Discover Awesome MCP Servers

Quark Auto-Save MCP Server

Integrates with the quark-auto-save service to automate file saving from Quark Cloud Drive shares. It enables users to manage auto-save tasks, update configurations, and trigger immediate file transfers through natural language.

web-search-agent

An MCP server that enables Claude Code to perform web searches via Bing, read webpage content, and get current time, with a smart search skill for structured multi-source verification.

mcp-stdio-to-streamable-http-adapter

Bridges STDIO MCP clients to Streamable HTTP MCP servers, allowing any STDIO-supported client to use Streamable HTTP servers immediately.

travel-planner

Enables travel planning through natural language, providing weather forecasts, attraction search, itinerary generation, and distance calculations using free APIs.

Onde Inference MCP Server

Enables managing Onde Inference accounts and model catalog operations through MCP tools such as login, app management, model registration, and assignment. Returns structured JSON over stdio for use with any MCP client.

Gemini Code Context MCP

Provides persistent codebase context caching via Gemini API, enabling fast, cost-effective repeat queries for MCP hosts like Claude Code.

Argo Workflow MCP Server

Enables AI agents to manage Argo Workflows through REST API, supporting workflow template and instance operations including creation, submission, monitoring, and deletion with token authentication.

Azure Model Context Protocol (MCP) Hub

Okay, here's a breakdown of resources, tools, and samples for building and integrating Model Context Protocol (MCP) servers on Azure, considering multiple languages. Since MCP is relatively new, direct "MCP on Azure" specific resources are limited. I'll focus on the underlying technologies and how to adapt them. **Understanding the Landscape** * **Model Context Protocol (MCP):** MCP is a protocol designed to provide context to Large Language Models (LLMs). It allows you to pass structured data, metadata, and other relevant information to the LLM along with the user's query. This helps the LLM provide more accurate, relevant, and personalized responses. Think of it as a way to give the LLM a "memory" or "knowledge base" for a specific conversation or task. * **Azure's Role:** Azure provides the infrastructure and services to host and manage your MCP server. This includes compute (Virtual Machines, Azure Container Apps, Azure Functions), data storage (Azure Cosmos DB, Azure SQL Database, Azure Blob Storage), and API management (Azure API Management). * **Key Technologies:** * **API Development:** You'll need to build an API endpoint that receives requests (likely HTTP), processes the MCP data, interacts with your LLM, and returns a response. * **Data Storage:** You'll likely need a database or storage solution to store the context data that your MCP server uses. * **LLM Integration:** You'll need to integrate with an LLM service, such as Azure OpenAI Service, or a locally hosted LLM. * **Authentication/Authorization:** Securing your API is crucial. Azure Active Directory (Azure AD) is a common choice. **Resources and Tools (with Portuguese considerations):** 1. **General Azure API Development (Foundation):** * **Azure Functions:** A serverless compute service that's great for building APIs. Supports multiple languages. * **Languages:** C#, Python, JavaScript/TypeScript, Java, PowerShell, Go. * **Documentation:** * English: [https://learn.microsoft.com/en-us/azure/azure-functions/](https://learn.microsoft.com/en-us/azure/azure-functions/) * Portuguese: Search for "Azure Functions documentação" on Microsoft Learn. While not all content is directly translated, you'll find many articles and tutorials in Portuguese. Use the language selector on the Microsoft Learn site. * **Samples:** Look for HTTP trigger function examples in your chosen language. Adapt these to handle MCP data. * **Azure App Service:** A platform for hosting web applications and APIs. More control than Functions, but requires more management. * **Languages:** Supports a wide range of languages and frameworks (e.g., .NET, Python (Flask, Django), Node.js, Java (Spring Boot)). * **Documentation:** * English: [https://learn.microsoft.com/en-us/azure/app-service/](https://learn.microsoft.com/en-us/azure/app-service/) * Portuguese: Search for "Azure App Service documentação" on Microsoft Learn. * **Samples:** Look for examples of building REST APIs with your chosen framework and deploying them to Azure App Service. * **Azure Container Apps:** A serverless container execution service. Ideal if you're using Docker containers. * **Languages:** Any language that can be containerized. * **Documentation:** * English: [https://learn.microsoft.com/en-us/azure/container-apps/](https://learn.microsoft.com/en-us/azure/container-apps/) * Portuguese: Search for "Azure Container Apps documentação" on Microsoft Learn. * **Samples:** Focus on containerizing your API application (e.g., a Flask API in Python) and deploying it to Azure Container Apps. 2. **Data Storage:** * **Azure Cosmos DB:** A NoSQL database service. Good for flexible data schemas. * **Documentation:** * English: [https://learn.microsoft.com/en-us/azure/cosmos-db/](https://learn.microsoft.com/en-us/azure/cosmos-db/) * Portuguese: Search for "Azure Cosmos DB documentação" on Microsoft Learn. * **Samples:** Look for examples of connecting to Cosmos DB from your chosen language (e.g., Python, .NET) and performing CRUD operations. * **Azure SQL Database:** A relational database service. Good for structured data. * **Documentation:** * English: [https://learn.microsoft.com/en-us/azure/azure-sql/database/](https://learn.microsoft.com/en-us/azure/azure-sql/database/) * Portuguese: Search for "Azure SQL Database documentação" on Microsoft Learn. * **Samples:** Look for examples of connecting to Azure SQL Database from your chosen language. * **Azure Blob Storage:** Object storage for unstructured data (e.g., documents, images). * **Documentation:** * English: [https://learn.microsoft.com/en-us/azure/storage/blobs/](https://learn.microsoft.com/en-us/azure/storage/blobs/) * Portuguese: Search for "Azure Blob Storage documentação" on Microsoft Learn. 