Discover Awesome MCP Servers

cdcx

MCP server for the Crypto.com Exchange API, providing 86 dynamically generated tools for market data, trading, account management, and more with real-time WebSocket streaming and safety enforcement.

Unsloth MCP Server

Cermin dari

Bitbucket Server MCP

An MCP server for Atlassian Bitbucket Server / Data Center, providing 66 tools for managing projects, repositories, branches, files, commits, pull requests, and code search with opt-in deletion operations.

n8n Advisor

Enables AI assistants to review workflow status in n8n instances, including active/inactive counts and workflows with recent errors.

Mr. Magic MCP Server

Bridges multiple lyrics providers (LRCLIB, Genius, Musixmatch, Melon) into a single toolchain accessible via MCP, HTTP, or CLI.

Aleph-10: Vector Memory MCP Server

Vector Memory MCP Server - Sebuah server MCP dengan kemampuan penyimpanan memori berbasis vektor.

Toolhouse MCP Server

Server MCP ini memungkinkan Anda untuk menghubungkan klien MCP dengan alat-alat Toolhouse.

Document Processing Server

Menyediakan pemrosesan dokumen yang komprehensif, termasuk membaca, mengonversi, dan memanipulasi berbagai format dokumen dengan kemampuan pemrosesan teks dan HTML tingkat lanjut.

heracleum-tox-mcp-server

Reproduces the in-silico toxicological profile of Heracleum sosnowskyi metabolites from Rassabina & Fedorov (2025) using open-source models for LD50 prediction, toxicity classification, chemical space clustering, and synthesis cost estimation.

@aws/ftr-eval-mcp

Automates the AWS Foundational Technical Review (FTR) partner self-assessment by evaluating SOC 2 and WAFR reports against defined controls, returning structured PASS/FAIL decisions with reasoning.

