Name", 100, 200, 600, 30, font_size=24) slide_id2 = add_slide(presentation_id, layout="title_and_content") if slide_id2: add_text(presentation_id, slide_id2, "Second Slide Title", 100, 50, 600, 40, font_size=28) add_text(presentation_id, slide_id2, "Some content for the second slide.", 100, 150, 600, 200, font_size=18) save_presentation(presentation_id, filename="my_presentation.pptx") ``` **Explanation of the Python Example:** * **`API_KEY` and `BASE_URL`:** Replace these with your actual API key and the base URL provided by Slidespeak. * **`create_presentation(title)`:** Creates a new presentation with the given title. It sends a POST request to the `/presentations` endpoint. * **`add_slide(presentation_id, layout)`:** Adds a new slide to the specified presentation with the given layout. It sends a POST request to the `/presentations/{presentation_id}/slides` endpoint. * **`add_text(presentation_id, slide_id, text, x, y, width, height, font_size, color)`:** Adds a text box to the specified slide with the given properties. It sends a POST request to the `/presentations/{presentation_id}/slides/{slide_id}/text` endpoint. * **`save_presentation(presentation_id, filename, format)`:** Saves the presentation to a file. It sends a POST request to the `/presentations/{presentation_id}/save` endpoint. * **Error Handling:** The code includes basic error handling by checking the HTTP status code of the response. * **JSON Encoding:** The `json.dumps()` function is used to convert Python dictionaries into JSON strings for the request body. * **Headers:** The `headers` dictionary includes the `Authorization` header (with the API key) and the `Content-Type` header (set to `application/json`). **5. Important Considerations** * **API Documentation is Key:** The Slidespeak API documentation is your primary source of information. Refer to it for the correct endpoints, request parameters, and response formats. * **Error Handling:** Implement robust error handling to catch API errors and handle them gracefully. Check the HTTP status codes and the response body for error messages. * **Rate Limiting:** Be aware of any rate limits imposed by the Slidespeak API. If you exceed the rate limit, you may need to implement a retry mechanism with exponential backoff. * **Data Validation:** Validate your input data before sending it to the API to prevent errors. * **Asynchronous Operations:** Some API operations may be asynchronous. You may need to use techniques like polling or webhooks to track the progress of these operations. * **Security:** Protect your API key. Do not hardcode it directly into your code. Use environment variables or a configuration file to store it securely. **6. Korean Translation of Key Phrases** * **API Key:** API 키 * **Presentation:** 프레젠테이션 * **Slide:** 슬라이드 * **Title:** 제목 * **Content:** 내용 * **Layout:** 레이아웃 * **Text:** 텍스트 * **Image:** 이미지 * **Save:** 저장 * **Error:** 오류 * **Success:** 성공 * **Create Presentation:** 프레젠테이션 생성 * **Add Slide:** 슬라이드 추가 * **Add Text:** 텍스트 추가 * **Save Presentation:** 프레젠테이션 저장 **Example Korean Code Comments (Illustrative):** ```python # API 키를 여기에 입력하세요. (API 키를 직접 코드에 넣지 마세요!) API_KEY = "YOUR_SLIDESPEAK_API_KEY" # 새 프레젠테이션을 생성합니다. def create_presentation(title): """새 프레젠테이션을 생성합니다.""" # ... (rest of the code) ``` **In summary, to use the Slidespeak API, you need to:** 1. **Study the Slidespeak API documentation thoroughly.** 2. **Obtain an API key.** 3. **Choose a programming language and HTTP client library.** 4. **Write code to authenticate with the API and make requests to create presentations, add slides, add content, and save the presentation.** 5. **Implement robust error handling.** Remember to replace the placeholder values in the example code with your actual API key and the correct Slidespeak API endpoints and parameters. Good luck!

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.