Discover Awesome MCP Servers

Webpage MCP Server

Enables querying and retrieving webpage content from websites by parsing sitemap.xml files and fetching HTML content. Includes rate limiting protection and supports listing available pages and accessing raw sitemap data.

Kluster.ai Verify MCP

Enables fact-checking of AI responses against reliable sources and validation of responses against document content to ensure accuracy and reliability.

VTEX Headless CMS MCP Server

An MCP Server that enables interaction with VTEX's Headless Content Management System API, allowing users to manage content through natural language commands.

Maton MCP Server

Berinteraksilah dengan alat SaaS Anda termasuk HubSpot, Salesforce, dan lainnya

Gmail MCP Server

Enables natural language interaction with Gmail, providing email search, categorized daily summaries, and Home Assistant integration through REST API with read-only access to your inbox.

fal-hidream-i1-full MCP Server

Enables high-quality AI image generation using the fal-ai/hidream-i1-full model with support for synchronous, streaming, and queue-based generation, custom image sizing, LoRA weights, and automatic local image downloads.

Pinme Deploy MCP Server

Enables one-click deployment of static websites and HTML files to IPFS through Pinme. Automatically detects common build directories (build, dist, out, .next), uploads to IPFS, and provides ENS URLs for accessing deployed sites.

telegram-mcp

An MCP server that enables interaction with Telegram to send, read, and search messages across chats and dialogs. It supports waiting for incoming messages and retrieving conversation history through natural language commands.

Kite MCP Server

Enables trading and portfolio management on Zerodha Kite Connect through natural language. Supports placing orders, viewing positions/holdings, accessing real-time market data, and managing GTT orders.

Graphiti MCP

Provides persistent memory and context continuity for AI agents using Zep's Graphiti and Neo4j graph database. Enables storing, retrieving, and linking memories to build a knowledge graph accessible across Cursor and Claude.

WinsecMCP

Windows Hardening MCP Server

Create your first own server

Oke, ini adalah kode server MCP sederhana untuk menghitung karakter "r" dalam pesan yang diterima: ```python from mcp import Client, Server class RCounter: def __init__(self): self.count = 0 def handle_message(self, message): """Menghitung karakter 'r' dalam pesan.""" self.count += message.lower().count('r') return f"Jumlah 'r' saat ini: {self.count}" def reset_count(self): """Mereset hitungan 'r'.""" self.count = 0 return "Hitungan 'r' direset." # Inisialisasi penghitung rcounter = RCounter() # Definisikan handler untuk perintah handlers = { "count": rcounter.handle_message, "reset": rcounter.reset_count } # Buat server server = Server(handlers) # Jalankan server server.run() ``` **Penjelasan:** 1. **`RCounter` Class:** * `__init__`: Menginisialisasi hitungan `self.count` menjadi 0. * `handle_message(message)`: * Menerima pesan sebagai input. * Mengubah pesan menjadi huruf kecil menggunakan `message.lower()`. * Menghitung jumlah karakter 'r' dalam pesan menggunakan `count('r')`. * Menambahkan jumlah tersebut ke `self.count`. * Mengembalikan string yang menunjukkan jumlah 'r' saat ini. * `reset_count()`: * Mereset `self.count` menjadi 0. * Mengembalikan pesan konfirmasi. 2. **`handlers` Dictionary:** * Memetakan perintah (string) ke fungsi handler yang sesuai. * `"count"`: Memetakan ke `rcounter.handle_message` (untuk menghitung 'r'). * `"reset"`: Memetakan ke `rcounter.reset_count` (untuk mereset hitungan). 3. **`Server` dan `server.run()`:** * Membuat instance dari kelas `Server` MCP, memberikan dictionary `handlers` sebagai argumen. * `server.run()` memulai server dan membuatnya mendengarkan koneksi. **Cara Menggunakan:** 1. **Instal MCP:** Pastikan Anda telah menginstal library `mcp`. Anda dapat menginstalnya menggunakan pip: ```bash pip install mcp ``` 2. **Jalankan Server:** Simpan kode di atas sebagai file Python (misalnya, `r_counter_server.py`) dan jalankan dari terminal: ```bash python r_counter_server.py ``` 3. **Kirim Pesan dari Klien MCP:** Gunakan klien MCP untuk terhubung ke server dan mengirim pesan. Contoh: ```python from mcp import Client client = Client() response = client.send("count", "Hello there, how are you?") print(response) # Output: Jumlah 'r' saat ini: 3 response = client.send("count", "Another message with more r's: rrrrr") print(response) # Output: Jumlah 'r' saat ini: 8 response = client.send("reset", "") print(response) # Output: Hitungan 'r' direset. response = client.send("count", "First message after reset") print(response) # Output: Jumlah 'r' saat ini: 1 ``` **Penting:** * **Error Handling:** Kode ini tidak memiliki penanganan kesalahan yang komprehensif. Dalam aplikasi produksi, Anda harus menambahkan penanganan kesalahan untuk menangani koneksi yang gagal, pesan yang tidak valid, dan masalah lainnya. * **Keamanan:** Kode ini tidak memiliki fitur keamanan. Jika Anda menggunakan ini dalam lingkungan yang tidak tepercaya, Anda harus menambahkan otentikasi dan otorisasi. * **MCP:** Pastikan Anda memahami cara kerja library MCP. Dokumentasi MCP akan sangat membantu. Kode ini memberikan dasar yang sederhana. Anda dapat memperluasnya dengan menambahkan lebih banyak perintah, fitur, dan penanganan kesalahan.

