Discover Awesome MCP Servers

Extend your agent with 26,683 capabilities via MCP servers.

All26,683
vmysql-mcp

vmysql-mcp

A lightweight, multi-environment MySQL MCP server that provides secure, policy-gated database access through simplified query and execution tools. It enables AI agents to interact with multiple database environments safely using environment-based routing and strict security constraints.

MCP Oracle Server

MCP Oracle Server

Enables interaction with Oracle databases through MCP by executing SELECT queries, describing table structures, and listing available tables with secure, read-only access.

DataBeak

DataBeak

Provides 40+ specialized tools for AI assistants to load, transform, analyze, and validate CSV data from URLs and string content through the Model Context Protocol.

Cursor MCP Installer

Cursor MCP Installer

Server Protokol Konteks Model (MCP) untuk Cursor IDE yang menyederhanakan instalasi dan konfigurasi server MCP lainnya.

New Relic MCP Server

New Relic MCP Server

Sebuah server Protokol Konteks Model yang memungkinkan Model Bahasa Besar seperti Claude untuk menanyakan log dan metrik New Relic menggunakan kueri NRQL.

Paperlib MCP

Paperlib MCP

Enables academic literature management through PDF import, hybrid search, knowledge graph construction, and automated literature review generation. Combines full-text search with semantic vector search for comprehensive paper analysis.

Bilibili MCP

Bilibili MCP

ComputeGauge MCP

ComputeGauge MCP

Provides cost intelligence and a reputation scoring system to help AI agents optimize spending through smart model selection and local-to-cloud routing. It enables real-time cost tracking and rewards agents for making efficient, high-credibility decisions across various LLM providers.

Google Calendar MCP Server

Google Calendar MCP Server

Enables natural language interaction with Google Calendar via the Model Context Protocol, allowing LLMs like Claude to read and manage calendar events through the Google Calendar v3 API.

FIWARE MCP Server

FIWARE MCP Server

Cermin dari

Local Filesystem MCP Server

Local Filesystem MCP Server

Enables exploration and search of local filesystems using glob pattern matching to find files and grep to search for text patterns within files.

Streamlit LangChain MCP Server GitHub

Streamlit LangChain MCP Server GitHub

Memory-MCP

Memory-MCP

Provides persistent memory for AI agents using hybrid search (vector embeddings + BM25) with neural reranking, enabling storage and retrieval of insights, debugging solutions, and patterns across coding sessions.

Redshift MCP Server

Redshift MCP Server

Enables AI agents to interact with Amazon Redshift databases using natural language to execute queries, explore schemas, and retrieve sample data.

Defense MCP

Defense MCP

Provides Claude Desktop access to Defense.com threat intelligence data for risk assessment, threat analysis, and workload management. It also features interactive security training tools and supports over 200 source type aliases for simplified querying.

Stealth-AntiCheat MCP

Stealth-AntiCheat MCP

Real-time anti-cheat analysis system that monitors Discord servers for cheating code patterns using AI (GPT-4), automatically detects and analyzes suspicious code, and generates custom anti-cheat signatures with 24/7 monitoring capabilities.

mcp-arsr

mcp-arsr

Adaptive Retrieval-Augmented Self-Refinement MCP Server — a closed-loop system that lets LLMs iteratively verify and correct their own claims using uncertainty-guided retrieval.

PostgREST

PostgREST

Ini adalah server MCP untuk PostgREST. Server ini memungkinkan LLM (Model Bahasa Besar) untuk melakukan kueri dan operasi database pada database Postgres melalui PostgREST. Server ini bekerja dengan proyek Supabase (yang menggunakan PostgREST) dan server PostgREST mandiri.

Gemini MCP Server

Gemini MCP Server

A TypeScript implementation of a Model Context Protocol server that integrates with Google's Gemini 2.0 Flash model, enabling Claude Desktop users to interact with Gemini through natural language conversations.

Jina AI Remote MCP Server

Jina AI Remote MCP Server

Provides access to Jina AI's suite of web tools including URL reading, web/image/academic search, content extraction, embeddings, and reranking capabilities. Enables AI assistants to search the web, extract content from URLs, and process information with semantic understanding.

MCP Fetch Page

MCP Fetch Page

Enables browser-based web page fetching with automatic cookie management and CSS selector extraction, supporting JavaScript rendering and authenticated sessions through a Chrome extension.

MCP Logic

MCP Logic

Enables first-order logic reasoning including theorem proving, model finding, counterexample detection, and category theory diagram verification using pure TypeScript with no external dependencies.

