Discover Awesome MCP Servers

Google Sheets MCP Server by CData

Google Sheets MCP Server by CData

Sales Tools MCP Server

Provides a suite of business tools for interacting with a SQLite sales database, including SQL query execution, KPI calculations, and report generation. It enables AI agents to analyze sales data across customers, products, and orders using the Model Context Protocol.

Fetch MCP Server

Enables fetching and converting web content into various formats including HTML, JSON, plain text, and Markdown. It supports custom request headers and provides specialized tools for on-demand web data retrieval and transformation.

Propstack MCP

Connect AI assistants (Claude, ChatGPT) to Propstack real estate CRM via MCP

foglift-mcp

MCP server for website SEO + GEO analysis. Scan any URL to get scores across 5 categories (SEO, GEO, Performance, Security, Accessibility) with actionable fix recommendations. Enables AI coding assistants to audit websites and implement fixes autonomously.

Context Optimizer MCP

Sebuah server MCP yang menggunakan Redis dan penyimpanan cache dalam memori untuk mengoptimalkan dan memperluas jendela konteks untuk riwayat obrolan yang besar.

My MCP Server

A customizable Model Context Protocol server built with mcp-framework that enables Claude to access external tools and capabilities through a standardized interface.

aica - AI Code Analyzer

aica (AI Code Analyzer) meninjau kode Anda menggunakan AI. Mendukung CLI dan GitHub Actions.

Vercel MCP Template

A template for deploying MCP servers on Vercel with example tools for rolling dice and fetching weather data. Provides a starting point for building custom MCP servers with TypeScript.