MCP Cron

Here are a few options for an MCP (Master Control Program) server that schedules and manages tasks, along with considerations for each: **1. Dedicated Task Scheduling Systems (Most Common & Recommended):** * **Apache Airflow:** A very popular open-source platform for programmatically authoring, scheduling, and monitoring workflows. It uses Python to define workflows as Directed Acyclic Graphs (DAGs). * **Pros:** Highly scalable, robust, large community support, good for complex workflows, integrates with many data sources and services. * **Cons:** Steeper learning curve, requires Python knowledge, can be overkill for very simple tasks. * **Suitable for:** Data pipelines, ETL processes, machine learning workflows, complex automation. * **Celery:** A distributed task queue. You define tasks in Python, and Celery distributes them to worker processes. * **Pros:** Simple to set up, good for asynchronous tasks, integrates well with web frameworks like Django and Flask. * **Cons:** Less sophisticated workflow management than Airflow, requires a message broker (e.g., RabbitMQ, Redis). * **Suitable for:** Background processing, image processing, sending emails, handling long-running operations. * **Luigi:** Another Python-based workflow management system. * **Pros:** Focuses on dependency resolution and data pipeline management. * **Cons:** Less popular than Airflow, smaller community. * **Suitable for:** Data pipelines, batch processing. * **Prefect:** A modern workflow orchestration platform. * **Pros:** More user-friendly than Airflow, good for data engineering workflows, supports Python. * **Cons:** Newer than Airflow, smaller community. * **Suitable for:** Data pipelines, ETL processes, machine learning workflows. **2. Operating System Task Schedulers (Simpler, but Limited):** * **Cron (Linux/Unix):** A standard Unix utility for scheduling tasks to run at specific times. * **Pros:** Simple to use for basic scheduling, widely available. * **Cons:** Limited in terms of dependency management, error handling, and monitoring. Not suitable for complex workflows. * **Suitable for:** Simple, repetitive tasks like backups, log rotation, or running scripts at regular intervals. * **Task Scheduler (Windows):** The Windows equivalent of Cron. * **Pros:** Built into Windows, easy to use for basic scheduling. * **Cons:** Similar limitations to Cron. * **Suitable for:** Simple tasks on Windows systems. **3. Custom Solutions (If You Have Very Specific Needs):** * You could build your own task scheduler using a programming language like Python, Java, or Go, and a database to store task information. * **Pros:** Complete control over the implementation, tailored to your exact requirements. * **Cons:** Significant development effort, requires expertise in scheduling algorithms, concurrency, and error handling. Generally not recommended unless you have very unusual needs. **Choosing the Right Option:** To choose the best option, consider these factors: * **Complexity of your tasks:** Simple tasks can be handled by Cron or Task Scheduler. Complex workflows require a dedicated task scheduling system like Airflow, Celery, Luigi, or Prefect. * **Scalability:** If you need to handle a large number of tasks or scale your system, Airflow, Celery, or Prefect are good choices. * **Programming language:** Airflow, Celery, Luigi, and Prefect are primarily Python-based. * **Integration with other systems:** Consider how well the task scheduler integrates with your existing infrastructure and tools. * **Learning curve:** Airflow has a steeper learning curve than Cron or Celery. * **Maintenance:** Consider the ongoing maintenance and support requirements of each option. **In summary, for most use cases, Apache Airflow, Celery, or Prefect are the best choices for an MCP server that schedules and manages tasks. Cron or Task Scheduler are suitable for very simple tasks.** --- **Indonesian Translation:** Berikut adalah beberapa opsi untuk server MCP (Master Control Program) yang menjadwalkan dan mengelola tugas, beserta pertimbangan untuk masing-masing: **1. Sistem Penjadwalan Tugas Khusus (Paling Umum & Direkomendasikan):** * **Apache Airflow:** Platform sumber terbuka yang sangat populer untuk membuat, menjadwalkan, dan memantau alur kerja secara terprogram. Menggunakan Python untuk mendefinisikan alur kerja sebagai Directed Acyclic Graphs (DAGs). * **Kelebihan:** Sangat skalabel, kuat, dukungan komunitas besar, bagus untuk alur kerja kompleks, terintegrasi dengan banyak sumber data dan layanan. * **Kekurangan:** Kurva pembelajaran lebih curam, membutuhkan pengetahuan Python, bisa berlebihan untuk tugas yang sangat sederhana. * **Cocok untuk:** Saluran data, proses ETL, alur kerja pembelajaran mesin, otomatisasi kompleks. * **Celery:** Antrian tugas terdistribusi. Anda mendefinisikan tugas dalam Python, dan Celery mendistribusikannya ke proses pekerja. * **Kelebihan:** Mudah diatur, bagus untuk tugas asinkron, terintegrasi dengan baik dengan kerangka kerja web seperti Django dan Flask. * **Kekurangan:** Manajemen alur kerja kurang canggih dibandingkan Airflow, membutuhkan message broker (misalnya, RabbitMQ, Redis). * **Cocok untuk:** Pemrosesan latar belakang, pemrosesan gambar, mengirim email, menangani operasi yang berjalan lama. * **Luigi:** Sistem manajemen alur kerja berbasis Python lainnya. * **Kelebihan:** Berfokus pada resolusi dependensi dan manajemen saluran data. * **Kekurangan:** Kurang populer dibandingkan Airflow, komunitas lebih kecil. * **Cocok untuk:** Saluran data, pemrosesan batch. * **Prefect:** Platform orkestrasi alur kerja modern. * **Kelebihan:** Lebih ramah pengguna daripada Airflow, bagus untuk alur kerja rekayasa data, mendukung Python. * **Kekurangan:** Lebih baru dari Airflow, komunitas lebih kecil. * **Cocok untuk:** Saluran data, proses ETL, alur kerja pembelajaran mesin. **2. Penjadwal Tugas Sistem Operasi (Lebih Sederhana, tetapi Terbatas):** * **Cron (Linux/Unix):** Utilitas Unix standar untuk menjadwalkan tugas untuk dijalankan pada waktu tertentu. * **Kelebihan:** Mudah digunakan untuk penjadwalan dasar, tersedia secara luas. * **Kekurangan:** Terbatas dalam hal manajemen dependensi, penanganan kesalahan, dan pemantauan. Tidak cocok untuk alur kerja kompleks. * **Cocok untuk:** Tugas sederhana dan berulang seperti pencadangan, rotasi log, atau menjalankan skrip secara berkala. * **Task Scheduler (Windows):** Setara Windows dengan Cron. * **Kelebihan:** Terpasang di Windows, mudah digunakan untuk penjadwalan dasar. * **Kekurangan:** Keterbatasan serupa dengan Cron. * **Cocok untuk:** Tugas sederhana pada sistem Windows. **3. Solusi Kustom (Jika Anda Memiliki Kebutuhan yang Sangat Spesifik):** * Anda dapat membuat penjadwal tugas sendiri menggunakan bahasa pemrograman seperti Python, Java, atau Go, dan database untuk menyimpan informasi tugas. * **Kelebihan:** Kontrol penuh atas implementasi, disesuaikan dengan kebutuhan Anda yang tepat. * **Kekurangan:** Upaya pengembangan yang signifikan, membutuhkan keahlian dalam algoritma penjadwalan, konkurensi, dan penanganan kesalahan. Umumnya tidak direkomendasikan kecuali Anda memiliki kebutuhan yang sangat tidak biasa. **Memilih Opsi yang Tepat:** Untuk memilih opsi terbaik, pertimbangkan faktor-faktor ini: * **Kompleksitas tugas Anda:** Tugas sederhana dapat ditangani oleh Cron atau Task Scheduler. Alur kerja kompleks membutuhkan sistem penjadwalan tugas khusus seperti Airflow, Celery, Luigi, atau Prefect. * **Skalabilitas:** Jika Anda perlu menangani sejumlah besar tugas atau menskalakan sistem Anda, Airflow, Celery, atau Prefect adalah pilihan yang baik. * **Bahasa pemrograman:** Airflow, Celery, Luigi, dan Prefect sebagian besar berbasis Python. * **Integrasi dengan sistem lain:** Pertimbangkan seberapa baik penjadwal tugas terintegrasi dengan infrastruktur dan alat yang ada. * **Kurva pembelajaran:** Airflow memiliki kurva pembelajaran yang lebih curam daripada Cron atau Celery. * **Pemeliharaan:** Pertimbangkan persyaratan pemeliharaan dan dukungan berkelanjutan dari setiap opsi. **Singkatnya, untuk sebagian besar kasus penggunaan, Apache Airflow, Celery, atau Prefect adalah pilihan terbaik untuk server MCP yang menjadwalkan dan mengelola tugas. Cron atau Task Scheduler cocok untuk tugas yang sangat sederhana.**

