Discover Awesome MCP Servers

Sleeper API MCP

This Model Context Protocol server provides access to the Sleeper Fantasy Football API, enabling agents to fetch data about users, leagues, drafts, rosters, matchups, and player information without requiring an API key.

Playwright MCP Server

Enables web browser automation and inspection using structured data instead of screenshots, allowing AI agents to interact with web pages programmatically through the Playwright framework.

g-gremlin-dynamics-mcp

A dedicated MCP server for interacting with Microsoft Dynamics 365 and Dataverse tools via the g-gremlin CLI. It enables users to read, analyze, and perform write operations on Dataverse environments through supported MCP clients.

frisco-mcp

MCP server for Frisco.pl — lets Claude add groceries to your cart, search products, get nutritional info, and manage recipes, all via natural language.

BACnet MCP Server

A lightweight MCP server that connects LLM agents to BACnet devices for building automation, enabling real-time monitoring, actuation, and task orchestration.

MCP JSON Sanitizer

Enables repair of malformed JSON strings into valid JSON for agent workflows by fixing common LLM formatting issues. Supports cleanup of code fences, smart quotes, unquoted keys, trailing commas, and missing brackets to ensure reliable data parsing.

Guía de Instalación de Supabase MCP Server

Tentu, berikut adalah terjemahan dari "Guía detallada de instalación para Supabase MCP Server" ke dalam bahasa Indonesia: **Panduan Instalasi Lengkap untuk Supabase MCP Server** Atau, bisa juga: **Panduan Instalasi Mendetail untuk Server Supabase MCP** Kedua terjemahan tersebut menyampaikan arti yang sama. Pilihan mana yang lebih baik tergantung pada preferensi gaya Anda.

Google Contacts MCP Server

Enables AI assistants to access and search Google Contacts through per-user OAuth authentication on serverless AWS Lambda. Provides read-only access to personal contacts with zero data storage and real-time API queries.

OCI MCP Server

Enables interaction with Oracle Cloud Infrastructure services through a unified interface. Supports comprehensive OCI resource management including compute instances, storage, networking, databases, and monitoring through natural language commands in VS Code.

Streamfog MCP

AI-driven AR lens orchestrator for live OBS streams that enables control of Streamfog face filters, AR effects, and Vtuber avatars through MCP tools via the local Streamer.bot WebSocket bridge.

Withings MCP

Local-first MCP server that connects AI agents to your Withings body, sleep, activity and heart data.

Xafari MCP

An MCP server and crawler for Xafari documentation that enables AI agents to search, retrieve pages, and extract code examples from a local index. It provides structured documentation access through stdio or HTTP interfaces for seamless IDE integration.

MCP-Todoist Integration

Here are a few options for an MCP (presumably referring to a **Minimal, Complete, and Verifiable Prototype**) server for Todoist integration for natural language task management, along with considerations for each: **Option 1: Simple Flask/FastAPI Server with Todoist API** * **Description:** A lightweight Python server using Flask or FastAPI. It receives natural language input, uses a basic NLP library (like spaCy or NLTK) to extract keywords, and then uses the Todoist API to create tasks. * **Pros:** * **Simple to implement:** Flask/FastAPI are easy to learn and use. * **Direct Todoist integration:** Uses the official Todoist API. * **Good for a basic prototype:** Focuses on core functionality. * **Cons:** * **Limited NLP capabilities:** Basic keyword extraction won't handle complex sentences or context well. * **Requires API key management:** You'll need to handle Todoist API keys securely. * **Scalability:** Not designed for high traffic. * **Example Workflow:** 1. User sends: "Remind me to buy milk tomorrow at 6 PM" 2. Server: * Receives the text. * Uses spaCy to identify "buy milk" as the task, "tomorrow" as the date, and "6 PM" as the time. * Uses the Todoist API to create a task with the content "buy milk" and a due date/time of tomorrow at 6 PM. * **Tech Stack:** * Python * Flask or FastAPI * spaCy or NLTK (for NLP) * `todoist-api-python` (Python Todoist API library) * **MCP Focus:** Demonstrates the basic flow of receiving text, extracting information, and creating a Todoist task. **Option 2: Serverless Function (AWS Lambda, Google Cloud Functions, Azure Functions) with Todoist API** * **Description:** A serverless function that triggers on an HTTP request. It performs the same NLP and Todoist API integration as Option 1, but without managing a server. * **Pros:** * **Scalable:** Serverless functions scale automatically. * **Cost-effective:** You only pay for the function when it's used. * **Easy deployment:** Relatively easy to deploy. * **Cons:** * **Cold starts:** Serverless functions can have a delay when they're first invoked. * **Limited execution time:** Serverless functions have time limits. * **Debugging:** Debugging can be more challenging than with a traditional server. * **Example Workflow:** Same as Option 1. * **Tech Stack:** * Python (or Node.js, Go, etc.) * AWS Lambda, Google Cloud Functions, or Azure Functions * spaCy or NLTK (for NLP) * `todoist-api-python` (or equivalent for other languages) * **MCP Focus:** Demonstrates a scalable and cost-effective way to integrate with Todoist. **Option 3: Using a Pre-built NLP Service (Dialogflow, LUIS, Rasa) with a Webhook to Todoist** * **Description:** Leverages a pre-built NLP service to handle the natural language understanding. The NLP service is configured to recognize task-related intents and entities (e.g., task description, due date, priority). When an intent is matched, the NLP service sends a webhook to your server (or serverless function), which then uses the Todoist API to create the task. * **Pros:** * **Improved NLP:** Pre-built NLP services offer more sophisticated natural language understanding. * **Easier intent and entity management:** These services provide tools for defining and managing intents and entities. * **Reduced coding effort:** You don't need to write as much NLP code. * **Cons:** * **Dependency on a third-party service:** You're reliant on the NLP service's availability and pricing. * **Learning curve:** You need to learn how to use the NLP service. * **Cost:** Some NLP services can be expensive for high usage. * **Example Workflow:** 1. User sends: "Remind me to buy milk tomorrow at 6 PM" 2. Dialogflow (or LUIS, Rasa): * Recognizes the intent "create_task". * Extracts the entities: `task_description` = "buy milk", `due_date` = "tomorrow", `due_time` = "6 PM". * Sends a webhook to your server with the intent and entities. 3. Server: * Receives the webhook. * Uses the Todoist API to create a task with the extracted information. * **Tech Stack:** * Python (or Node.js, Go, etc.) * Flask or FastAPI (for the webhook endpoint) * Dialogflow, LUIS, or Rasa (for NLP) * `todoist-api-python` (or equivalent for other languages) * **MCP Focus:** Demonstrates the use of a pre-built NLP service for more accurate and robust natural language understanding. **Recommendation for an MCP:** Start with **Option 1 (Simple Flask/FastAPI Server)**. It's the easiest to implement and will allow you to quickly demonstrate the core functionality of integrating natural language input with Todoist. Once you have a working prototype, you can then explore Option 3 (using a pre-built NLP service) to improve the accuracy and robustness of your NLP. Option 2 (Serverless) is a good choice for deployment once you have a working prototype. **Indonesian Translation of the Recommendation:** **Rekomendasi untuk MCP (Minimal, Complete, and Verifiable Prototype):** Mulailah dengan **Opsi 1 (Server Flask/FastAPI Sederhana)**. Ini adalah yang paling mudah diimplementasikan dan akan memungkinkan Anda untuk dengan cepat mendemonstrasikan fungsionalitas inti dari mengintegrasikan input bahasa alami dengan Todoist. Setelah Anda memiliki prototipe yang berfungsi, Anda kemudian dapat menjelajahi Opsi 3 (menggunakan layanan NLP yang sudah jadi) untuk meningkatkan akurasi dan ketahanan NLP Anda. Opsi 2 (Serverless) adalah pilihan yang baik untuk penyebaran setelah Anda memiliki prototipe yang berfungsi.