example-mcp-server

Okay, I will provide you with an example code structure for an Anthropic MCP (Model Control Plane) server. Keep in mind that this is a *conceptual* example and would need significant fleshing out to be production-ready. It focuses on the core ideas of receiving requests, interacting with Anthropic's API, and managing model access. **Important Considerations:** * **Security:** This example omits crucial security measures like authentication, authorization, and input validation. A real-world MCP *must* prioritize security. * **Error Handling:** Error handling is simplified for clarity. Robust error handling, logging, and monitoring are essential in production. * **Rate Limiting:** Anthropic's API has rate limits. Your MCP needs to implement rate limiting to avoid being throttled. * **Scalability:** This is a basic example. For high-volume usage, you'd need to consider scaling strategies (e.g., load balancing, caching). * **Configuration:** API keys, model settings, and other parameters should be configurable (e.g., using environment variables or a configuration file). * **Asynchronous Operations:** For better performance, especially with potentially long-running model requests, consider using asynchronous operations (e.g., `asyncio` in Python). * **Anthropic API Client:** This example assumes you're using the official Anthropic Python client library (`anthropic`). Install it with `pip install anthropic`. **Python Example (using Flask):** ```python from flask import Flask, request, jsonify import anthropic import os app = Flask(__name__) # Replace with your actual Anthropic API key (ideally, load from environment variable) ANTHROPIC_API_KEY = os.environ.get("ANTHROPIC_API_KEY") if not ANTHROPIC_API_KEY: raise ValueError("Anthropic API key not found in environment variables.") client = anthropic.Anthropic(api_key=ANTHROPIC_API_KEY) @app.route('/generate', methods=['POST']) def generate_text(): """ Endpoint to generate text using Anthropic's models. Expects a JSON payload with 'prompt' and optional 'model' parameters. """ try: data = request.get_json() prompt = data.get('prompt') model = data.get('model', "claude-v1.3") # Default model if not prompt: return jsonify({'error': 'Prompt is required'}), 400 # Call Anthropic API try: response = client.completions.create( model=model, prompt=f"{anthropic.HUMAN_PROMPT} {prompt}{anthropic.AI_PROMPT}", max_tokens_to_sample=200, # Adjust as needed ) generated_text = response.completion return jsonify({'generated_text': generated_text}) except anthropic.APIError as e: print(f"Anthropic API Error: {e}") return jsonify({'error': f'Anthropic API Error: {e}'}), 500 # Or a more specific error code except Exception as e: print(f"Error processing request: {e}") return jsonify({'error': f'Internal Server Error: {e}'}), 500 if __name__ == '__main__': app.run(debug=True, host='0.0.0.0', port=5000) ``` **Explanation:** 1. **Imports:** Imports necessary libraries (Flask for the web server, `anthropic` for the Anthropic API client, and `os` for environment variables). 2. **API Key:** Retrieves the Anthropic API key from an environment variable. *Never* hardcode API keys directly in your code. 3. **Flask App:** Creates a Flask web application. 4. **`/generate` Endpoint:** * Handles `POST` requests to the `/generate` endpoint. * **Request Parsing:** Extracts the `prompt` and optional `model` from the JSON request body. * **Input Validation:** Checks if the `prompt` is provided. * **Anthropic API Call:** * Uses the `anthropic.Anthropic` client to call the `completions.create` method. * **Prompt Formatting:** Crucially, it formats the prompt using `anthropic.HUMAN_PROMPT` and `anthropic.AI_PROMPT`. This is *essential* for Anthropic's models to understand the context. * Sets `max_tokens_to_sample` to limit the length of the generated text. Adjust this value based on your needs. * **Response:** Returns the generated text in a JSON response. * **Error Handling:** Includes basic `try...except` blocks to catch potential errors (e.g., API errors, JSON parsing errors). 5. **Running the App:** Starts the Flask development server. **How to Run:** 1. **Install Dependencies:** ```bash pip install flask anthropic ``` 2. **Set API Key:** ```bash export ANTHROPIC_API_KEY="YOUR_ANTHROPIC_API_KEY" ``` (Replace `"YOUR_ANTHROPIC_API_KEY"` with your actual API key.) 3. **Run the Script:** ```bash python your_script_name.py ``` 4. **Send a Request:** Use `curl`, `Postman`, or a similar tool to send a `POST` request to `http://localhost:5000/generate` with a JSON payload like this: ```json { "prompt": "Write a short story about a cat who goes on an adventure." } ``` **Indonesian Translation of Explanation:** Oke, saya akan memberikan contoh struktur kode untuk server Anthropic MCP (Model Control Plane). Perlu diingat bahwa ini adalah contoh *konseptual* dan perlu pengembangan lebih lanjut agar siap untuk produksi. Ini berfokus pada ide-ide inti menerima