AutoCAD MCP Server

AutoCAD MCP Server

Sebuah server yang memungkinkan interaksi bahasa alami dengan AutoCAD melalui model bahasa besar seperti Claude, memungkinkan pengguna untuk membuat dan memodifikasi gambar menggunakan perintah percakapan.

template-mcp-server

template-mcp-server

Okay, here's a PDM template structure you can use as a starting point for developing an MCP (Minecraft Coder Pack) server mod in Python. This template focuses on setting up the project structure, dependencies, and basic build process. Remember that MCP itself is primarily a Java toolchain, so this template focuses on *interfacing* with MCP, likely for tasks like generating patches, managing configuration, or automating certain aspects of the mod development workflow. ``` mcp-server-mod/ ├── pyproject.toml # PDM configuration file ├── pdm.lock # Locked dependencies (generated by PDM) ├── src/ │ └── mcp_server_mod/ # Your Python package │ ├── __init__.py │ ├── main.py # Main script or entry point │ ├── config.py # Configuration handling (optional) │ └── utils.py # Utility functions (optional) ├── scripts/ # Scripts for interacting with MCP │ ├── apply_patches.py # Example: Script to apply MCP patches │ └── build_mod.py # Example: Script to build the mod (e.g., create a JAR) ├── mcp/ # (Optional) Directory for MCP-related files │ ├── conf/ # MCP configuration files (e.g., `mcp.cfg`) │ └── patches/ # Patches generated by MCP (or to be applied) ├── README.md # Project documentation └── .gitignore # Git ignore file ``` **Explanation:** * **`pyproject.toml`:** This is the heart of your PDM project. It defines your project metadata, dependencies, and build system. Here's an example: ```toml [project] name = "mcp-server-mod" version = "0.1.0" description = "A Python-based tool for developing MCP server mods." authors = [ {name = "Your Name", email = "your.email@example.com"} ] dependencies = [ "click", # Example: For command-line interface "requests", # Example: For downloading files # Add other dependencies as needed ] requires-python = ">=3.8" # Specify Python version [build-system] requires = ["pdm-backend"] build-backend = "pdm.backend" [tool.pdm] # Optional: Configure PDM settings here ``` * **`pdm.lock`:** This file is automatically generated by PDM when you install dependencies (`pdm install`). It locks the exact versions of your dependencies to ensure reproducible builds. *Do not edit this file manually.* * **`src/mcp_server_mod/`:** This is where your Python code lives. The `__init__.py` file makes `mcp_server_mod` a Python package. * **`main.py`:** This is the main entry point for your script. You might use it to define a command-line interface (using `click`, for example) or to start a background process. * **`config.py`:** (Optional) Use this to handle configuration settings for your mod development process. You could load settings from a file or environment variables. * **`utils.py`:** (Optional) Put reusable utility functions here. * **`scripts/`:** This directory contains Python scripts that interact with MCP or automate parts of the mod development process. * **`apply_patches.py`:** Example script to apply patches generated by MCP to the Minecraft server code. This would likely involve using Python to read patch files and apply them using a patching library (or by executing command-line tools). * **`build_mod.py`:** Example script to build the final mod JAR file. This might involve compiling Java code (if you have any), packaging resources, and creating the JAR. You might use `subprocess` to call Java commands. * **`mcp/`:** (Optional) This directory can hold MCP-related files, such as configuration files (`mcp.cfg`) and patch files. It's a good place to keep these files organized. You might not need this if you're using MCP in a more automated way. * **`README.md`:** A Markdown file to document your project, including instructions on how to set it up, use it, and contribute to it. * **.gitignore:** Specifies intentionally untracked files that Git should ignore. This should include files like `.venv` (virtual environment), `pdm.lock`, and any build artifacts. **How to Use This Template:** 1. **Install PDM:** If you don't have it already, install PDM: ```bash pip install pdm ``` 2. **Create the Project:** Create the directory structure as shown above. 3. **Initialize PDM:** In the root directory (`mcp-server-mod`), run: ```bash pdm init ``` This will guide you through setting up the `pyproject.toml` file. Answer the questions appropriately. 