3. **LLM Integration (Azure OpenAI Service):** * **Azure OpenAI Service:** Provides access to OpenAI's models (GPT-3, GPT-4, etc.). * **Documentation:** * English: [https://learn.microsoft.com/en-us/azure/cognitive-services/openai/](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/) * Portuguese: Search for "Azure OpenAI Service documentação" on Microsoft Learn. * **Samples:** The Azure OpenAI Service documentation has code samples in Python and C# for interacting with the models. Adapt these to incorporate the context data from your MCP server. * **Langchain:** A framework that simplifies working with LLMs. It has integrations for Azure OpenAI Service and various data sources. * **Documentation:** [https://www.langchain.com/](https://www.langchain.com/) * **Languages:** Primarily Python. * **Note:** While Langchain's documentation might not be directly in Portuguese, the Python code itself is language-agnostic. You can find community tutorials and examples in Portuguese. 4. **API Management:** * **Azure API Management:** A service for managing and securing your APIs. * **Documentation:** * English: [https://learn.microsoft.com/en-us/azure/api-management/](https://learn.microsoft.com/en-us/azure/api-management/) * Portuguese: Search for "Azure API Management documentação" on Microsoft Learn. 5. **Authentication/Authorization:** * **Azure Active Directory (Azure AD):** Microsoft's cloud-based identity and access management service. * **Documentation:** * English: [https://learn.microsoft.com/en-us/azure/active-directory/](https://learn.microsoft.com/en-us/azure/active-directory/) * Portuguese: Search for "Azure Active Directory documentação" on Microsoft Learn. **Example Scenario (Python with Flask and Azure OpenAI):** 1. **Create a Flask API:** Build a simple Flask API endpoint that receives HTTP requests. 2. **Parse MCP Data:** The API endpoint parses the incoming request body, extracting the MCP data (e.g., user ID, conversation history, relevant documents). You'll need to define the structure of your MCP data. 3. **Retrieve Context:** Based on the MCP data, retrieve relevant context information from Azure Cosmos DB (or another data store). 4. **Format Prompt:** Combine the user's query with the retrieved context to create a prompt for the LLM. This is a crucial step for effective context injection. 5. **Call Azure OpenAI:** Use the Azure OpenAI Service Python SDK to send the prompt to the LLM. 6. **Return Response:** Return the LLM's response to the client. 7. **Deploy to Azure:** Deploy the Flask API to Azure App Service or Azure Container Apps. 8. **Secure with Azure AD:** Integrate Azure AD for authentication and authorization. **Code Snippet (Python - Flask Example):** ```python from flask import Flask, request, jsonify import openai import os app = Flask(__name__) # Configure Azure OpenAI openai.api_type = "azure" openai.api_base = os.getenv("AZURE_OPENAI_ENDPOINT") openai.api_version = "2023-05-15" # Or your API version openai.api_key = os.getenv("AZURE_OPENAI_KEY") model_name = "your-deployment-name" # Replace with your deployment name # Mock function to retrieve context (replace with your Cosmos DB logic) def get_context(user_id): # In a real application, you'd query your database here if user_id == "123": return "User is a software engineer specializing in Python." else: return "No context available for this user." @app.route('/mcp', methods=['POST']) def mcp_endpoint(): try: data = request.get_json() user_query = data.get('query') user_id = data.get('user_id') # Example MCP data context = get_context(user_id) prompt = f"Context: {context}\nUser Query: {user_query}\nResponse:" response = openai.Completion.create( engine=model_name, prompt=prompt, max_tokens=150, n=1, stop=None, temperature=0.7, ) llm_response = response.choices[0].text.strip() return jsonify({'response': llm_response}) except Exception as e: return jsonify({'error': str(e)}), 500 if __name__ == '__main__': app.run(debug=True) ``` **Key Considerations for Portuguese:** * **LLM Language Support:** Ensure that the LLM you're using (e.g., Azure OpenAI) has good support for the Portuguese language. Test its performance with Portuguese prompts and context. * **Data Storage Encoding:** Use UTF-8 encoding for your data storage to properly handle Portuguese characters (accent marks, etc.). * **Natural Language Processing (NLP) Libraries:** Consider using NLP libraries that support Portuguese for tasks like tokenization, stemming, and sentiment analysis if you need to process the context data. Examples include: * **spaCy:** Has Portuguese language models. * **NLTK:** Supports Portuguese. * **Translation Services:** If your context data is in English, you might need to use a translation service (e.g., Azure Translator) to translate it to Portuguese before sending it to the LLM. However, this can add latency and complexity. **Steps to Build Your MCP Server:** 1. **Define your MCP data structure:** What information will you pass to the LLM? 2. **Choose your language and framework:** Python (Flask/FastAPI), .NET, Node.js are good choices. 3. **Set up your Azure environment:** Create an Azure account, provision the necessary resources (App Service, Cosmos DB, Azure OpenAI). 4. **Develop your API:** Implement the API endpoint to receive MCP data, retrieve context, format the prompt, and call the LLM. 5. **Test thoroughly:** Test your API with different MCP data and user queries. 6. **Deploy to Azure:** Deploy your API to Azure App Service or Azure Container Apps. 7. **Monitor and optimize:** Monitor the performance of your API and optimize it as needed. **Important Notes:** * **Security:** Implement proper authentication and authorization to protect your API. * **Error Handling:** Implement robust error handling to gracefully handle unexpected errors. * **Logging:** Log important events to help you debug and monitor your API. * **Scalability:** Design your API to be scalable to handle a large number of requests. Consider using Azure's autoscaling features. * **Cost Optimization:** Monitor your Azure resource usage and optimize your configuration to minimize costs. By combining these resources and adapting them to your specific needs, you can build a robust and effective MCP server on Azure using multiple languages. Remember to focus on the core principles of API development, data storage, and LLM integration. Good luck!

