Discover Awesome MCP Servers

mcp-server-wikipedia

Enables efficient Wikipedia access through a progressive retrieval strategy that minimizes token usage by searching, summarizing, and fetching only relevant sections.

mcp-browser

Native macOS browser (SwiftUI + WKWebView) that exposes an MCP server in-process so AI agents can drive a real local browser with the user's existing logged-in sessions. ~40 tools (navigate, click, fill, screenshot, eval_js, network log, accessibility tree). Local-only with bearer-token auth.

GOD MODE INTEL MCP Server

A comprehensive B2B intelligence server providing over 48 tools for lead generation, company research, and sales automation via the Model Context Protocol. It enables AI-powered prospect discovery, enrichment, and competitive analysis through seamless integrations with Make.com, Claude Desktop, and Apify.

expense-tracker

Enables tracking business trip expenses and calculating settlements using Google Sheets, with natural language parsing of expenses.

pns-server MCP Server

Enables natural language conversion of production and queueing systems into Petri net models, with simulation and PNML export via MCP tools.

JSONPlaceholder MCP Server

Provides access to JSONPlaceholder's free fake REST API for testing and prototyping, enabling interaction with sample posts, users, comments, albums, photos, and todos through tools, resources, and prompts.

Edgee MCP Server

Enables interaction with the Edgee API for managing organizations, projects, domains, components, users, invitations, and API tokens through the Model Context Protocol.

Smart-MCP

Generates complex draw.io diagrams (tables, kanbans, GANTT) using a local 9B LLM with RAG, featuring a real-time dashboard and CI/CD pipeline.

SellerChamp MCP Server

An MCP server that enables AI agents to manage multi-marketplace e-commerce operations by connecting to the SellerChamp API. It supports inventory reporting, cross-listing analysis, order management, and bulk updates across platforms like Amazon, eBay, and Shopify.

mcp-dev-feeds

Enables AI agents to browse and read curated software-development feeds, fetch any RSS/Atom/RDF feed via URL, and filter items by keywords.

ACMS (Apple Container MCP Server)

Provides programmatic access to Apple's container CLI tool on macOS, enabling users to perform 50+ container operations including creation, management, and system control of Apple Silicon containers.

Homelab MCP Server

Enables Claude to monitor and manage homelab infrastructure including Docker containers, OPNsense firewall, and TrueNAS storage with configurable capability levels from read-only monitoring to full management control.

bricks-and-context

Enables AI assistants to interact with Databricks workspaces, running SQL queries, managing jobs, and exploring schemas via the Model Context Protocol.

onpe-mcp

MCP server for querying Peruvian electoral data (ONPE) including mesa results, candidate votes, and regional statistics. Enables natural language queries about the 2026 presidential election with local SQLite cache and live API fallback.

Memlord

Self-hosted MCP memory server for personal use and teams

Secure MCP-gRPC

Provides a secure gRPC transport layer for the Model Context Protocol (MCP) with mutual TLS, token-based authentication, and fine-grained authorization. Includes comprehensive telemetry and a real-time visualization dashboard for monitoring AI model interactions and security events.

sliver-mcp

A Model Context Protocol server for the Sliver C2 framework that exposes operator tools like listeners, implant generation, sessions, command execution, and file operations for LLM-driven adversary emulation.

Project Customization MCP

An open-source MCP server that automates project customization by analyzing your codebase and generating AI-ready configuration files based on industry best practices.

RedNote MCP Server

A Model Context Protocol (MCP) server that enables AI assistants to search, retrieve, and analyze content from Xiaohongshu (Little Red Book), providing access to notes, user information, and trending topics.

nr-mcp: New Relic MCP Server

Server MCP New Relic

Luxxon

On-demand live vision MCP for AI agents — open a session at a lat/lng, receive a JPEG snapshot or WebRTC stream, settled per-second in USDC on Base. Four tools (get_session, get_frame, get_stream_url, cancel_session); currently Base Sepolia testnet.

VGL CV Data MCP

A Model Context Protocol server that provides access to Valentin Gonzalez Loureiro's curriculum vitae data through a REST API.

JMA Data MCP

Provides access to Japan Meteorological Agency (JMA) weather data including real-time observations, historical weather data, and forecasts from 1286 AMeDAS stations across Japan.

presto-mcp-server

Integrates Presto construction budgeting software with Claude Code, enabling analysis, audit, and search of BC3 budget files locally or via WebAPI.

@getplexa/mcp

A Model Context Protocol server that gives any MCP client two economic-safety tools: realizable quote and pretrade check, paid per call in USDC with no accounts.

BachStudio Excel MCP Server

Enables creation, reading, and manipulation of Excel workbooks without Microsoft Excel installed, supporting formulas, formatting, charts, pivot tables, and data validation through multiple transport protocols.

