Discover Awesome MCP Servers

MCP Project Context Server

A persistent memory layer for Claude Code that maintains project information, technology stack, tasks, decisions, and session history between coding sessions, eliminating the need to re-explain project context.

mcp_repo_c11db53a

Ini adalah repositori pengujian yang dibuat oleh skrip pengujian MCP Server untuk GitHub.

Web3 MCP Server

Server MCP Web3 untuk rantai EVM (saat ini)

mcp-linkedinads

Analyse your LinkedIn Ads performance. Compare to benchmarks and get optimisation recommendations.

富途 MCP 服务器 (Futu MCP Server)

Exposes Futu API client capabilities as an MCP (Model Context Protocol) tool, allowing AI assistants to access stock data from Futu through a standardized interface.

solana-launchpads-mcp

An MCP server that tracks daily activity and graduate metrics across multiple Solana launchpads.

Cisco ISE MCP Server

Enables management of Cisco Identity Services Engine (ISE) resources through the ERS API. Supports identity management, endpoint registration, network device configuration, and authorization profiles through natural language interactions.

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)

Menerapkan Model Context Protocol (MCP) melalui HTTP untuk menyediakan akses jarak jauh ke standar pengkodean BluestoneApps dan contoh kode React Native.

Google Calendar MCP Server

Server Protokol Konteks Model yang menyediakan akses tanpa hambatan ke Google Calendar API dengan dukungan operasi asinkron, memungkinkan pengelolaan kalender yang efisien melalui antarmuka terstandarisasi.

Slidespeak

Okay, here's a breakdown of how to generate PowerPoint presentations using the Slidespeak API, along with considerations and potential code examples (in Python, as it's a common language for API interaction): **Understanding the Slidespeak API** Before diving into code, you need to understand the core concepts of the Slidespeak API. I don't have direct access to the Slidespeak API documentation, so I'll make some educated assumptions based on common presentation API patterns. You'll need to **consult the official Slidespeak API documentation** for the *definitive* details. Here's what I'd expect: * **Authentication:** Most APIs require authentication. This usually involves an API key or token that you'll need to include in your requests. Find out how Slidespeak handles authentication. * **Presentation Structure:** The API will likely have a way to define the structure of your presentation. This will involve specifying: * **Slides:** Each slide in the presentation. * **Slide Layouts:** The layout of each slide (e.g., title slide, title and content, two content sections, etc.). Slidespeak will probably have predefined layout names or IDs. * **Elements:** The elements within each slide (e.g., text boxes, images, charts, shapes). You'll need to specify the type of element, its position, size, and content. * **Data Input:** You'll need to provide the data that will populate the presentation. This could be text, image URLs, chart data, etc. * **Output Format:** The API will likely allow you to specify the output format (e.g., `.pptx`, `.pdf`). * **Error Handling:** The API should provide error codes and messages to help you debug any issues. **General Steps for Generating a Presentation** 1. **Authentication:** Obtain your API key or token from Slidespeak. 2. **Define Presentation Structure:** Create a data structure (e.g., a Python dictionary or JSON object) that describes the presentation you want to generate. This will include the slides, layouts, and elements. 3. **Populate with Data:** Fill in the data for each element in the presentation. 4. **Make API Request:** Send a request to the Slidespeak API, including your authentication credentials and the presentation data. 5. **Handle Response:** Process the API response. If the request was successful, you'll receive a URL or a file containing the generated presentation. If there was an error, you'll need to handle it appropriately. **Example Python Code (Conceptual - Requires Slidespeak API Documentation)** ```python import requests import json # Replace with your actual Slidespeak API key API_KEY = "YOUR_SLIDESPEAK_API_KEY" API_ENDPOINT = "https://api.slidespeak.com/presentations" # Example endpoint def create_presentation(presentation_data): """ Creates a PowerPoint presentation using the Slidespeak API. Args: presentation_data: A dictionary containing the presentation structure and data. Returns: The URL of the generated presentation, or None if there was an error. """ headers = { "Authorization": f"Bearer {API_KEY}", # Or however Slidespeak authenticates "Content-Type": "application/json" } try: response = requests.post(API_ENDPOINT, headers=headers, data=json.dumps(presentation_data)) response.raise_for_status() # Raise HTTPError for bad responses (4xx or 5xx) response_json = response.json() presentation_url = response_json.get("presentation_url") # Adjust based on API response return presentation_url except requests.exceptions.RequestException as e: print(f"Error making API request: {e}") if response is not None: print(f"Response status code: {response.status_code}") print(f"Response body: {response.text}") # Print the error message from the API return None except json.JSONDecodeError as e: print(f"Error decoding JSON response: {e}") if response is not None: print(f"Response text: {response.text}") return None # Example presentation data (replace with your actual data) presentation_data = { "title": "My Awesome Presentation", "slides": [ { "layout": "title_slide", # Example layout name "title": "Introduction", "subtitle": "A brief overview" }, { "layout": "title_and_content", "title": "Key Points", "content": "Here are some important points to consider." } ] } # Create the presentation presentation_url = create_presentation(presentation_data) if presentation_url: print(f"Presentation created successfully! URL: {presentation_url}") else: print("Failed to create presentation.") ``` **Explanation of the Code:** 1. **Import Libraries:** Imports the `requests` library for making HTTP requests and the `json` library for working with JSON data. 2. **API Key and Endpoint:** Sets the API key and endpoint. **Replace these with the actual values from Slidespeak.** 3. **`create_presentation` Function:** * Takes `presentation_data` as input, which is a dictionary representing the presentation. * Sets the `headers` for the API request, including the `Authorization` header (using a bearer token, which is common) and the `Content-Type` header. * Uses a `try...except` block to handle potential errors during the API request. * Makes a `POST` request to the API endpoint using `requests.post()`. * Calls `response.raise_for_status()` to raise an exception if the response status code indicates an error (4xx or 5xx). * Parses the JSON response using `response.json()`. * Extracts the presentation URL from the JSON response (adjust the key based on the API's response format). * Handles `requests.exceptions.RequestException` (for network errors, timeouts, etc.) and `json.JSONDecodeError` (if the API returns invalid JSON). 4. **Example Presentation Data:** Creates a sample `presentation_data` dictionary. **This is where you'll need to define the structure and content of your presentation according to the Slidespeak API's specifications.** Pay close attention to the expected layout names and element types. 5. **Call the Function:** Calls the `create_presentation` function with the example data. 6. **Print Results:** Prints the URL of the generated presentation or an error message. **Important Considerations:** * **Slidespeak API Documentation:** **This is the most important thing.** You *must* consult the official Slidespeak API documentation to understand the exact format of the presentation data, the available layouts, the authentication method, and the API's response format. * **Error Handling:** Implement robust error handling to catch potential issues during the API request and processing. Print detailed error messages to help you debug. * **Data Validation:** Validate the data you're sending to the API to ensure that it conforms to the expected format. This can help prevent errors. * **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. * **Asynchronous Operations:** For large presentations, the API might use asynchronous operations. This means that the API will return a task ID, and you'll need to poll the API periodically to check the status of the task. * **Layouts and Elements:** Carefully choose the appropriate layouts and elements for your presentation. The Slidespeak API documentation should provide a list of available layouts and element types. * **Image Handling:** If you're including images in your presentation, make sure that the image URLs are publicly accessible. The Slidespeak API may also have specific requirements for image formats and sizes. **How to Adapt the Code:** 1. **Replace Placeholders:** Replace the placeholder values for `API_KEY` and `API_ENDPOINT` with your actual Slidespeak API credentials. 2. **Define Presentation Data:** Modify the `presentation_data` dictionary to match the structure and content of your desired presentation. Refer to the Slidespeak API documentation for the correct format. 3. **Adjust Authentication:** If Slidespeak uses a different authentication method (e.g., API key in the query string), adjust the `headers` accordingly. 4. **Handle API Response:** Modify the code that extracts the presentation URL from the API response to match the actual response format. 5. **Add Error Handling:** Add more specific error handling based on the error codes and messages returned by the Slidespeak API. **In summary, generating PowerPoint presentations with the Slidespeak API requires a thorough understanding of the API's documentation, careful construction of the presentation data, and robust error handling. Use the example code as a starting point and adapt it to your specific needs.**