Bitbucket

Bitbucket Cloud MCP in Go: complete API auto-generated from spec, customizable prompts.

SmartBear MCP server

Enables AI assistants to interact with SmartBear's suite of testing and monitoring tools including BugSnag, Swagger, Reflect, and more through natural language, allowing querying of testing data, analysis of performance metrics, and management of test automation.

MES Document MCP

Enables AI agents to safely ingest, inspect, edit, and export manufacturing documents (Excel, PDF, Word, Markdown) with controlled patch workflows and MES entity extraction.

CodeMax

Cross-stack MCP server that scans frontend and backend code together, detects mismatches like phantom calls, dead endpoints, and field drift, and provides a full-stack health audit.

Weather & Prayer Times MCP Server

Enables users to get weather information and Islamic prayer (Namaz) times, along with motivational prompts and random quotes. Integrates with OpenWeatherMap and Aladhan APIs to provide location-based weather data and prayer schedules.

trollspace-mcp

MCP server for the Trollspace API that exposes 47 type-safe tools for managing snippets, nuggets, todos, ideas, tools, repos, travel, subscriptions, and more.

arch-viewer

Provides AI-powered architecture analysis and visualization of codebases, exposing 17 MCP tools for querying components, dependencies, and generating interactive diagrams.

PubMed MCP Server

Enables searching PubMed's biomedical literature database and retrieving article metadata, abstracts, and full content through the E-utilities API. Supports advanced queries, batch operations, and multiple output formats with automatic rate limiting.

Gmail MCP Server

Server Protokol Konteks Model yang memungkinkan asisten AI untuk berinteraksi dengan layanan Gmail, mendukung operasi email, manajemen draf, dan fungsionalitas kalender melalui integrasi Google API.

Quolle MCP

Enables AI agents to send transactional emails through Quolle, including sending, batching, canceling, and checking delivery status of emails.

x402-test-mcp

An MCP server that tests agent payment capabilities by making a real x402 payment ($10 USDC on Base) and returning a signed diagnostic report covering the entire payment flow.

metabase-mcp-navi

A MCP server for Metabase that gives AI assistants direct access to dashboards, cards, and query execution.

Git Commit Message Generator MCP Server

An intelligent MCP server that automatically generates Conventional Commits style commit messages by analyzing git diffs using LLM providers like DeepSeek and Groq. It enables developers to maintain standardized version history through natural language interactions in supported MCP clients.

MCP Server

A server implementation of the Model Context Protocol that allows users to extend Claude's capabilities by creating custom tools that can be used within the Claude Desktop client.

Teleprompter

Enables storage and reuse of prompt templates with variable substitution for LLMs. Supports creating, searching, and retrieving prompt templates to avoid repeating complex instructions across conversations.

OpenProject MCP

An MCP server that lets local AI agents read and manage OpenProject project data through structured, guarded tools, with write operations requiring explicit confirmation.

MCP Server Deployment Demo

A demonstration MCP server that provides a simple addition tool for learning how to create and deploy servers following the Model-Context-Protocol specification. Serves as a basic example for developers getting started with MCP server development.

XcodeBazelMCP

A comprehensive MCP server and CLI for Bazel-based Apple platform development, providing 112 tools across 19 workflow categories for building, testing, debugging, and managing iOS, macOS, tvOS, watchOS, visionOS, and Swift Package Manager projects.