persistenceone-bridgekitty

Cross-chain bridge aggregator MCP server for AI agents. Compares routes across LI.FI, deBridge, Relay, Across and Squid to find the best rate. Use when an agent needs to bridge or swap tokens between EVM chains, Solana, or Cosmos. The aggregator of aggregators.

mcp-horoscope

Horoscope MCP — wraps the keyless Horoscope App API.

mcp-malt

Enables access to the documented Malt API for back-office tasks, including retrieving invoices, payments, and commission invoices, as well as SCIM user provisioning for organization accounts.

Handwrytten MCP Server

Enables AI assistants to send real handwritten notes via physical cards using Handwrytten's robotic pen service, along with managing cards, addresses, and orders.

ms-teams

Provides a standardized interface for interacting with Microsoft Teams tools and services through the Model Context Protocol.

agentforge

MCP server that exposes 300+ AI agents as tools via a single API key. Supports listing agents, invoking any agent with chat-completion style messages, checking agent health, and retrieving platform statistics.

nexus

Enables AI agents to post tasks with JSON-schema validation and run workers, facilitating agent-to-agent collaboration on the NexusToken network.

SSW Workforce Intelligence MCP

Enables workforce and labor market analysis for Specified Skilled Workers in Japan by aggregating public census data to provide regional and industry insights, labor supply-demand gaps, competitive landscape, and wage trends.

Multimodal MCP

Enables semantic image search using CLIP embeddings and visual question answering through MCP tools, allowing natural language interaction with images.

ourgroceries-mcp

Manage grocery lists on OurGroceries.com via CLI or MCP, supporting item operations, list management, and natural-language resolution.

Tribunal TRF3: Certidão de Distribuição

MCP server for consulting distribution certificates from TRF3 (Tribunal Regional Federal da 3ª Região) via official source, providing read-only access with usage-based pricing.

Cloudflare Image MCP

An MCP server for image generation and editing using Cloudflare Workers AI, providing OpenAI-compatible APIs and support for multiple models.

P-Link-MCP

Payment & Transaction Tools that allow AI agents to send, receive, and request payments

mcp-sofa

MCP server for Stack Overflow for Agents, enabling search, post creation, voting, and knowledge exchange for AI agents.

perplexity-mcp

Enables web search using Perplexity AI's API, allowing users to search the web with optional recency filters and integration with Claude, Cursor, and other MCP clients.

mcp-usaspending

Enables access to federal spending data from USAspending.gov API via Pipeworx MCP gateway.

argus

Reverse engineering against a running Windows process instead of the file on disk: memory reads, pattern and value scanning, disassembly of the code that actually executed, resolved IAT thunks, caller-chain tracing, and structure recovery. Complements the Ghidra and IDA servers rather than replacing them — correlate_addr maps a runtime address back to a module and RVA.

serpdive

Provides AI coding agents with a live web search tool that returns extracted, answer-ready text from web pages. Enables real-time information retrieval without any local installation or maintenance.

sre-toolkit-mcp

Enables LLM agents to perform SRE reliability calculations like error budgets and burn rates using deterministic tools, integrating with Prometheus and Loki for real data.

AI List My Business

Country-agnostic MCP-callable directory for AI agents to find local SMBs — realtors, insurance agents, medical practitioners — by category, location, or natural-language query. Returns business catalog data and UTM-tagged booking URLs (zero PII).

openrouter-mcp

Enables AI assistants to consult other AI models via OpenRouter for help with coding tasks.