permintaan, berinteraksi dengan API Anthropic, dan mengelola akses model. **Pertimbangan Penting:** * **Keamanan:** Contoh ini menghilangkan langkah-langkah keamanan penting seperti otentikasi, otorisasi, dan validasi input. MCP dunia nyata *harus* memprioritaskan keamanan. * **Penanganan Kesalahan:** Penanganan kesalahan disederhanakan untuk kejelasan. Penanganan kesalahan, pencatatan log, dan pemantauan yang kuat sangat penting dalam produksi. * **Pembatasan Tingkat (Rate Limiting):** API Anthropic memiliki batasan tingkat. MCP Anda perlu menerapkan pembatasan tingkat untuk menghindari pembatasan. * **Skalabilitas:** Ini adalah contoh dasar. Untuk penggunaan volume tinggi, Anda perlu mempertimbangkan strategi penskalaan (misalnya, penyeimbangan beban, caching). * **Konfigurasi:** Kunci API, pengaturan model, dan parameter lainnya harus dapat dikonfigurasi (misalnya, menggunakan variabel lingkungan atau file konfigurasi). * **Operasi Asinkron:** Untuk kinerja yang lebih baik, terutama dengan permintaan model yang berpotensi berjalan lama, pertimbangkan untuk menggunakan operasi asinkron (misalnya, `asyncio` di Python). * **Klien API Anthropic:** Contoh ini mengasumsikan Anda menggunakan pustaka klien Python Anthropic resmi (`anthropic`). Instal dengan `pip install anthropic`. **Contoh Python (menggunakan Flask):** ```python from flask import Flask, request, jsonify import anthropic import os app = Flask(__name__) # Ganti dengan kunci API Anthropic Anda yang sebenarnya (idealnya, muat dari variabel lingkungan) ANTHROPIC_API_KEY = os.environ.get("ANTHROPIC_API_KEY") if not ANTHROPIC_API_KEY: raise ValueError("Kunci API Anthropic tidak ditemukan di variabel lingkungan.") client = anthropic.Anthropic(api_key=ANTHROPIC_API_KEY) @app.route('/generate', methods=['POST']) def generate_text(): """ Endpoint untuk menghasilkan teks menggunakan model Anthropic. Mengharapkan payload JSON dengan parameter 'prompt' dan opsional 'model'. """ try: data = request.get_json() prompt = data.get('prompt') model = data.get('model', "claude-v1.3") # Model default if not prompt: return jsonify({'error': 'Prompt diperlukan'}), 400 # Panggil API Anthropic try: response = client.completions.create( model=model, prompt=f"{anthropic.HUMAN_PROMPT} {prompt}{anthropic.AI_PROMPT}", max_tokens_to_sample=200, # Sesuaikan sesuai kebutuhan ) generated_text = response.completion return jsonify({'generated_text': generated_text}) except anthropic.APIError as e: print(f"Kesalahan API Anthropic: {e}") return jsonify({'error': f'Kesalahan API Anthropic: {e}'}), 500 # Atau kode kesalahan yang lebih spesifik except Exception as e: print(f"Kesalahan memproses permintaan: {e}") return jsonify({'error': f'Kesalahan Server Internal: {e}'}), 500 if __name__ == '__main__': app.run(debug=True, host='0.0.0.0', port=5000) ``` **Penjelasan:** 1. **Impor:** Mengimpor pustaka yang diperlukan (Flask untuk server web, `anthropic` untuk klien API Anthropic, dan `os` untuk variabel lingkungan). 2. **Kunci API:** Mengambil kunci API Anthropic dari variabel lingkungan. *Jangan pernah* menyimpan kunci API secara langsung dalam kode Anda. 3. **Aplikasi Flask:** Membuat aplikasi web Flask. 4. **Endpoint `/generate`:** * Menangani permintaan `POST` ke endpoint `/generate`. * **Penguraian Permintaan:** Mengekstrak `prompt` dan `model` opsional dari badan permintaan JSON. * **Validasi Input:** Memeriksa apakah `prompt` disediakan. * **Panggilan API Anthropic:** * Menggunakan klien `anthropic.Anthropic` untuk memanggil metode `completions.create`. * **Pemformatan Prompt:** Yang terpenting, ia memformat prompt menggunakan `anthropic.HUMAN_PROMPT` dan `anthropic.AI_PROMPT`. Ini *penting* agar model Anthropic memahami konteksnya. * Menetapkan `max_tokens_to_sample` untuk membatasi panjang teks yang dihasilkan. Sesuaikan nilai ini berdasarkan kebutuhan Anda. * **Respons:** Mengembalikan teks yang dihasilkan dalam respons JSON. * **Penanganan Kesalahan:** Menyertakan blok `try...except` dasar untuk menangkap potensi kesalahan (misalnya, kesalahan API, kesalahan penguraian JSON). 5. **Menjalankan Aplikasi:** Memulai server pengembangan Flask. **Cara Menjalankan:** 1. **Instal Dependensi:** ```bash pip install flask anthropic ``` 2. **Setel Kunci API:** ```bash export ANTHROPIC_API_KEY="KUNCI_API_ANTHROPIC_ANDA" ``` (Ganti `"KUNCI_API_ANTHROPIC_ANDA"` dengan kunci API Anda yang sebenarnya.) 3. **Jalankan Skrip:** ```bash python nama_skrip_anda.py ``` 4. **Kirim Permintaan:** Gunakan `curl`, `Postman`, atau alat serupa untuk mengirim permintaan `POST` ke `http://localhost:5000/generate` dengan payload JSON seperti ini: ```json { "prompt": "Tulis cerita pendek tentang seekor kucing yang melakukan petualangan." } ``` This provides a basic, functional example. Remember to adapt and expand upon it to meet the specific requirements of your application and to incorporate best practices for security, error handling, and scalability. Good luck!

