Discover Awesome MCP Servers

Bilibili MCP (Playwright)

An MCP server that utilizes Playwright to automate Bilibili video uploads, including automated metadata entry for titles, tags, and descriptions. It features QR code login and cookie persistence to enable seamless interaction with the Bilibili creator platform.

MCP Technopark Job Search

Enables AI assistants to search and retrieve real-time job listings from the Technopark job portal using Puppeteer web scraping. Users can search by role or keyword to obtain job details including company name, closing date, and posted date.

Recursive Thinking MCP Server

Enables AI agents to achieve production-ready solutions through iterative refinement and recursive thinking processes. It features token optimization via context compression and session-based tracking to improve problem-solving depth while minimizing cost.

Doctah-MCP

Enables AI assistants to search and access Arknights game data including operator information, enemy intelligence, skills, talents, and attributes through PRTS.wiki integration. Provides fuzzy search functionality for operators and enemies with clean Markdown output.

fakturka-api-mcp

Free Polish VAT invoice generation MCP server with PDF output and preview. No API key required.

Nanonets MCP Server

Converts images, PDFs, Word documents, and Excel spreadsheets to structured markdown using Nanonets OCR, with support for tables, LaTeX equations, and complex layouts.

Fastmail MCP Server

Enables AI models to interact with Fastmail accounts via the JMAP API through the Model Context Protocol. It supports managing emails, accessing usage analytics, and performing account operations using secure token-based authentication.

Brex MCP Server

Enables AI agents to interact with the Brex financial platform, allowing access to account information, transactions, expenses, receipts, budgets, and spend limits through the Brex API.

Databricks MCP Server

A FastAPI-based server that provides tools for local file management and Databricks operations, enabling users to create/edit files locally and interact with Databricks clusters, jobs, and DLT pipelines.

Hammerspace Storage Management MCP Server

Enables natural language management of Hammerspace storage clusters with automated file ingestion, tagging, tier management, and vector embedding generation. Supports real-time file monitoring, multi-format document processing, and Kubernetes-based ingestion workflows with Milvus integration.

Time-Zone

A comprehensive MCP server that provides global time zone management and time conversion functions, suitable for global business coordination, travel planning, and development and operation.

Exa MCP Server

Connects AI assistants to Exa AI's search capabilities, enabling web search, company research, URL crawling, LinkedIn search, and specialized code search across GitHub repos, documentation, and Stack Overflow for finding relevant coding context and examples.

bitbank-mcp-server

Integrates bitbank's cryptocurrency market data with Claude to provide advanced technical analysis, pattern detection, and SVG chart generation. It enables users to perform complex market evaluations using real-time pricing, volatility metrics, and flow analysis through natural language interactions.

USASpending MCP Server

Enables research of federal contract awards, market opportunities, and competitive landscapes using the USASpending.gov API. It provides specialized tools for AI agents to analyze government spending trends, identify incumbents, and search contractor details.

Markdown Sidecar MCP Server

Provides access to markdown documentation for local NPM, Go, and PyPi packages as MCP resources or tools. It enables informed code generation by surfacing documentation directly from a project's working directory.

自动发文 MCP Server

Layanan penerbitan otomatis MCP

Azure AI Search Integration

Server Protokol Konteks Model untuk Azure AI Search

Artificial Analysis MCP Server

Provides access to real-time LLM pricing, speed metrics, and performance benchmarks for over 300 models from Artificial Analysis. It enables users to list, filter, and compare models based on costs, tokens per second, and intelligence indices.

Weather Forecast MCP Server

Provides weather forecast data for any location using the Open-Meteo API, returning temperature, precipitation, cloud cover, humidity, and wind speed for specified date ranges.