4. **Install Dependencies:** Edit the `pyproject.toml` file to add your dependencies (e.g., `click`, `requests`). Then, run: ```bash pdm install ``` This will create a virtual environment and install the dependencies. 5. **Write Your Code:** Start writing your Python code in the `src/mcp_server_mod/` directory. Implement the scripts in the `scripts/` directory to interact with MCP and automate your mod development process. 6. **Run Your Scripts:** You can run your scripts using `pdm run`: ```bash pdm run python scripts/apply_patches.py pdm run python scripts/build_mod.py ``` 7. **Version Control:** Initialize a Git repository: ```bash git init ``` Add a `.gitignore` file (see example below) and commit your code. **Example `.gitignore` file:** ``` .venv/ pdm.lock __pycache__/ *.pyc *.log build/ dist/ mcp/patches/ # If you generate patches in the mcp/patches directory ``` **Important Considerations:** * **MCP's Java Nature:** Remember that MCP is primarily a Java toolchain. This template focuses on using Python to *complement* MCP, not to replace it entirely. You'll likely need to use `subprocess` to execute MCP commands from your Python scripts. * **MCP Setup:** You'll need to have MCP set up separately. This template assumes you have MCP installed and configured. * **Patching:** Applying patches is a common task when working with MCP. You'll need to find a suitable patching library for Python or use command-line tools like `patch`. * **Build Process:** The build process for Minecraft mods can be complex. You'll need to understand how to compile Java code, package resources, and create the final JAR file. * **Minecraft Server Version:** Make sure your MCP setup and your mod are compatible with the Minecraft server version you're targeting. * **Modding API (Forge/Fabric):** If you're using a modding API like Forge or Fabric, you'll need to integrate their build processes into your Python scripts. **Example `apply_patches.py` (Illustrative):** ```python import subprocess import os def apply_patches(patch_dir, minecraft_source_dir): """Applies all patches in the given directory to the Minecraft source code.""" for patch_file in os.listdir(patch_dir): if patch_file.endswith(".patch"): patch_path = os.path.join(patch_dir, patch_file) print(f"Applying patch: {patch_path}") # Example using the 'patch' command-line tool try: subprocess.run( ["patch", "-p0", "-i", patch_path], cwd=minecraft_source_dir, # Run patch in the Minecraft source directory check=True, # Raise an exception if the command fails capture_output=True, text=True ) print(f"Patch {patch_file} applied successfully.") except subprocess.CalledProcessError as e: print(f"Error applying patch {patch_file}:") print(e.stderr) raise if __name__ == "__main__": # Example usage: patch_directory = "mcp/patches" # Directory containing your patch files minecraft_source = "src/minecraft_source" # Replace with the actual path to your decompiled Minecraft source code # Ensure the Minecraft source directory exists if not os.path.exists(minecraft_source): print(f"Error: Minecraft source directory not found: {minecraft_source}") exit(1) # Ensure the patch directory exists if not os.path.exists(patch_directory): print(f"Error: Patch directory not found: {patch_directory}") exit(1) try: apply_patches(patch_directory, minecraft_source) print("All patches applied successfully!") except Exception as e: print(f"An error occurred: {e}") ``` **Indonesian Translation of the Explanation:** Berikut adalah struktur template PDM yang dapat Anda gunakan sebagai titik awal untuk mengembangkan mod server MCP (Minecraft Coder Pack) di Python. Template ini berfokus pada pengaturan struktur proyek, dependensi, dan proses build dasar. Ingatlah bahwa MCP itu sendiri adalah toolchain Java, jadi template ini berfokus pada *berinteraksi* dengan MCP, kemungkinan untuk tugas-tugas seperti menghasilkan patch, mengelola konfigurasi, atau mengotomatiskan aspek-aspek tertentu dari alur kerja pengembangan mod. ``` mcp-server-mod/ ├── pyproject.toml # File konfigurasi PDM ├── pdm.lock # Dependensi yang terkunci (dihasilkan oleh PDM) ├── src/ │ └── mcp_server_mod/ # Paket Python Anda │ ├── __init__.py │ ├── main.py # Skrip utama atau titik masuk │ ├── config.py # Penanganan konfigurasi (opsional) │ └── utils.py # Fungsi utilitas (opsional) ├── scripts/ # Skrip untuk berinteraksi