Discover Awesome MCP Servers

aura-mnemos

A persistent-memory MCP server for AI agents with an honest health endpoint that survives its store dying.

mcp-youtube

High-efficiency YouTube MCP server: Get token-optimized, structured data for your LLMs using the YouTube Data API v3.

@looppause/mcp

Pauses AI agent execution and routes approval requests to humans via Slack or email, with cryptographically signed proof of the human's decision.

obsidian-mcp-server

Connects Claude.ai to your local Obsidian vault for full CRUD access, search, and daily note creation via the Model Context Protocol.

ToolRoute

Intelligent routing layer for AI agents — recommends the best MCP server and LLM for any task, scored on 132+ real benchmark executions.

Supply Chain Disruption Monitor

MCP server that exposes tools for monitoring supply chain disruptions, including vessel positions, port weather, congestion, and news. Includes an AI agent that synthesizes these sources to assess route risks.

cro_ro_cadastro_mcp

MCP server to query official dental council registration data for Rondônia, Brazil, via a pay-per-use hosted API.

ActTrace

MCP server for EU AI Act compliance, providing risk classification of AI features and Article 50 transparency notices.

Geond Agent Protocol

Local-first shared memory and coordination layer for AI coding agents, with repository evidence, reservations, handoffs, code graph context, and dashboard review backed by PostgreSQL/pgvector.

ERP MCP Server

It enables LLMs to query enterprise data such as sales orders, stock levels, and vendor information through structured MCP-compliant tools, using localized JSON databases for demonstration.

agent-cost-allocator-mcp

Multi-tenant LLM cost attribution for chargeback billing.

Azure Assistant MCP

Enables natural language exploration of Azure environments by generating and executing KQL queries against Azure Resource Graph. Supports multi-tenant configurations, subscription scoping, and provides direct access to Azure resource information through conversational interactions.

Tribunal TJSC: Processo

Enables consultation of TJSC court processes from official source through a read-only MCP tool.