MCP Node Server

Berikut adalah server Node.js dasar untuk MCP (Minecraft Protocol): ```javascript const net = require('net'); const server = net.createServer((socket) => { console.log('Klien terhubung:', socket.remoteAddress, socket.remotePort); // Tangani data yang diterima dari klien socket.on('data', (data) => { console.log('Data diterima:', data); // Di sini Anda akan memproses data MCP // Ini mungkin melibatkan parsing paket, memvalidasi data, // dan merespons dengan paket yang sesuai. // Contoh: Kirim pesan kembali ke klien socket.write('Server menerima data Anda!\n'); }); // Tangani koneksi yang terputus socket.on('end', () => { console.log('Klien terputus:', socket.remoteAddress, socket.remotePort); }); // Tangani kesalahan socket.on('error', (err) => { console.error('Kesalahan koneksi:', err); }); }); const port = 25565; // Port default untuk Minecraft server.listen(port, () => { console.log('Server mendengarkan di port', port); }); ``` **Penjelasan:** * **`const net = require('net');`**: Mengimpor modul `net` bawaan Node.js, yang menyediakan fungsionalitas untuk membuat server TCP. * **`const server = net.createServer((socket) => { ... });`**: Membuat server TCP. Fungsi yang diteruskan ke `createServer` dipanggil setiap kali klien baru terhubung. Objek `socket` mewakili koneksi antara server dan klien. * **`console.log('Klien terhubung:', socket.remoteAddress, socket.remotePort);`**: Mencetak informasi tentang klien yang terhubung (alamat IP dan port). * **`socket.on('data', (data) => { ... });`**: Menangani data yang diterima dari klien. `data` adalah objek Buffer yang berisi data yang diterima. **Bagian ini adalah tempat Anda akan mengimplementasikan logika MCP yang sebenarnya.** Anda perlu mengurai data ini sesuai dengan spesifikasi protokol Minecraft. * **`socket.write('Server menerima data Anda!\n');`**: Mengirim pesan kembali ke klien. Ini hanyalah contoh; Anda akan menggantinya dengan respons MCP yang sesuai. * **`socket.on('end', () => { ... });`**: Menangani saat klien memutuskan koneksi. * **`socket.on('error', (err) => { ... });`**: Menangani kesalahan koneksi. * **`const port = 25565;`**: Menentukan port yang akan didengarkan server. 25565 adalah port default untuk server Minecraft. * **`server.listen(port, () => { ... });`**: Memulai server dan mulai mendengarkan koneksi masuk pada port yang ditentukan. **Cara menjalankan kode ini:** 1. **Simpan kode:** Simpan kode di atas sebagai file, misalnya `mcp_server.js`. 2. **Instal Node.js:** Pastikan Anda telah menginstal Node.js di sistem Anda. Anda dapat mengunduhnya dari [https://nodejs.org/](https://nodejs.org/). 3. **Buka terminal/command prompt:** Buka terminal atau command prompt di direktori tempat Anda menyimpan file `mcp_server.js`. 4. **Jalankan server:** Jalankan perintah `node mcp_server.js`. Server akan mulai berjalan dan mendengarkan koneksi pada port 25565. **Penting:** * **Ini hanyalah server dasar.** Ini tidak mengimplementasikan protokol Minecraft yang lengkap. Anda perlu menambahkan logika untuk mengurai paket MCP, memvalidasi data, dan merespons dengan paket yang sesuai. * **Spesifikasi Protokol Minecraft:** Anda perlu mempelajari spesifikasi protokol Minecraft untuk memahami cara mengurai dan membuat paket MCP. Anda dapat menemukan informasi tentang protokol di [https://wiki.vg/Protocol](https://wiki.vg/Protocol). * **Pustaka:** Pertimbangkan untuk menggunakan pustaka Node.js yang ada untuk membantu Anda mengurai dan membuat paket MCP. Beberapa pustaka populer termasuk `minecraft-protocol` dan `prismarine-protocol`. **Langkah selanjutnya:** 1. **Pelajari Protokol Minecraft:** Pahami struktur paket dan alur komunikasi. 2. **Implementasikan Parsing Paket:** Tulis kode untuk mengurai data yang diterima dari klien menjadi objek yang bermakna. 3. **Implementasikan Penanganan Paket:** Tulis kode untuk menangani berbagai jenis paket MCP (misalnya, handshake, login, obrolan). 4. **Implementasikan Pembuatan Paket:** Tulis kode untuk membuat paket MCP untuk dikirim kembali ke klien. 5. **Uji Server Anda:** Gunakan klien Minecraft atau alat pengujian protokol untuk menguji server Anda. Semoga ini membantu!

MCP Finnhub Server

Provides comprehensive financial market data and news through the Finnhub API. Enables real-time stock quotes, company profiles, financial metrics, analyst recommendations, and market news access.

Slack MCP Server

An MCP server that enables AI agents to search and retrieve messages within a Slack workspace using the Slack Web API. It supports specific channel filtering and includes built-in rate limit handling for efficient message discovery.

Unipile MCP Server

Enables AI models to interact with messages from various messaging platforms (Mobile, Mail, WhatsApp, LinkedIn, Slack, Twitter, Telegram, Instagram, Messenger) through a standardized interface.

MCP JSONDiff Kel

An efficient MCP server for performing accurate, deep comparisons between JSON objects or strings using the deepdiff engine. It provides AI agents with standardized difference reports, supporting nested structures and various input formats to ensure precise data analysis.

Google API Discovery Service MCP Server

An MCP server that provides access to Google's API Discovery Service, allowing agents to discover and interact with Google APIs through natural language commands.

Apple Health MCP

Enables users to query Apple Health metrics, workouts, and trends from CSV files exported via the Health Auto Export app. It allows MCP clients to analyze health data such as heart rate, sleep stages, and activity levels directly from local iCloud Drive storage.

Debug-MCP

Enables AI assistants to perform interactive Python debugging with breakpoints, step execution, and variable inspection using the Debug Adapter Protocol (DAP) through an MCP server interface.

Gmail MCP Server

Enables AI assistants to read, search, organize, and draft emails in Gmail inboxes with support for multiple accounts, OAuth authentication, and 26 comprehensive tools for email management.

ChunkHound

A local-first codebase intelligence tool that enables AI assistants to research codebases using semantic search, multi-hop relationship discovery, and structural parsing. It allows users to extract architectural patterns and institutional knowledge across 30+ programming languages through an MCP-compatible interface.

Market Price Finder

Enables querying and comparing product prices across different marketplaces with real-time updates. Deployable on Cloudflare Workers with tools for searching products, comparing prices, and retrieving price history.