Discover Awesome MCP Servers

Book4Time MCP Server

Enables interaction with the Book4Time API through an Azure Function-hosted server. It allows users to query product information and manage bookings using MCP-compatible clients like Claude Desktop.

trac-mcp-server

Enables AI agents to manage Trac projects with full CRUD operations on tickets, wiki pages, and milestones via the Model Context Protocol.

web-scrapper-stdio

A headless web scraping server that extracts main content from web pages into Markdown, text, or HTML for AI and automation integration. It features per-domain rate limiting and robust error handling using Playwright and BeautifulSoup.

Azure DevOps Multi-Organization MCP Server

Enables interaction with multiple Azure DevOps organizations simultaneously, providing access to pipelines, builds, repositories, and pull requests across different organizations without switching contexts or restarting the server.

Untappd MCP Server using Azure Functions

Okay, here's an example of a simple Azure Function written in F# that uses the Managed Identity (formerly known as Managed Service Identity or MSI) to access Azure resources. This example will demonstrate how to retrieve an access token for Azure Key Vault. ```fsharp namespace MyAzureFunction open System open System.Net open System.Net.Http open System.Threading.Tasks open Microsoft.Azure.WebJobs open Microsoft.Azure.WebJobs.Extensions.Http open Microsoft.AspNetCore.Http open Microsoft.Extensions.Logging open Azure.Identity // Function to get an access token for Azure Key Vault using Managed Identity let getAccessTokenForAzureKeyVault (log: ILogger) : Task<string> = task { try let credential = new DefaultAzureCredential() let tokenRequestContext = new Azure.Identity.TokenRequestContext([| "https://vault.azure.net/.default" |]) let! accessToken = credential.GetTokenAsync tokenRequestContext log.LogInformation($"Successfully retrieved access token for Key Vault. Expires on: {accessToken.ExpiresOn}") return accessToken.Token with | ex -> log.LogError($"Error retrieving access token: {ex.Message}") return null } // Azure Function triggered by HTTP [<FunctionName("MyHttpTriggeredFunction")>] let Run ( [<HttpTrigger(AuthorizationLevel.Function, "get", "post", Route = null)>] req: HttpRequest, log: ILogger) : Task<IActionResult> = task { log.LogInformation "C# HTTP trigger function processed a request." let name = match req.Query.["name"].ToString() with | null -> let body = new System.IO.StreamReader(req.Body).ReadToEnd() let data = Newtonsoft.Json.JsonConvert.DeserializeObject<{| name : string |}>(body) match data with | null -> "Azure Function" | _ -> data.name | name -> name let accessTokenTask = getAccessTokenForAzureKeyVault log let! accessToken = accessTokenTask let responseMessage = if String.IsNullOrEmpty accessToken then $"Hello, {name}. Failed to retrieve Key Vault access token." else $"Hello, {name}. Successfully retrieved Key Vault access token." let response = new Microsoft.AspNetCore.Mvc.OkObjectResult(responseMessage) :> IActionResult return response } ``` **Explanation:** 1. **Dependencies:** Make sure you have the necessary NuGet packages installed in your Azure Function project: * `Microsoft.Azure.Functions.Worker.Sdk` * `Microsoft.Azure.Functions.Worker` * `Azure.Identity` * `Newtonsoft.Json` (if you're using JSON deserialization) 2. **Namespaces:** The code imports necessary namespaces for HTTP handling, logging, and Azure Identity. 3. **`getAccessTokenForAzureKeyVault` Function:** * This function is responsible for obtaining the access token for Azure Key Vault. * It uses `DefaultAzureCredential()`. `DefaultAzureCredential` automatically tries different authentication methods (including Managed Identity if the function is running in an Azure environment with Managed Identity enabled). * `TokenRequestContext` specifies the scope for the access token. `"https://vault.azure.net/.default"` is the standard scope for accessing Azure Key Vault. * `credential.GetTokenAsync` retrieves the access token. * Error handling is included to log any exceptions that occur during token retrieval. 4. **`Run` Function (Azure Function Entry Point):** * `[<FunctionName("MyHttpTriggeredFunction")>]`: This attribute defines the name of the Azure Function. * `[<HttpTrigger(AuthorizationLevel.Function, "get", "post", Route = null)>]`: This attribute configures the function to be triggered by HTTP requests (GET or POST). `AuthorizationLevel.Function` means you'll need a function key to access it. * The function retrieves a `name` parameter from the query string or the request body (JSON). * It calls `getAccessTokenForAzureKeyVault` to get the Key Vault access token. * It constructs a response message indicating whether the access token was successfully retrieved. * Finally, it returns an `OkObjectResult` containing the response message. **How to Deploy and Test:** 1. **Create an Azure Function App:** If you don't already have one, create an Azure Function App in the Azure portal. Choose the `.NET` runtime stack. 2. **Enable Managed Identity:** In the Azure portal, go to your Function App. Under "Settings," find "Identity." Enable "System assigned managed identity" and save. Note the Object (principal) ID. 3. **Grant Key Vault Access (if needed):** If you want to *use* the access token to access Key Vault secrets, you'll need to grant the Managed Identity permissions to Key Vault. Go to your Key Vault in the Azure portal. Under "Access configuration", choose "Azure role-based access control (recommended)". Then go to "Access control (IAM)" and add a role assignment. Assign the "Key Vault Secrets User" role to the Managed Identity of your Function App. You can search for the Function App's Managed Identity using its name. 4. **Deploy the Function:** Deploy your F# Azure Function code to the Function App. You can use Visual Studio, Azure DevOps, or other deployment methods. 5. **Test the Function:** Use a tool like Postman or `curl` to send an HTTP request to your function's URL. For example: ``` https://<your-function-app-name>.azurewebsites.net/api/MyHttpTriggeredFunction?name=Test ``` You'll need to include the function key in the request header (if you're using `AuthorizationLevel.Function`). You can find the function key in the Azure portal under your Function App -> Functions -> Your Function -> Function Keys. The response should indicate whether the Key Vault access token was successfully retrieved. If it was, the function is correctly using Managed Identity. **Important Considerations:** * **Error Handling:** The example includes basic error handling, but you should add more robust error handling for production environments. * **Configuration:** For more complex scenarios, you might want to use Azure App Configuration or other configuration services to manage your application settings. * **Logging:** Use the `ILogger` interface to log important information and errors. Azure Functions provides integration with Azure Monitor for logging and monitoring. * **Security:** Always follow security best practices when developing Azure Functions, including using Managed Identity, minimizing permissions, and validating input. * **Key Vault Usage:** This example only retrieves the access token. To actually *use* the token to retrieve secrets from Key Vault, you would need to use the `Azure.Security.KeyVault.Secrets` NuGet package and the `SecretClient` class. You would then pass the access token to the `SecretClient`'s constructor. However, the `SecretClient` can also use `DefaultAzureCredential` directly, so you might not need to manually retrieve the token in many cases. This comprehensive example should get you started with using Managed Identity in your F# Azure Functions. Remember to adapt the code to your specific requirements and follow best practices for security and error handling.