Remote MCP Server on Cloudflare

Enables deploying MCP servers on Cloudflare Workers with OAuth authentication and SSE transport. Allows connecting Claude Desktop and other MCP clients to remotely hosted tools via HTTP.

Momento MCP Server

Enables interaction with Momento Cache to manage cache entries and perform administrative tasks like creating, listing, or deleting caches. It provides tools for getting and setting values with configurable TTLs through a serverless caching infrastructure.

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

RunwayML + Luma AI MCP Server

Menyediakan alat untuk berinteraksi dengan API RunwayML dan Luma AI untuk pembuatan video dan gambar, termasuk teks-ke-video, gambar-ke-video, peningkatan prompt, dan pengelolaan generasi.

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

Kontrol Perangkat Pintar 🎮 💡 Lampu: Kecerahan, warna, RGB 🌡️ Iklim: Suhu, HVAC, kelembapan 🚪 Penutup: Posisi dan kemiringan 🔌 Sakelar: Hidup/mati 🚨 Sensor: Pemantauan status Organisasi Cerdas 🏠 Pengelompokan dengan kesadaran konteks. Arsitektur yang Kuat 🛠️ Penanganan kesalahan, validasi status ...

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.

Tandoor MCP Server

Server Protokol Konteks Model (MCP) untuk berinteraksi dengan Tandoor Recipe Manager.

OpenCollective MCP Server

Provides programmatic access to OpenCollective and Hetzner Cloud to automate bookkeeping, collective management, and invoice handling. It enables AI agents to manage expenses, query transactions, and automatically reconcile hosting invoices without manual intervention.

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 adalah alat untuk menghasilkan server Model Context Protocol (MCP) dari deskripsi bahasa alami. MVP ini menggunakan Google Gemini API untuk mengubah deskripsi pengguna menjadi server MCP Python fungsional dengan konfigurasi JSON yang sesuai.

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.

vantagate-mcp-server

Human-in-the-Loop authorization gateway for AI Agents. Securely pause MCP workflows and route high-risk actions to human approvers via Slack or Email.

Sophia Labs

Two MCP endpoints for building cognitive AI agents. /blueprint/mcp serves a 9-chapter architecture blueprint (4 tools). /devops/mcp serves a 7-chapter coding agent playbook (3 tools). Each product has its own Gumroad license key. Free chapters available without auth.

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.