CBCI MCP

Enables dynamic database querying through natural language questions using LLM-powered parameter extraction and template-based SQL generation. Supports flexible configuration for various domains and databases with automated response formatting.

Gemini MCP Server

Integrates Google Gemini API capabilities into Claude Code, supporting text generation, image analysis, and AI image creation. It features specialized tools for creative brainstorming and managing multi-turn chat sessions.

hyperliquid-whalealert-mcp

hyperliquid-whalealert-mcp

DataForSEO MCP Server

Enables AI assistants to interact with DataForSEO APIs and obtain SEO data including SERP results, keyword research, on-page metrics, backlink analysis, and domain analytics through a standardized interface.

MCP Keyword Search

Enables keyword searching within text files with configurable case sensitivity, returning matching lines with line numbers and occurrence counts.

Software Planning Tool

Facilitates software development planning through interactive sessions that break down projects into manageable tasks with complexity scoring, code examples, and implementation plan management.

MCP Server: ComfyUI Selfie

As a large language model, I am unable to generate images, including selfies. I can only process and generate text.

Heimdall

Heimdall adalah layanan ringan untuk mengelola Server MCP lokal dan dapat diinstal dengan satu perintah npx. Alat server MCP tertentu dapat diotorisasi untuk klien MCP Anda, dan konfigurasi yang sama dapat diakses oleh semua klien MCP di perangkat Anda.

PostHog MCP Server

A server that allows users to interact with PostHog analytics platform through Claude Desktop, enabling listing projects, creating annotations, searching insights, and accessing documentation.

faster-whisper-mcp

Enables high-quality transcription and subtitle generation from local media files or URLs using Faster Whisper on local hardware. It supports automatic language detection and integration with MCP clients for seamless speech-to-text workflows.

AnkiMCP Server

Exposes Anki flashcard collections to AI assistants via MCP, enabling AI-powered study sessions, card creation, deck management, and review workflows. Supports comprehensive collection operations including search, media management, and note type customization.

mcp-for-docs

Automatically crawls documentation websites, converts them to organized markdown files, and generates condensed cheat sheets. Intelligently categorizes content into tools/APIs and provides local-first access to downloaded documentation.

Qdrant MCP Server

Terjemahan: Server MCP sederhana untuk mengakses Qdrant

Philips Hue MCP Server

Sebuah antarmuka Protokol Konteks Model yang memungkinkan asisten AI seperti Claude untuk mengendalikan sistem pencahayaan pintar Philips Hue melalui perintah bahasa alami.

MATLAB MCP Server

Memungkinkan eksekusi kode MATLAB dari Python menggunakan MATLAB Engine API, memungkinkan sesi MATLAB bersama di beberapa permintaan untuk integrasi tanpa hambatan dengan Claude Desktop.

NetBrain MCP

An open-source network operations integration platform that connects large language models with network devices through the Model Context Protocol, allowing AI assistants to perform network configuration, diagnostics, and management tasks.