MyDriverParis MCP Server

Enables booking premium private chauffeur transfers in Paris and across Europe directly from AI agents. Provides tools to list vehicles, get quotes, book rides, and retrieve service information.

fittok

An MCP server that filters and compresses context by 80-90% before sending to an LLM, using code knowledge graphs and compression.

Portfolio MCP Server

An MCP server that exposes an AI project portfolio as queryable tools, allowing users to ask about projects, search by technology, or get details via natural language.

MetaVision AI Studio

Generate 3D models from text or image. Browse 10K+ free 3D models. AI creative platform with API

mcp-server-creem

MCP server for Creem.io providing tools to manage subscriptions, products, payments, license keys, and more through the Creem API.

PayHere Documentation MCP Server

Provides AI-ready documentation for the PayHere payment gateway, enabling access to API references, SDK guides, and documentation search through MCP tools.

mcp-postman-runner

Run the requests in a Postman collection folder and get structured, assertion-level results back straight from your AI assistant.

AskOnSlackMCP

A Human-in-the-Loop MCP server that enables AI assistants to request information or clarification from humans via Slack. It uses real-time, thread-based conversations with socket mode integration to bridge the gap between AI systems and human experts.

Arcate MCP Connect

Gives AI agents direct access to your Arcate product discovery workspace to read signals, browse roadmaps, and ingest new customer feedback. It enables users to search existing data and link signals to initiatives through natural language commands.

Document Conversion Assistant

Enables conversion between multiple document formats including Markdown, HTML, TXT, PDF, and DOCX with automatic format detection. Supports high-fidelity document transformation while preserving content integrity.

BMAD MCP Server

A Model Context Protocol (MCP) server that bridges BMAD agents with GitHub Copilot, enabling AI-assisted development workflows through specialized agent tools and prompts.

Angular Toolkit MCP

A Model Context Protocol server that provides Angular project analysis and refactoring capabilities, enabling LLMs to analyze component usage patterns, dependency structures, and perform safe refactoring with breaking change detection.

Halo ITSM MCP Server

Enables AI-driven IT service management by exposing the full Halo ITSM REST API through 172 tools across 43 resource domains to any MCP-compatible client.

Pubtator MCP Server

Provides an async Python server for interacting with the PubTator3 API, exposing multiple biomedical text-mining tools compatible with the MCP agent protocol.

Halo LMS MCP Server

MCP server that provides access to Grand Canyon University's Halo LMS, enabling AI agents to manage classes, assignments, grades, discussions, announcements, inbox messages, notifications, and user profiles.

remote-mcp-server-authless

Deploy a remote MCP server on Cloudflare Workers without authentication, enabling custom tools accessible via SSE and compatible with clients like Claude Desktop.

MCP Server Template (

Templat ini membantu Anda dengan cepat melakukan bootstrap proyek server Model Context Protocol (MCP) baru berdasarkan praktik yang direkomendasikan.

Microsoft Fabric RTI MCP Server

Enables AI agents to interact with Microsoft Fabric Real-Time Intelligence services, allowing for seamless data querying, analysis, and streaming capabilities.

memtrace

Memtrace is a persistent memory layer for coding agents, built as a bi‑temporal structural knowledge graph over your codebase (AST‑driven symbols and relationships, plus temporal evolution and cross‑service API topology)

MCP TypeScript Template

A starter template for building remote Model Context Protocol servers using TypeScript, providing modern tooling and best practices while leveraging the MCP TypeScript SDK.

@vorionsys/mcp-server

MCP server for AI-agent governance using trust scoring, behavioral signals, and pre-flight action checks.

WooCommerce MCP Server

Enables AI agents to manage WooCommerce stores, including products, orders, customers, categories, coupons, attributes, variations, order notes, refunds, reports, payment gateways, meta data, reviews, settings, data, posts, and system status through natural language.

TouchDesigner MCP

Enables control of a running TouchDesigner instance via MCP protocol, providing tools to manage operators, parameters, and project state through a local HTTP bridge.

Rvvel Affiliate Links MCP Server

Central hub for managing affiliate links across all Rvvel applications and AI agents, enabling storage, retrieval, search, and tracking.