dengan MCP │ ├── apply_patches.py # Contoh: Skrip untuk menerapkan patch MCP │ └── build_mod.py # Contoh: Skrip untuk membangun mod (misalnya, membuat JAR) ├── mcp/ # (Opsional) Direktori untuk file terkait MCP │ ├── conf/ # File konfigurasi MCP (misalnya, `mcp.cfg`) │ └── patches/ # Patch yang dihasilkan oleh MCP (atau untuk diterapkan) ├── README.md # Dokumentasi proyek └── .gitignore # File ignore Git ``` **Penjelasan:** * **`pyproject.toml`:** Ini adalah inti dari proyek PDM Anda. Ini mendefinisikan metadata proyek Anda, dependensi, dan sistem build. Berikut adalah contoh: ```toml [project] name = "mcp-server-mod" version = "0.1.0" description = "Alat berbasis Python untuk mengembangkan mod server MCP." authors = [ {name = "Nama Anda", email = "email.anda@example.com"} ] dependencies = [ "click", # Contoh: Untuk antarmuka baris perintah "requests", # Contoh: Untuk mengunduh file # Tambahkan dependensi lain sesuai kebutuhan ] requires-python = ">=3.8" # Tentukan versi Python [build-system] requires = ["pdm-backend"] build-backend = "pdm.backend" [tool.pdm] # Opsional: Konfigurasikan pengaturan PDM di sini ``` * **`pdm.lock`:** File ini secara otomatis dihasilkan oleh PDM ketika Anda menginstal dependensi (`pdm install`). Ini mengunci versi pasti dari dependensi Anda untuk memastikan build yang dapat direproduksi. *Jangan edit file ini secara manual.* * **`src/mcp_server_mod/`:** Di sinilah kode Python Anda berada. File `__init__.py` membuat `mcp_server_mod` menjadi paket Python. * **`main.py`:** Ini adalah titik masuk utama untuk skrip Anda. Anda dapat menggunakannya untuk mendefinisikan antarmuka baris perintah (menggunakan `click`, misalnya) atau untuk memulai proses latar belakang. * **`config.py`:** (Opsional) Gunakan ini untuk menangani pengaturan konfigurasi untuk proses pengembangan mod Anda. Anda dapat memuat pengaturan dari file atau variabel lingkungan. * **`utils.py`:** (Opsional) Letakkan fungsi utilitas yang dapat digunakan kembali di sini. * **`scripts/`:** Direktori ini berisi skrip Python yang berinteraksi dengan MCP atau mengotomatiskan bagian dari proses pengembangan mod. * **`apply_patches.py`:** Contoh skrip untuk menerapkan patch yang dihasilkan oleh MCP ke kode server Minecraft. Ini kemungkinan akan melibatkan penggunaan Python untuk membaca file patch dan menerapkannya menggunakan pustaka patching (atau dengan menjalankan alat baris perintah). * **`build_mod.py`:** Contoh skrip untuk membangun file JAR mod akhir. Ini mungkin melibatkan kompilasi kode Java (jika Anda memilikinya), pengemasan sumber daya, dan pembuatan JAR. Anda dapat menggunakan `subprocess` untuk memanggil perintah Java. * **`mcp/`:** (Opsional) Direktori ini dapat menyimpan file terkait MCP, seperti file konfigurasi (`mcp.cfg`) dan file patch. Ini adalah tempat yang baik untuk menjaga file-file ini tetap teratur. Anda mungkin tidak memerlukan ini jika Anda menggunakan MCP dengan cara yang lebih otomatis. * **`README.md`:** File Markdown untuk mendokumentasikan proyek Anda, termasuk instruksi tentang cara menyiapkan, menggunakan, dan berkontribusi ke dalamnya. * **.gitignore:** Menentukan file yang sengaja tidak dilacak yang harus diabaikan oleh Git. Ini harus mencakup file seperti `.venv` (lingkungan virtual), `pdm.lock`, dan artefak build apa pun. **Cara Menggunakan Template Ini:** 1. **Instal PDM:** Jika Anda belum memilikinya, instal PDM: ```bash pip install pdm ``` 2. **Buat Proyek:** Buat struktur direktori seperti yang ditunjukkan di atas. 3. **Inisialisasi PDM:** Di direktori root (`mcp-server-mod`), jalankan: ```bash pdm init ``` Ini akan memandu Anda melalui pengaturan file `pyproject.toml`. Jawab pertanyaan dengan tepat. 4. **Instal Dependensi:** Edit file `pyproject.toml` untuk menambahkan dependensi Anda (misalnya, `click`, `requests`). Kemudian, jalankan: ```bash pdm install ``` Ini akan membuat lingkungan virtual dan menginstal dependensi. 