Kirby MCP

CLI-first MCP server for Composer-based Kirby CMS projects that enables IDE or agent to inspect blueprints, templates, plugins, docs, and interact with a real Kirby runtime.

git-mcp-server

Here are a few ways an MCP (Managed Cloud Provider) server might handle GitHub/GitLab integrations, along with explanations: **1. Webhooks:** * **How it works:** This is the most common and direct approach. GitHub/GitLab sends HTTP POST requests (webhooks) to a specific endpoint on the MCP server whenever certain events occur in the repository (e.g., code push, pull request creation, merge). * **MCP Server Role:** * **Receives and Parses Webhooks:** The server needs an endpoint that can receive the webhook payload (usually in JSON format) and parse it to understand the event that triggered it. * **Authentication/Authorization:** The server must verify that the webhook is coming from a legitimate source (GitHub/GitLab) and that the user/repository has the necessary permissions. This often involves using secrets or tokens configured in both GitHub/GitLab and the MCP server. * **Triggers Actions:** Based on the event type and the configuration, the server triggers specific actions. Examples: * **Automated Builds:** A code push might trigger a build process (compilation, testing, packaging) on the MCP server. * **Deployment:** A merge to the `main` branch could trigger a deployment to a staging or production environment. * **Infrastructure Updates:** Changes to infrastructure-as-code files (e.g., Terraform, CloudFormation) could trigger updates to the cloud infrastructure managed by the MCP. * **Notifications:** Send notifications (email, Slack, etc.) to relevant teams about the event. * **Advantages:** * Real-time: Events are processed as they happen. * Flexible: Can be configured to trigger a wide range of actions. * **Disadvantages:** * Requires a publicly accessible endpoint (or a secure tunnel if the server is behind a firewall). * Requires careful security considerations to prevent unauthorized access. * Can be complex to set up and maintain. **2. Polling:** * **How it works:** The MCP server periodically checks the GitHub/GitLab repository for changes. * **MCP Server Role:** * **Authentication:** Uses API keys or OAuth tokens to authenticate with the GitHub/GitLab API. * **API Calls:** Makes API calls to retrieve information about the repository (e.g., recent commits, branches, pull requests). * **Change Detection:** Compares the current state of the repository with the previous state to detect changes. * **Triggers Actions:** If changes are detected, the server triggers the appropriate actions (similar to the webhook approach). * **Advantages:** * Simpler to set up than webhooks (no need for a publicly accessible endpoint). * **Disadvantages:** * Not real-time: There's a delay between the event and the action. * Less efficient: The server is constantly making API calls, even if there are no changes. * Can hit API rate limits if the polling frequency is too high. **3. GitOps (with a Git Operator):** * **How it works:** This is a more advanced approach that uses Git as the single source of truth for the desired state of the system. A "Git operator" running on the MCP server monitors the Git repository for changes and automatically reconciles the system to match the desired state. * **MCP Server Role:** * **Runs the Git Operator:** The Git operator is a piece of software (often a Kubernetes controller) that continuously monitors the Git repository. * **Authentication:** The operator authenticates with the Git repository using API keys or SSH keys. * **Reconciliation:** When changes are detected in the Git repository (e.g., changes to Kubernetes manifests, configuration files), the operator automatically applies those changes to the system. This might involve creating, updating, or deleting resources in the cloud environment. * **Advantages:** * Declarative: The desired state of the system is defined in Git, making it easy to track changes and roll back to previous versions. * Auditable: All changes are tracked in Git, providing a complete audit trail. * Self-healing: The operator continuously reconciles the system to the desired state, automatically correcting any deviations. * **Disadvantages:** * More complex to set up than webhooks or polling. * Requires a good understanding of GitOps principles. **4. Direct API Integration:** * **How it works:** The MCP server directly uses the GitHub/GitLab API to perform various tasks. * **MCP Server Role:** * **Authentication:** Uses API keys or OAuth tokens to authenticate with the GitHub/GitLab API. * **API Calls:** Makes API calls to: * Create repositories. * Manage users and permissions. * Retrieve code. * Create pull requests. * Get commit statuses. * **Advantages:** * Fine-grained control over GitHub/GitLab resources. * **Disadvantages:** * Requires a deep understanding of the GitHub/GitLab API. * Can be complex to implement. **Example Scenario (Webhook-based):** Let's say an MCP offers automated deployment. Here's how a webhook integration might work: 1. **User Configuration:** The user configures a webhook in their GitHub repository to send events to a specific URL on the MCP server. They also provide an API key or secret to authenticate the webhook. 