Untappd MCP Server using Azure Functions

Okay, here's an example of a minimal, complete, and verifiable (MCP) Azure Function written in F# that uses the Azure Functions programming model (isolated process): ```fsharp namespace MyFunctionApp open Microsoft.Azure.Functions.Worker open Microsoft.Azure.Functions.Worker.Http open System.Net [<EntryPoint>] let Run([<HttpTrigger(AuthorizationLevel.Anonymous, "get", "post")>] req: HttpRequestData, context: FunctionContext) : HttpResponseData = context.GetLogger "HttpExample" |> ignore let name = req.Query.GetValues("name") |> Seq.tryHead |> Option.defaultValue "Azure Functions" let response = req.CreateResponse(HttpStatusCode.OK) response.Headers.Add("Content-Type", "text/plain; charset=utf-8") response.WriteString($"Welcome to F#, {name}!") response ``` **Explanation:** * **`namespace MyFunctionApp`**: Defines the namespace for your function. Important for organization and potential dependency resolution. * **`open Microsoft.Azure.Functions.Worker`**: Imports the core Azure Functions Worker SDK. This is essential for isolated process functions. * **`open Microsoft.Azure.Functions.Worker.Http`**: Imports the HTTP-specific types for working with HTTP triggers and responses. * **`open System.Net`**: Imports the `System.Net` namespace, which provides access to network-related classes, including `HttpStatusCode`. * **`[<EntryPoint>]`**: This attribute marks the `Run` function as the entry point for the Azure Function. It's crucial. * **`let Run([<HttpTrigger(AuthorizationLevel.Anonymous, "get", "post")>] req: HttpRequestData, context: FunctionContext) : HttpResponseData =`**: * **`let Run(...)`**: Defines the function named `Run`. This is the standard name for an Azure Function. * **`[<HttpTrigger(AuthorizationLevel.Anonymous, "get", "post")>]`**: This attribute defines the trigger for the function. In this case, it's an HTTP trigger that responds to both GET and POST requests. `AuthorizationLevel.Anonymous` means no authentication is required. You can change this to `Function`, `Admin`, or `User` if you need authentication. * **`req: HttpRequestData`**: The `req` parameter is an `HttpRequestData` object, which represents the incoming HTTP request. It provides access to headers, query parameters, the request body, etc. * **`context: FunctionContext`**: The `context` parameter is a `FunctionContext` object, which provides access to the function's execution context, including logging, invocation ID, and other metadata. * **`: HttpResponseData`**: Specifies that the function returns an `HttpResponseData` object, which represents the HTTP response. * **`context.GetLogger "HttpExample" |> ignore`**: Gets a logger instance (named "HttpExample") from the context. The `ignore` function discards the logger instance, but in a real-world function, you would use the logger to write log messages. * **`let name = ...`**: This section extracts the `name` query parameter from the request. * **`req.Query.GetValues("name")`**: Gets a sequence of values associated with the query parameter "name". Query parameters are part of the URL (e.g., `?name=John`). * **`|> Seq.tryHead`**: Attempts to get the first element of the sequence. If the sequence is empty (i.e., the "name" parameter is not present), it returns `None`. * **`|> Option.defaultValue "Azure Functions"`**: If the `tryHead` returns `None`, this provides a default value of "Azure Functions". So, if the `name` parameter is missing, the function will use the default name. * **`let response = req.CreateResponse(HttpStatusCode.OK)`**: Creates an `HttpResponseData` object with an HTTP status code of 200 (OK). The `req.CreateResponse` method is the recommended way to create a response object. * **`response.Headers.Add("Content-Type", "text/plain; charset=utf-8")`**: Sets the `Content-Type` header of the response to `text/plain; charset=utf-8`. This tells the client that the response body is plain text encoded in UTF-8. * **`response.WriteString($"Welcome to F#, {name}!")`**: Writes the response body. The `$` indicates an interpolated string, which allows you to embed variables directly into the string. * **`response`**: Returns the `HttpResponseData` object. **How to Deploy and Test:** 1. **Create an Azure Functions Project:** Use the Azure Functions extension in VS Code or the Azure CLI to create a new F# Azure Functions project using the isolated process model. Make sure you select the `.NET 6.0` or later runtime. 2. **Replace the Default Function:** Replace the contents of the default function file (usually `Function1.fs`) with the code above. 3. **Publish to Azure:** Use the Azure Functions extension in VS Code or the Azure CLI to publish your project to an Azure Functions app. 4. **Test:** After deployment, you can test the function by sending an HTTP request to its URL. For example: * `https://<your-function-app-name>.azurewebsites.net/api/Function1?name=YourName` * If you don't provide the `name` parameter, it will default to "Azure Functions". **Key Considerations for Isolated Process Functions:** * **Isolated Process:** Isolated process functions run in a separate process from the Azure Functions host. This provides better isolation and allows you to use different .NET runtimes. * **`Microsoft.Azure.Functions.Worker` Package:** You *must* use the `Microsoft.Azure.Functions.Worker` NuGet package for isolated process functions. Do *not* use the `Microsoft.Azure.WebJobs.Extensions.*` packages, which are for in-process functions. * **`FunctionContext`:** The `FunctionContext` is essential for accessing logging and other function-specific information. * **`HttpRequestData` and `HttpResponseData`:** Use these types for working with HTTP requests and responses in isolated process functions. They provide a more streamlined and efficient way to handle HTTP data. * **Startup Class (Optional):** For more complex scenarios (dependency injection, configuration), you can create a `Startup.fs` file to configure your function app. This example provides a solid foundation for building more complex Azure Functions in F#. Remember to adjust the trigger type, authorization level, and function logic to meet your specific requirements.

fittok

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

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.

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.

DocuWare Read-only MCP

Read-only MCP server for DocuWare that lets you list file cabinets, search documents, view metadata, and download documents.

krexel-mcp

Enables AI assistants to deploy, manage, and rollback websites via the Krexel API, supporting site uploads, deploys, logs, rollbacks, environment variables, and status checks.

effective-potato

Provides a sandboxed Ubuntu 24.04 container for secure command execution, with tools for git operations, background tasks, and GUI automation (screenshots and screen recording).

dev.io MCP Server

Captures AI conversation summaries, converts them to Markdown posts, and manages local or remote publishing with metrics tracking.

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.

lab-units-mcp

Converts clinical blood-test results between conventional and SI units and resolves lab-marker names to canonical analytes.

aspicio-dxf-viewer

Opens, inspects, and renders DXF/CAD drawings for AI agents: describe_dxf returns structured facts (layers with actual drawn colors, units, bounds, text content) and render_dxf returns PNG images. On MCP Apps hosts like ChatGPT and Claude, view_dxf opens an interactive in-chat viewer with pan, zoom, and layer toggles.

MetaVision AI Studio

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

skilltap

Exposes MCP tools to list, search, and load Markdown skills from a local folder, enabling coding agents to discover and reuse procedural knowledge.

kalvium-livebooks

A read-only MCP server that lets you browse Kalvium Livebooks using your existing browser session, listing livebooks and lessons and retrieving lesson content as Markdown.

Jira MCP

MCP server for Jira ticket context via REST API — read issues, search, post comments with @mentions.

remote-mcp-server-authless

Deploy a remote MCP server on Cloudflare Workers without authentication. Supports custom tools and can connect to AI Playground and Claude Desktop via SSE.

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.