SyncroMSP MCP Server

Enables AI assistants to fully access and manage SyncroMSP resources including tickets, customers, assets, invoices, and over 30 resource types through 180+ API endpoints.

DemandSphere MCP Server

Connects AI assistants to the DemandSphere search intelligence platform, enabling SERP analytics and GenAI visibility tracking through 20 tools across five domains.

claude-config-mcp

Manages Claude Code configuration and provides cross-session intelligent memory via the Luoshu system, enabling Claude to remember decisions and project context across conversations.

Filesystem MCP Server

A Model Context Protocol server that provides AI agents with secure access to local filesystem operations, enabling reading, writing, and managing files through a standardized interface.

Uniswap MCP Server

Exposes Uniswap V2 and V3 on-chain data and swap execution as MCP tools, resources, and prompts, enabling AI agents to query prices, inspect pools, get quotes, and execute trades.

Expert MCP

Enables AI models to consult a configured advanced model (e.g., GPT-5.5, Claude Opus 4.7) via a streamable HTTP MCP server for deep analysis and expert advice on complex problems.

Web3 Research MCP

Penelitian Mendalam untuk kripto - gratis & sepenuhnya lokal

Config MCP Server

Enables AI assistants to search documentation, read and update configuration files, and discover settings across your development workspace. Supports JSON, YAML, TOML, and Markdown files with seamless integration for GitHub Copilot and other MCP clients.

Codebase MCP Server

A Model Context Protocol server that analyzes application codebases with real-time file watching, providing AI assistants like Claude with deep insights into project structure, code patterns, and architecture.

database

Database MCP server for MySQL, MariaDB, PostgreSQL & SQLite

markupR MCP Server

Enables AI coding agents to capture screen and voice recordings, extract timestamped frames, and receive structured Markdown reports with context for bug fixing and UI feedback.

Gmail MCP Server

A Node.js server that connects MCP to Gmail, enabling LLMs to send, read, and manage emails securely using the Gmail API.

Drupal MCP Server

Enables AI models to interact with Drupal 10+ sites via JSON:API for querying, searching, and retrieving content. It supports listing content types, searching by title across all types, and fetching detailed node information including relationships.

rapid7-mcp

A unified MCP server for Rapid7's security platform, exposing InsightVM (vulnerability management), InsightIDR (SIEM/investigations), and Metasploit Pro (pentest telemetry) as tools for Claude, Cursor, and any MCP-compatible LLM client.

Elastic MCP Server

A read-only MCP server that gives AI assistants natural language access to Elasticsearch/Kibana logs for querying and analysis.

Codebase RAG MCP Server

Enables semantic search and retrieval of code files using embeddings stored in PostgreSQL. Supports intelligent codebase exploration through natural language queries, file listing, and content retrieval.

scplus-mcp

A local code-intelligence MCP server that provides structural, exact-query, related-search, and research capabilities from a validated repo-local index, enabling agents to perform deterministic lookups, semantic search, and code analysis.