Discover Awesome MCP Servers

CSMAR MCP Server

Enables direct access to CSMAR financial databases through Claude Code. Supports 240+ databases including financial statements, stock trading data, and company information with intelligent login management and 11 MCP tools.

Outline MCP Server

An MCP server that enables reading, writing, and searching documents in Outline via its API. It supports document management, full-text search, and collection organization using Markdown formatting.

autoglm-mcp

Enables AI agents to analyze and interact with Android phone screens via ADB, using the AutoGLM model to answer queries about screen content and coordinates.

Google Workspace MCP Server

Exposes a curated set of Google Workspace CLI operations as tools for managing Drive, Sheets, Calendar, Docs, and Gmail. It provides a focused set of high-value operations to avoid context window bloat while enabling file management, spreadsheet updates, and email interactions.

mcp-governance-proxy

An MCP server that acts as a governance proxy for AI agents, evaluating each tool call against policies before execution, enabling secure and controlled access to systems like Slack, GitHub, and AWS without exposing credentials to the agent.

Superset MCP Server - TypeScript

Enables AI assistants to interact with Apache Superset instances programmatically, providing 45+ tools for dashboard management, chart creation, database operations, SQL execution, and complete Superset API coverage. Supports multiple transport modes including stdio, SSE, and HTTP streaming for flexible deployment options.

lineageverse-mcp

MCP server for single-cell lineage tracing analysis, enabling conversational reconstruction, visualization, and heritability analysis of lineage trees using Cassiopeia, pycea, and treedata.

Jira Cloud MCP Server

Enables AI assistants to manage Jira Cloud projects, issues, sprints, and more through a curated set of 62 tools covering the full lifecycle of stories, epics, bugs, and sprints.

Whoop MCP Server

Integrates WHOOP biometric data into Claude and other MCP-compatible applications, providing access to sleep analysis, recovery metrics, strain tracking, and biological age data through natural language queries.

Harvest MCP Server

Integrates with Harvest time tracking to allow AI assistants to log time, view projects, manage tasks, and track work hours, with optional Azure DevOps integration for automated time logging from work items.