2. **Code Push:** A developer pushes code to the repository. 3. **Webhook Trigger:** GitHub sends a `push` event webhook to the MCP server. 4. **MCP Server Receives and Authenticates:** The MCP server receives the webhook, verifies the API key/secret, and parses the payload. 5. **Build and Deploy:** The server identifies the repository and branch that triggered the event. It then initiates a build process (e.g., using Docker) and, if the build is successful, deploys the application to the appropriate environment (e.g., a Kubernetes cluster). 6. **Status Updates:** The MCP server might update the commit status in GitHub/GitLab to indicate whether the build and deployment were successful. **Key Considerations for MCPs:** * **Security:** Proper authentication and authorization are crucial to prevent unauthorized access to GitHub/GitLab repositories. Use strong secrets, rotate keys regularly, and follow security best practices. * **Scalability:** The integration should be able to handle a large number of repositories and events. Consider using message queues or other asynchronous processing techniques to handle high volumes of traffic. * **Error Handling:** Implement robust error handling to gracefully handle failures and provide informative error messages to users. * **Configuration:** Provide a user-friendly interface for configuring the integration. Allow users to specify which events should trigger actions and how those actions should be performed. * **Monitoring:** Monitor the integration to ensure that it is working correctly and to identify any potential problems. In Indonesian: Berikut adalah beberapa cara server MCP (Managed Cloud Provider) dapat menangani integrasi GitHub/GitLab, beserta penjelasannya: **1. Webhooks:** * **Cara kerjanya:** Ini adalah pendekatan yang paling umum dan langsung. GitHub/GitLab mengirimkan permintaan HTTP POST (webhooks) ke endpoint tertentu di server MCP setiap kali peristiwa tertentu terjadi di repositori (misalnya, push kode, pembuatan pull request, merge). * **Peran Server MCP:** * **Menerima dan Memproses Webhooks:** Server membutuhkan endpoint yang dapat menerima payload webhook (biasanya dalam format JSON) dan memprosesnya untuk memahami peristiwa yang memicunya. * **Autentikasi/Otorisasi:** Server harus memverifikasi bahwa webhook berasal dari sumber yang sah (GitHub/GitLab) dan bahwa pengguna/repositori memiliki izin yang diperlukan. Ini sering melibatkan penggunaan rahasia atau token yang dikonfigurasi di GitHub/GitLab dan server MCP. * **Memicu Tindakan:** Berdasarkan jenis peristiwa dan konfigurasi, server memicu tindakan tertentu. Contoh: * **Build Otomatis:** Push kode dapat memicu proses build (kompilasi, pengujian, pengemasan) di server MCP. * **Deployment:** Merge ke branch `main` dapat memicu deployment ke lingkungan staging atau produksi. * **Pembaruan Infrastruktur:** Perubahan pada file infrastructure-as-code (misalnya, Terraform, CloudFormation) dapat memicu pembaruan pada infrastruktur cloud yang dikelola oleh MCP. * **Notifikasi:** Mengirim notifikasi (email, Slack, dll.) ke tim yang relevan tentang peristiwa tersebut. * **Keuntungan:** * Real-time: Peristiwa diproses saat terjadi. * Fleksibel: Dapat dikonfigurasi untuk memicu berbagai tindakan. * **Kerugian:** * Membutuhkan endpoint yang dapat diakses publik (atau tunnel aman jika server berada di belakang firewall). * Membutuhkan pertimbangan keamanan yang cermat untuk mencegah akses tidak sah. * Dapat menjadi rumit untuk diatur dan dipelihara. **2. Polling:** * **Cara kerjanya:** Server MCP secara berkala memeriksa repositori GitHub/GitLab untuk perubahan. * **Peran Server MCP:** * **Autentikasi:** Menggunakan kunci API atau token OAuth untuk mengautentikasi dengan API GitHub/GitLab. * **Panggilan API:** Melakukan panggilan API untuk mengambil informasi tentang repositori (misalnya, commit terbaru, branch, pull request). * **Deteksi Perubahan:** Membandingkan keadaan repositori saat ini dengan keadaan sebelumnya untuk mendeteksi perubahan. * **Memicu Tindakan:** Jika perubahan terdeteksi, server memicu tindakan yang sesuai (mirip dengan pendekatan webhook). * **Keuntungan:** * Lebih