Discover Awesome MCP Servers

Octocat Harry Potter MCP Server

Enables interaction with Harry Potter API and GitHub Octodex API to retrieve character data from Hogwarts houses, spells, staff, students, and Octocats, with support for creating magical visualizations that match characters with Octocats.

BluestoneApps Development Standards (Remote)

BluestoneAppsのコーディング標準とReact Nativeのコード例へのリモートアクセスを提供するために、HTTP経由でModel Context Protocol (MCP) を実装します。

Google Calendar MCP Server

非同期操作をサポートし、標準化されたインターフェースを通じて効率的なカレンダー管理を可能にする、Google Calendar APIへのシームレスなアクセスを提供するModel Context Protocolサーバー。

Slidespeak

Okay, I understand. You want information on how to generate PowerPoint presentations using the Slidespeak API. Here's a breakdown of how you would likely approach this, along with important considerations: **Understanding the Slidespeak API (Assumptions and General Approach)** Since I don't have direct access to the Slidespeak API documentation (which is crucial for precise instructions), I'll make some reasonable assumptions based on common API design principles. You'll need to **consult the official Slidespeak API documentation** for the *exact* details, endpoints, request formats, and authentication methods. **General Steps Involved** 1. **API Key and Authentication:** * **Obtain an API Key:** You'll almost certainly need to register for a Slidespeak account and obtain an API key or other authentication credentials. This key is used to identify your application and authorize your requests. * **Authentication:** The API documentation will specify how to include your API key in your requests. Common methods include: * **Header:** Adding an `Authorization` header (e.g., `Authorization: Bearer YOUR_API_KEY`) * **Query Parameter:** Including the key as a query parameter in the URL (e.g., `?api_key=YOUR_API_KEY`) 2. **Identify the Relevant API Endpoints:** * **Presentation Creation:** Look for an endpoint specifically designed to create new presentations. It might be something like: * `/presentations` (POST request) * `/create_presentation` (POST request) * **Slide Creation:** Find an endpoint to add slides to a presentation. This might require the presentation ID. Examples: * `/presentations/{presentation_id}/slides` (POST request) * `/slides` (POST request, requiring a `presentation_id` in the request body) * **Content Addition:** Endpoints to add text, images, charts, and other elements to slides. These will likely require the slide ID. Examples: * `/slides/{slide_id}/text` (POST or PUT request) * `/slides/{slide_id}/image` (POST or PUT request) * `/slides/{slide_id}/chart` (POST or PUT request) * **Presentation Retrieval/Download:** An endpoint to get the final PowerPoint file. * `/presentations/{presentation_id}/download` (GET request) 3. **Construct API Requests:** * **Request Method:** Use the correct HTTP method (POST for creating, GET for retrieving, PUT/PATCH for updating). * **Headers:** Set the `Content-Type` header to `application/json` if you're sending JSON data in the request body. Include any required authentication headers. * **Request Body (JSON):** The request body will typically be a JSON object containing the data for the presentation, slides, and content. The structure of this JSON will be defined by the Slidespeak API. For example: ```json // Example: Creating a presentation { "title": "My Awesome Presentation", "theme": "Modern" } // Example: Adding a slide { "presentation_id": "12345", "layout": "Title and Content" } // Example: Adding text to a slide { "slide_id": "67890", "text": "This is the title of the slide", "position": "top", "font_size": 24 } // Example: Adding an image to a slide { "slide_id": "67890", "image_url": "https://example.com/image.jpg", "position": "center" } ``` 4. **Send API Requests:** * Use a programming language like Python, JavaScript, or Java, along with an HTTP client library (e.g., `requests` in Python, `fetch` in JavaScript, `HttpClient` in Java) to send the API requests. 5. **Handle API Responses:** * **Status Codes:** Check the HTTP status code of the response. `200 OK` usually indicates success. `4xx` codes indicate client errors (e.g., invalid API key, bad request). `5xx` codes indicate server errors. * **Response Body (JSON):** The response body will often contain JSON data, such as the ID of the newly created presentation or slide, or error messages. Parse the JSON to extract the information you need. 6. **Error Handling:** * Implement robust error handling to catch exceptions, check status codes, and handle error messages from the API. Log errors for debugging. **Example (Conceptual Python Code using `requests` library)** ```python import requests import json API_KEY = "YOUR_SLIDESPEAK_API_KEY" # Replace with your actual API key BASE_URL = "https://api.slidespeak.com" # Replace with the actual Slidespeak API base URL def create_presentation(title, theme="Default"): url = f"{BASE_URL}/presentations" headers = { "Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json" } data = { "title": title, "theme": theme } response = requests.post(url, headers=headers, data=json.dumps(data)) if response.status_code == 201: # Assuming 201 Created on success 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, position="top", font_size=24): url = f"{BASE_URL}/slides/{slide_id}/text" headers = { "Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json" } data = { "text": text, "position": position, "font_size": font_size } 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): url = f"{BASE_URL}/presentations/{presentation_id}/download" headers = { "Authorization": f"Bearer {API_KEY}" } response = requests.get(url, headers=headers) if response.status_code == 200: # Save the presentation to a file with open(f"presentation_{presentation_id}.pptx", "wb") as f: f.write(response.content) print(f"Presentation downloaded to presentation_{presentation_id}.pptx") return True else: print(f"Error downloading presentation: {response.status_code} - {response.text}") return False # Example Usage presentation_id = create_presentation("My Demo Presentation") if presentation_id: slide_id = add_slide(presentation_id) if slide_id: add_text_to_slide(slide_id, "Welcome to my presentation!", position="center", font_size=36) download_presentation(presentation_id) ``` **Important Considerations and Best Practices:** * **Rate Limiting:** Be aware of the Slidespeak API's rate limits (the number of requests you can make per unit of time). Implement logic to handle rate limiting errors (e.g., using exponential backoff). * **Error Handling:** Implement comprehensive error handling to gracefully handle API errors and prevent your application from crashing. * **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 (e.g., using `asyncio` in Python) to avoid blocking the main thread. * **API Documentation:** **The Slidespeak API documentation is your primary source of truth.** Refer to it for the most accurate and up-to-date information. * **Testing:** Thoroughly test your code to ensure it's working correctly and handling errors properly. **In summary, to use the Slidespeak API, you'll need to:** 1. **Get an API key.** 2. **Study the API documentation.** 3. **Identify the endpoints you need.** 4. **Construct and send API requests using a programming language and an HTTP client library.** 5. **Handle API responses and errors.** Remember to replace the placeholder values (API key, base URL) with the actual values from the Slidespeak API. Good luck!