SharePoint MCP: The .NET MCP Server with Graph API & Semantic Kernel

Okay, I understand. You want to create an **application** (not a server in the traditional sense) that uses the Microsoft Cloud Platform (MCP) - specifically, the Microsoft Graph API - to access SharePoint Online. This application will act as a bridge, allowing you to interact with SharePoint Online programmatically. Here's a breakdown of the steps involved and a conceptual outline. **This is not a complete, runnable code example, but a guide to the process. You'll need to choose a programming language and framework (e.g., Python with Flask/Django, Node.js with Express, C# with ASP.NET Core) and adapt the code accordingly.** **1. Prerequisites:** * **Microsoft 365 Subscription:** You need a Microsoft 365 subscription that includes SharePoint Online. * **Azure Active Directory (Azure AD) Tenant:** Your Microsoft 365 subscription is linked to an Azure AD tenant. This is where you'll register your application. * **Development Environment:** Choose your preferred programming language and framework (e.g., Python, Node.js, C#, Java). Install the necessary SDKs and libraries. * **Microsoft Graph SDK:** Install the Microsoft Graph SDK for your chosen language. This simplifies interacting with the Graph API. **2. Register Your Application in Azure AD:** 1. **Sign in to the Azure portal:** Go to [https://portal.azure.com/](https://portal.azure.com/) using an account with sufficient permissions (e.g., Global Administrator). 2. **Navigate to Azure Active Directory:** Search for "Azure Active Directory" in the search bar and select it. 3. **App registrations:** In the left-hand menu, click on "App registrations." 4. **New registration:** Click on "New registration." 5. **Name:** Give your application a descriptive name (e.g., "SharePointOnlineConnector"). 6. **Supported account types:** Choose the appropriate account type. For most scenarios, "Accounts in this organizational directory only" is sufficient. If you need to support external users, choose a multi-tenant option. 7. **Redirect URI (Optional):** This is important for interactive authentication (user login). If your application will have a web interface, enter the URL where users will be redirected after authentication (e.g., `http://localhost:5000/callback` for a local development server). If it's a command-line application, you might not need a redirect URI initially. You can add/modify this later. For testing, `http://localhost` is often used. 8. **Register:** Click "Register." **3. Configure Application Permissions (API Permissions):** 1. **Navigate to your app registration:** Find the application you just registered in the "App registrations" list. 2. **API permissions:** In the left-hand menu, click on "API permissions." 3. **Add a permission:** Click on "Add a permission." 4. **Microsoft Graph:** Select "Microsoft Graph." 5. **Delegated permissions** *or* **Application permissions:** This is a crucial choice: * **Delegated permissions:** The application acts on behalf of a *signed-in user*. The user must grant consent. Use this if you need to access SharePoint data based on a user's permissions. Examples: `Sites.Read.All`, `Sites.ReadWrite.All`, `Files.Read.All`, `Files.ReadWrite.All`. * **Application permissions:** The application acts as itself, without a signed-in user. This requires *administrator consent*. Use this for background processes or services that need to access SharePoint data regardless of a user's presence. Examples: `Sites.FullControl.All` (very powerful, use with caution!), `Sites.Read.All`, `Sites.ReadWrite.All`. 6. **Select the necessary permissions:** Choose the *least* privileged permissions required for your application to function. For example, if you only need to read site information, select `Sites.Read.All`. If you need to upload files, select `Files.ReadWrite.All`. 7. **Add permissions:** Click "Add permissions." 8. **Grant admin consent (if using Application permissions):** If you selected Application permissions, you'll need to grant administrator consent. Click the "Grant admin consent for <your organization>" button and confirm. This requires an account with Global Administrator privileges. **4. Get Application Credentials:** 1. **Navigate to your app registration:** Find your application in the "App registrations" list. 2. **Overview:** On the "Overview" page, note the **Application (client) ID**. This is a unique identifier for your application. 3. **Certificates & secrets:** In the left-hand menu, click on "Certificates & secrets." 4. **Client secrets:** Click on "New client secret." 5. **Description:** Give the secret a descriptive name (e.g., "AppSecret"). 6. **Expires:** Choose an expiration date for the secret. 7. **Add:** Click "Add." 8. **Important:** **Copy the *Value* of the client secret immediately!** You will not be able to retrieve it later. This is your application's password. Store it securely. **5. Code Implementation (Conceptual Outline):** This is where you'll write the code to authenticate and interact with the Microsoft Graph API. Here's a general outline, using Python as an example: ```python # Python example (using the Microsoft Graph SDK) import msal import requests # Configuration CLIENT_ID = "YOUR_APPLICATION_CLIENT_ID" # Replace with your Application (client) ID CLIENT_SECRET = "YOUR_APPLICATION_CLIENT_SECRET" # Replace with your client secret AUTHORITY = "https://login.microsoftonline.com/YOUR_TENANT_ID" # Replace with your Tenant ID (or "common" for multi-tenant) SCOPES = ["https://graph.microsoft.com/.default"] # Use ".default" for Application permissions #SCOPES = ["Sites.Read.All"] # Example for delegated permissions # For delegated permissions, you'd typically use a redirect URI and interactive login. # This example focuses on Application permissions for simplicity. # Create a confidential client application app = msal.ConfidentialClientApplication( CLIENT_ID, authority=AUTHORITY, client_credential=CLIENT_SECRET ) # Acquire a token result = None try: result = app.acquire_token_for_client(scopes=SCOPES) except Exception as e: print(f"Error acquiring token: {e}") exit() if "access_token" in result: access_token = result["access_token"] # Use the access token to call the Microsoft Graph API graph_url = "https://graph.microsoft.com/v1.0/sites/YOUR_SITE_ID/lists" # Replace with your SharePoint site ID headers = { "Authorization": f"Bearer {access_token}" } try: response = requests.get(graph_url, headers=headers) response.raise_for_status() # Raise an exception for bad status codes lists = response.json() print("SharePoint Lists:") for list_item in lists["value"]: print(f"- {list_item['displayName']}") except requests.exceptions.RequestException as e: print(f"Error calling Graph API: {e}") else: print(result.get("error_description", "No access token found.")) ``` **Explanation of the Python Code:** * **Import Libraries:** Imports the `msal` (Microsoft Authentication Library) and `requests` libraries. * **Configuration:** Sets the `CLIENT_ID`, `CLIENT_SECRET`, `AUTHORITY` (your Azure AD tenant ID), and `SCOPES` (the permissions you requested). **Replace the placeholder values with your actual values.** The `AUTHORITY` is usually in the format `https://login.microsoftonline.com/<your tenant ID>`. You can find your tenant ID in the Azure portal under Azure Active Directory -> Overview. * **ConfidentialClientApplication:** Creates an instance of the `ConfidentialClientApplication` class, which is used for applications that can securely store a client secret (like a server-side application). * **acquire_token_for_client:** Acquires an access token using the client credentials flow (for Application permissions). For delegated permissions, you'd use `acquire_token_for_user` or `acquire_token_interactive`. * **Call the Microsoft Graph API:** Uses the `requests` library to make a GET request to the Microsoft Graph API endpoint for retrieving lists in a SharePoint site. **Replace `YOUR_SITE_ID` with the actual ID of your SharePoint site.** You can find the site ID in the SharePoint admin center or by using the Graph API itself. * **Error Handling:** Includes `try...except` blocks to handle potential errors during token acquisition and API calls. * **Print Results:** Prints the display names of the SharePoint lists. **Important Considerations:** * **Security:** Protect your client secret! Do not hardcode it directly into your code. Use environment variables or a secure configuration management system. * **Error Handling:** Implement robust error handling to gracefully handle issues like network errors, API errors, and authentication failures. * **Rate Limiting:** The Microsoft Graph API has rate limits. Implement retry logic with exponential backoff to avoid being throttled. * **Pagination:** The Graph API often returns results in pages. You may need to implement pagination to retrieve all the data. * **Permissions:** Always request the *least* privileged permissions necessary for your application to function. * **Logging:** Implement logging to track application activity and diagnose issues. * **User Interface (Optional):** If you need a user interface, you can use a web framework like Flask (Python), Express (Node.js), or ASP.NET Core (C#). You'll need to handle user authentication and authorization in your UI. * **Deployment:** Deploy your application to a suitable hosting environment (e.g., Azure App Service, AWS Lambda, a virtual machine). **Key Takeaways:** * You're building an *application* that uses the Microsoft Graph API to access SharePoint Online, not a traditional server. * Azure AD app registration and permission configuration are crucial. * Choose the appropriate authentication flow (delegated or application permissions) based on your requirements. * Use the Microsoft Graph SDK to simplify API interactions. * Implement robust error handling, security measures, and rate limiting. This detailed explanation should give you a solid foundation for building your SharePoint Online connector. Remember to adapt the code examples to your chosen programming language and framework. Good luck!