kmux

A terminal emulator MCP server specifically engineered for LLMs with block-oriented design that organizes command input/output into recognizable blocks and semantic session management. Enables AI to efficiently use terminals for writing code, installing software, and executing commands without context overflow.

Prompt Registry MCP

A lightweight, file-based server for managing and serving personal prompt templates with variable substitution support via the Model Context Protocol. It allows users to store, update, and organize prompts in a local directory through integrated MCP tools and CLI assistants.

kospell

한글 MCP (글자 수 세기, 맞춤법 오류, 로만화) Korean lang mcp

ShowDoc MCP Server

Automatically fetches API documentation from ShowDoc and generates Android code including Entity classes, Repository patterns, and Retrofit interfaces.

Weather Query MCP Server

Implementasi server MCP yang memungkinkan pengguna untuk mengambil dan menampilkan informasi cuaca untuk kota-kota tertentu, termasuk suhu, kelembapan, kecepatan angin, dan deskripsi cuaca.

MCP Server Boilerplate

A starter template for building custom MCP servers that can integrate with Claude Desktop, Cursor, and other AI assistants. Provides example tools, TypeScript support, and automated publishing workflows to help developers quickly create their own MCP integrations.

MCP System Monitor Server

Enables real-time monitoring of system resources including CPU, GPU (NVIDIA, Apple Silicon, AMD/Intel), memory, disk, network, and processes across Windows, macOS, and Linux platforms through natural language queries.

Perplexity Comet MCP

Bridges Claude with Perplexity's Comet browser for autonomous web browsing, research, and multi-tab workflow management. Supports dynamic content interaction, login wall handling, file uploads, and intelligent completion detection across Windows, macOS, and WSL platforms.

MCP SSH Tools Server

A server based on the MCP framework that provides remote server management capabilities through SSH, supporting features like connection pooling, file transfers, and remote command execution.

Jamb MCP Server

Jamb MCP Server

GDB-MCP

An MCP server that provides programmatic access to the GNU Debugger (GDB), enabling AI models to interact with GDB through natural language for debugging tasks.

Jina AI Remote MCP Server

Provides access to Jina AI's Reader, Embeddings, and Reranker APIs with tools for web scraping, web/image/academic search, content extraction, screenshot capture, document reranking, and semantic deduplication.

Email Social Media Checker

Enables checking email addresses through the Email Social Media Checker API to verify and validate email information.

Trade It

Trade Agent

Outscraper MCP Server

Provides access to Outscraper's data extraction services for business intelligence, location data, and reviews across platforms like Google Maps, Amazon, and Yelp. It enables AI assistants to perform comprehensive web scraping tasks including contact information retrieval and geolocation services.

GetMailer MCP Server

Enables sending transactional emails through GetMailer from AI assistants. Supports email operations, template management, domain verification, analytics, suppression lists, and batch email jobs.

Replicate Imagen 4 MCP Server

Enables high-quality image generation using Google's Imagen 4 Ultra model through Replicate, with automatic local download and organized file management. Supports multiple aspect ratios, output formats, and configurable safety filtering.

AstroInsight Research Assistant

Enables AI-powered academic research workflow from keyword search to hypothesis generation. Integrates multiple AI models to automatically search ArXiv papers, extract key information, and generate innovative research hypotheses for researchers.

gitlab-mcp

Full-coverage GitLab MCP server with 44 tools across 18 resource types. Agent-optimized CQRS design — one tool call handles complete multi-step operations. Supports OAuth 2.1, read-only mode, stdio/SSE/StreamableHTTP transports, and GraphQL-native work items with full hierarchy (epics,issues,etc)