sederhana untuk diatur daripada webhook (tidak memerlukan endpoint yang dapat diakses publik). * **Kerugian:** * Tidak real-time: Ada penundaan antara peristiwa dan tindakan. * Kurang efisien: Server terus-menerus melakukan panggilan API, bahkan jika tidak ada perubahan. * Dapat mencapai batas laju API jika frekuensi polling terlalu tinggi. **3. GitOps (dengan Git Operator):** * **Cara kerjanya:** Ini adalah pendekatan yang lebih canggih yang menggunakan Git sebagai sumber kebenaran tunggal untuk keadaan sistem yang diinginkan. "Git operator" yang berjalan di server MCP memantau repositori Git untuk perubahan dan secara otomatis merekonsiliasi sistem agar sesuai dengan keadaan yang diinginkan. * **Peran Server MCP:** * **Menjalankan Git Operator:** Git operator adalah perangkat lunak (seringkali pengontrol Kubernetes) yang terus-menerus memantau repositori Git. * **Autentikasi:** Operator mengautentikasi dengan repositori Git menggunakan kunci API atau kunci SSH. * **Rekonsiliasi:** Ketika perubahan terdeteksi di repositori Git (misalnya, perubahan pada manifes Kubernetes, file konfigurasi), operator secara otomatis menerapkan perubahan tersebut ke sistem. Ini mungkin melibatkan pembuatan, pembaruan, atau penghapusan sumber daya di lingkungan cloud. * **Keuntungan:** * Deklaratif: Keadaan sistem yang diinginkan didefinisikan dalam Git, sehingga mudah untuk melacak perubahan dan mengembalikan ke versi sebelumnya. * Dapat diaudit: Semua perubahan dilacak di Git, menyediakan jejak audit lengkap. * Penyembuhan diri: Operator terus-menerus merekonsiliasi sistem ke keadaan yang diinginkan, secara otomatis memperbaiki setiap penyimpangan. * **Kerugian:** * Lebih rumit untuk diatur daripada webhook atau polling. * Membutuhkan pemahaman yang baik tentang prinsip-prinsip GitOps. **4. Integrasi API Langsung:** * **Cara kerjanya:** Server MCP secara langsung menggunakan API GitHub/GitLab untuk melakukan berbagai tugas. * **Peran Server MCP:** * **Autentikasi:** Menggunakan kunci API atau token OAuth untuk mengautentikasi dengan API GitHub/GitLab. * **Panggilan API:** Melakukan panggilan API untuk: * Membuat repositori. * Mengelola pengguna dan izin. * Mengambil kode. * Membuat pull request. * Mendapatkan status commit. * **Keuntungan:** * Kontrol terperinci atas sumber daya GitHub/GitLab. * **Kerugian:** * Membutuhkan pemahaman mendalam tentang API GitHub/GitLab. * Dapat menjadi rumit untuk diimplementasikan. **Contoh Skenario (berbasis Webhook):** Katakanlah MCP menawarkan deployment otomatis. Berikut cara integrasi webhook dapat bekerja: 1. **Konfigurasi Pengguna:** Pengguna mengonfigurasi webhook di repositori GitHub mereka untuk mengirim peristiwa ke URL tertentu di server MCP. Mereka juga menyediakan kunci API atau rahasia untuk mengautentikasi webhook. 2. **Push Kode:** Seorang pengembang mendorong kode ke repositori. 3. **Pemicu Webhook:** GitHub mengirimkan webhook peristiwa `push` ke server MCP. 4. **Server MCP Menerima dan Mengautentikasi:** Server MCP menerima webhook, memverifikasi kunci API/rahasia, dan memproses payload. 5. **Build dan Deploy:** Server mengidentifikasi repositori dan branch yang memicu peristiwa tersebut. Kemudian memulai proses build (misalnya, menggunakan Docker) dan, jika build berhasil, men-deploy aplikasi ke lingkungan yang sesuai (misalnya, klaster Kubernetes). 6. **Pembaruan Status:** Server MCP dapat memperbarui status commit di GitHub/GitLab untuk menunjukkan apakah build dan deployment berhasil. **Pertimbangan Utama untuk MCP:** * **Keamanan:** Autentikasi dan otorisasi yang tepat sangat penting untuk mencegah akses tidak sah ke repositori GitHub/GitLab. Gunakan rahasia yang kuat, putar kunci secara teratur, dan ikuti praktik terbaik keamanan. * **Skalabilitas:** Integrasi harus dapat menangani sejumlah besar repositori dan peristiwa. Pertimbangkan untuk menggunakan antrian pesan atau teknik pemrosesan asinkron lainnya untuk menangani volume lalu lintas yang tinggi. * **Penanganan Kesalahan:** Terapkan penanganan kesalahan yang kuat untuk menangani kegagalan dengan baik dan memberikan pesan kesalahan yang informatif kepada pengguna. * **Konfigurasi:** Sediakan antarmuka yang mudah digunakan untuk mengonfigurasi integrasi. Izinkan pengguna untuk menentukan peristiwa mana yang harus memicu tindakan dan bagaimana tindakan tersebut harus dilakukan. * **Pemantauan:** Pantau integrasi untuk memastikan bahwa integrasi berfungsi dengan benar dan untuk mengidentifikasi potensi masalah.

Suricata MCP

An MCP server for validating Suricata rule syntax and testing rules against pcap files to verify alert matching. It automates the testing process by running Suricata and parsing generated alert logs to confirm signature IDs.