MCP Text Editor Server

A Model Context Protocol (MCP) server that provides line-oriented text file editing capabilities through a standardized API. Optimized for LLM tools with efficient partial file access to minimize token usage.

Postlark MCP Server

Enables AI agents to manage and publish blog posts on Postlark via tools like create_post, update_post, list_posts, and more.

Poppify Studio

Photo-to-reel MCP for solo founders and SMBs. Upload 1–10 photos and get a captioned vertical reel for Instagram, TikTok, YouTube Shorts, or Facebook — with motion, library-matched music, and optional AI voiceover.

document-manager-mcp

MCP server for managing product documentation as markdown files. Supports creating, reading, updating, deleting, and searching docs with optional semantic search.

simple-mcp-runner

Simple MCP Runner makes it effortless to safely expose system commands to language models via a lightweight MCP server—all configurable with a clean, minimal YAML file and zero boilerplate.

ProtonMail MCP Server

An MCP server that connects to ProtonMail via Bridge, enabling AI assistants like Claude to manage your email.

mcp-nrepl

Connects to nREPL servers to evaluate Clojure code interactively, enabling AI assistants like Claude to run Clojure code in real-time.

TradeX MCP Server

Enables AI agents to research, analyze, and trade Pokemon card perpetual futures on the TradeX platform. It supports market data retrieval, trading simulations, and secure transaction execution using local Solana keypairs.

mcp-toolselect

An MCP server that recommends specific tools for tasks by learning from usage patterns and historical success rates. It enables users to register tool capabilities and provides ranked recommendations that adapt based on feedback and execution data.

Chotu Robo Server

An MCP server that integrates Arduino-based robotics (ESP32 or Arduino Nano) with AI, allowing control of hardware components like LEDs, motors, servos, and sensors through AI assistants.

Universal Memory MCP Server

A portable MCP server providing a shared intelligent memory system for any MCP-compatible AI tool, enabling storage, retrieval, extraction, and governance of memories across sessions.

@thatworkagency/mcp-shopify

Model Context Protocol server providing read-only access to Shopify Admin API for products, orders, customers, and shop information with multi-store support via HTTP.

Slack MCP Server

Self-hosted MCP server for Slack using User OAuth Token, enabling message management, channel operations, and user interactions via natural language.

Slack MCP Server

A Model Context Protocol (MCP) server for Slack integration, allowing Claude to interact with your Slack workspace.

tsrs-mcp-server

Tushare Rust MCP サーバー

Fabric MCP Server

An MCP server that exposes Fabric patterns as tools for Cline, enabling AI-driven pattern execution directly within Cline tasks.

OpenSCAD MCP Server

Enables AI assistants to render 3D models from OpenSCAD code, generating single views or multiple perspectives with full camera control. Supports animations, custom parameters, and returns base64-encoded PNG images for seamless integration.

TrendKia MCP Server

Enables AI assistants to access and search TrendKia articles, retrieving clean markdown content without HTML scraping.

macOS Defaults MCP Server

Enables reading and writing macOS system defaults and settings through commands equivalent to the defaults command-line tool. Supports listing domains, searching for settings, and modifying system preferences programmatically.