Gaia Health MCP Server

Exposes Supabase functionality for Gaia Health to n8n workflows, enabling appointment scheduling and management operations through MCP tools.

Kali MCP Server

Provides access to 20+ Kali Linux penetration testing tools including nmap, sqlmap, nikto, and hydra for authorized security testing and vulnerability assessment through a Docker-based MCP interface.

Mantis MCP Server

鏡 (Kagami)

VaultMesh Architect MCP Server

Enables governance and orchestration of VaultMesh deployments through subsystem spawning, multi-chain anchoring, threat mitigation, constitutional amendments, and LAWCHAIN governance tracking. Provides auditable tools for managing decentralized infrastructure with cryptographic proofs and alchemical phase orchestration.

Smart Search MCP Server

Enables web search capabilities through a remote smart search API with configurable result count, pagination, language, and safety filters, returning structured JSON results.

Cloudflare Playwright MCP

Enables AI assistants to control a browser through Playwright and Cloudflare Workers, allowing web automation tasks like navigation, typing, clicking, and taking screenshots through natural language instructions.

Task Trellis MCP

An MCP server for Task Trellis that provides tools for AI coding agents to manage tasks, currently featuring a simple hello_world demonstration tool.

Kagami

Kagami is an MCP server designed exclusively for the Claude Code Web environment that enables browser automation using Playwright and Firefox. It features an automated setup process and manages secure external access through a JWT authentication proxy with integrated CA certificate support.

Scientific Search MCP for Cursor

科学的なリソースを検索するためのMCPサーバー。AIによってAIのために作られたバイブス。

NodeCodeStudio

NodeCodeStudio is a hybrid MCP implementation that lets AI agents activate and manage tools like Gmail, Google Calendar, WordPress, Asana and more through a unified interface. It also includes a Browser MCP extension with ready-made automations like LinkedIn jobs and price searches.

MCP Feedback Collector

Enables AI assistants to collect interactive user feedback through a modern GUI that supports text input, multiple image uploads (via file selection or clipboard paste), allowing users to provide comprehensive feedback with screenshots and comments.

Shopify Python MCP Server

Shopify APIと連携し、Claude DesktopユーザーがShopifyストアから商品情報を取得・操作できるMCPサーバー

Concurrent Browser MCP

A concurrent browser MCP server that supports multiple parallel browser instances

weather-mcp

天気取得のテスト用 MCP サーバー

VeniAI-Hukuk-EmsalKarar-MCPServer

An AI-powered legal research tool that enables users to search for and retrieve legal precedents and case law decisions through a Model Context Protocol server. It supports both Turkish and English, providing lawyers and researchers with streamlined access to a comprehensive database of jurisprudence.

MyMCP Prompt

MyMCP Promptは、自然言語による記述からModel Context Protocol（MCP）サーバーを生成するためのツールです。このMVP（Minimum Viable Product：実用最小限の製品）は、Google Gemini APIを使用して、ユーザーの記述を機能的なPython MCPサーバーと対応するJSON構成に変換します。

Obsidian MCP Tools

A read-only toolkit for searching and analyzing Markdown note directories and Obsidian vaults through AI clients. It enables metadata extraction, full-text search, and natural language querying of note content, tags, and backlinks.

open-webSearch

Web search using free multi-engine search (NO API KEYS REQUIRED) — Supports Bing, Baidu, DuckDuckGo, Brave, Exa, and CSDN.

MCP Teamtailor

A Model Context Protocol server that enables integration with the Teamtailor API, allowing users to list, filter, and retrieve candidate information from their Teamtailor recruitment platform.

SAST MCP Server

Integrates 15+ static application security testing tools (Semgrep, Bandit, TruffleHog, etc.) with Claude Code AI, enabling automated vulnerability scanning and security analysis through natural language commands. Supports cross-platform operation with remote execution on dedicated security VMs.

LLM Tool-Calling Assistant

Connects local LLMs to external tools (calculator, knowledge base) via MCP protocol, enabling automatic tool detection and execution to enhance query responses.

browser-mcp

An MCP server that allows users to interact with their browser through natural language commands, enabling actions like getting page content as markdown, modifying page styles, and searching browser history.

Genai Toolbox

データベース向けの簡単、高速、かつ安全なツールに特化した、オープンソースのMCPサーバー。

Browser MCP Server (Anchor)

Enables browser automation through Anchor Browser's cloud infrastructure with built-in proxies, stealth features, and anti-detection capabilities. Allows LLMs to navigate, click, type, take screenshots, and interact with web pages using Playwright's accessibility tree without requiring local browser installations.

cite-mcp

CiteAsとGoogle Scholarから簡単に引用データを取得できます。数個のコマンドだけで、リソースのBibTeX形式の引用を取得できます。引用取得をアプリケーションに直接統合することで、研究ワークフローを強化できます。