5. **Tulis Kode Anda:** Mulai tulis kode Python Anda di direktori `src/mcp_server_mod/`. Implementasikan skrip di direktori `scripts/` untuk berinteraksi dengan MCP dan mengotomatiskan proses pengembangan mod Anda. 6. **Jalankan Skrip Anda:** Anda dapat menjalankan skrip Anda menggunakan `pdm run`: ```bash pdm run python scripts/apply_patches.py pdm run python scripts/build_mod.py ``` 7. **Kontrol Versi:** Inisialisasi repositori Git: ```bash git init ``` Tambahkan file `.gitignore` (lihat contoh di bawah) dan commit kode Anda. **Contoh file `.gitignore`:** ``` .venv/ pdm.lock __pycache__/ *.pyc *.log build/ dist/ mcp/patches/ # Jika Anda menghasilkan patch di direktori mcp/patches ``` **Pertimbangan Penting:** * **Sifat Java MCP:** Ingatlah bahwa MCP terutama adalah toolchain Java. Template ini berfokus pada penggunaan Python untuk *melengkapi* MCP, bukan untuk menggantinya sepenuhnya. Anda kemungkinan perlu menggunakan `subprocess` untuk menjalankan perintah MCP dari skrip Python Anda. * **Pengaturan MCP:** Anda perlu menyiapkan MCP secara terpisah. Template ini mengasumsikan Anda telah menginstal dan mengonfigurasi MCP. * **Patching:** Menerapkan patch adalah tugas umum saat bekerja dengan MCP. Anda perlu menemukan pustaka patching yang sesuai untuk Python atau menggunakan alat baris perintah seperti `patch`. * **Proses Build:** Proses build untuk mod Minecraft bisa jadi rumit. Anda perlu memahami cara mengkompilasi kode Java, mengemas sumber daya, dan membuat file JAR akhir. * **Versi Server Minecraft:** Pastikan pengaturan MCP Anda dan mod Anda kompatibel dengan versi server Minecraft yang Anda targetkan. * **Modding API (Forge/Fabric):** Jika Anda menggunakan Modding API seperti Forge atau Fabric, Anda perlu mengintegrasikan proses build mereka ke dalam skrip Python Anda. **Contoh `apply_patches.py` (Ilustratif):** ```python import subprocess import os def apply_patches(patch_dir, minecraft_source_dir): """Menerapkan semua patch di direktori yang diberikan ke kode sumber Minecraft.""" for patch_file in os.listdir(patch_dir): if patch_file.endswith(".patch"): patch_path = os.path.join(patch_dir, patch_file) print(f"Menerapkan patch: {patch_path}") # Contoh menggunakan alat baris perintah 'patch' try: subprocess.run( ["patch", "-p0", "-i", patch_path], cwd=minecraft_source_dir, # Jalankan patch di direktori sumber Minecraft check=True, # Munculkan pengecualian jika perintah gagal capture_output=True, text=True ) print(f"Patch {patch_file} berhasil diterapkan.") except subprocess.CalledProcessError as e: print(f"Kesalahan saat menerapkan patch {patch_file}:") print(e.stderr) raise if __name__ == "__main__": # Contoh penggunaan: patch_directory = "mcp/patches" # Direktori yang berisi file patch Anda minecraft_source = "src/minecraft_source" # Ganti dengan jalur sebenarnya ke kode sumber Minecraft yang didekompilasi # Pastikan direktori sumber Minecraft ada if not os.path.exists(minecraft_source): print(f"Kesalahan: Direktori sumber Minecraft tidak ditemukan: {minecraft_source}") exit(1) # Pastikan direktori patch ada if not os.path.exists(patch_directory): print(f"Kesalahan: Direktori patch tidak ditemukan: {patch_directory}") exit(1) try: apply_patches(patch_directory, minecraft_source) print("Semua patch berhasil diterapkan!") except Exception as e: print(f"Terjadi kesalahan: {e}") ``` This template provides a solid foundation for building your MCP server mod development tools in Python. Remember to adapt it to your specific needs and the requirements of your mod. Good luck!

Reachy Claude MCP

Reachy Claude MCP

Integrates the Reachy Mini robot or its simulation with Claude Code to provide interactive physical feedback through emotions, speech, and celebratory animations. It features advanced capabilities like sentiment analysis, semantic problem search, and cross-project memory to enhance the developer experience.

MCP Greetings Server

MCP Greetings Server

Enables AI assistants to greet users in 7 different languages including English, Spanish, French, German, Japanese, Chinese, and Korean. A lightweight multilingual greeting tool for the Model Context Protocol.

nft-analytics-mcp

nft-analytics-mcp

An MCP server that delivers NFT collection analytics powered by data from Dune Analytics.

MCP Template Server

MCP Template Server

A Python starter template for building MCP servers with client connection management and Jupyter notebook integration. Provides a structured foundation for adding custom tools, prompts, and workflows to create AI-powered applications.

Blender MCP Server

Blender MCP Server

A lightweight HTTP server that exposes Blender's camera system for real-time image capture and scene interaction from external applications.

Zerocracy MCP Server

Zerocracy MCP Server

A server module for Claude Desktop that enables integration with Zerocracy, allowing interaction with the Zerocracy project management platform through natural language commands.