Discover Awesome MCP Servers

SAP Ariba Procurement MCP Server by CData

This project builds a read-only MCP server. For full read, write, update, delete, and action capabilities and a simplified setup, check out our free CData MCP Server for SAP Ariba Procurement (beta): https://www.cdata.com/download/download.aspx?sku=PAZK-V&type=beta

caniuse-mcp

An MCP server that provides browser compatibility data and web API support information using caniuse.com, MDN BCD, and Web Features, enabling developers to check feature support across browsers and against browserslist configurations.

MCP Node Tasks 05 - Sampling

An MCP server that demonstrates sampling, enabling the server to request LLM completions from the client to assist in workflow tasks like planning work sessions.

Soma MCP Server

Enables running code against tests in an isolated sandbox to obtain PASS/FAIL verdicts with signed, offline-checkable certificates, and generating verified code with attached certificates after execution against derived tests.

Engram

A self-hosted MCP server enabling multiple AI coding agents to share state, preserve context across sessions, and coordinate with each other.

browse

Headless browser automation via MCP using Playwright WebKit.

cyberdyne-mcp

Lets an AI agent hire and pay a verified human: post real-world tasks (voice, observation, judgment) and pay in USDC via a non-custodial x402 auth-capture escrow on Base, budget frozen at deploy. Humans verify their X identity before submitting.

Interactive Feedback MCP

MCP server that enables human-in-the-loop workflow in AI-assisted development tools by allowing users to provide direct feedback to AI agents without consuming additional premium requests.

docs-mcp

Local documentation search server for AI models using hybrid retrieval (phrase, keyword, vector). Provides MCP tools to search and fetch documentation from bundled or custom doc sets without any external API keys.

SkillMCP

Serves project-specific skills and behavioral rules to AI agents via MCP, enabling automatic injection of behavioral rules and on-demand knowledge for coding assistants like Claude Code and Gemini CLI.

satellite-mcp

Full-spectrum GEOINT server with 171 tools covering satellite imagery, aircraft tracking, maritime surveillance, military intelligence, conflict monitoring, environmental analysis, critical infrastructure, sanctions compliance, and cyber-geo intelligence from open-source data.

MCP Server Implementations

Implementasi server khusus untuk Model Control Protocol (MCP) menggunakan Server-Sent Events (SSE)

FAA Advisory Circular MCP

Enables searching, retrieving, and tracking FAA Advisory Circulars for airport operations with filtering by airport type, bookmarking, and export capabilities.

rocket-cli

Rocket.Chat bridge with a local SQLite/FTS5 cache — CLI for humans, MCP server for LLM agents.

OpenFeature MCP Server

Provides OpenFeature SDK installation guidance for various programming languages and enables feature flag evaluation through the OpenFeature Remote Evaluation Protocol (OFREP). Supports multiple AI clients and can connect to any OFREP-compatible feature flag service.

天气 MCP 服务器

Ini adalah server MCP kueri cuaca yang dibangun berdasarkan FastMCP.

packforai-mcp

Converts PDF, DOCX, PPTX, XLSX, CSV, and JSON into clean, compact, AI-ready Markdown, reducing tokens up to 65%.

long-context-mcp

An MCP server implementing Recursive Language Models (RLM) to process arbitrarily large contexts through a programmatic probe, recurse, and synthesize loop. It enables LLMs to perform multi-step investigations and evidence-backed extraction across massive file sets without being limited by standard context windows.

aris-md/mcp

A minimal, well-structured MCP server implementation for learning and experimentation that exposes three tools: web search, API search, and client ID processing. It demonstrates clean separation between tool, transport, and LLM layers while supporting multiple AI clients through the Model Context Protocol standard.

stockdata-mcp

An MCP server for stock research with 52 tools across FMP and Qualtrim backends, providing raw financial data plus derived analytics, DCF, AI commentary, and portfolio management. It handles caching, API budgeting, and credential management.

willow-mcp

An agent-neutral MCP server providing SQLite key/value storage, Postgres knowledge base, and Kart task queue functionality. Features SAP/1.0 authorization on every tool call for secure multi-application access.

MCP Web Chat

A server that enables WebChat functionality through MCP (Model-Control-Protocol), solving long-term connection issues while providing both common method calls and business API integration capabilities.

mcp-stackexchange

Wraps the StackExchange API v2.3 to enable reading StackExchange data (questions, answers, etc.) without authentication. Allows AI agents to query StackExchange content through natural language or direct tool calls.

Directmedia MCP

Provides programmatic access to the Directmedia Publishing 'Digitale Bibliothek' collection, a 1990s German electronic book library containing 101 volumes of classic literature and philosophy with text extraction, search, and navigation capabilities.

Karbon MCP Server

An unofficial Model Context Protocol server that connects MCP-compatible clients to Karbon practice management, enabling natural language interaction with contacts, work items, notes, timesheets, and more.

meta-ads-mcp

A self-hosted Model Context Protocol (MCP) server that gives AI agents secure, multi-tenant access to the Meta Marketing API for Facebook Ads and Instagram Ads. It enables campaign management, audience targeting, insights, lead management, and more across multiple ad accounts.

Sample Model Context Protocol Demos

Okay, here are some examples of how to use the Model Context Protocol with AWS, translated into Indonesian: **Judul: Kumpulan Contoh Penggunaan Protokol Konteks Model dengan AWS** **Pendahuluan:** Protokol Konteks Model (Model Context Protocol) adalah cara untuk menyediakan informasi kontekstual ke model machine learning Anda saat di-deploy. Informasi ini dapat mencakup data konfigurasi, kredensial, atau metadata lainnya yang dibutuhkan model untuk beroperasi dengan benar. Dengan AWS, Anda dapat memanfaatkan berbagai layanan untuk mengelola dan menyediakan konteks model ini. **Contoh 1: Menyediakan Kredensial AWS ke Model yang Berjalan di Amazon SageMaker** * **Bahasa Inggris:** "Let's say you have a model deployed on Amazon SageMaker that needs to access data from an S3 bucket. Instead of hardcoding the AWS credentials into the model code, you can use the SageMaker execution role to provide the necessary permissions. The model can then use the AWS SDK to assume the role and access the S3 bucket." * **Bahasa Indonesia:** "Katakanlah Anda memiliki model yang di-deploy di Amazon SageMaker yang perlu mengakses data dari bucket S3. Alih-alih memasukkan kredensial AWS secara langsung (hardcoding) ke dalam kode model, Anda dapat menggunakan peran eksekusi SageMaker untuk menyediakan izin yang diperlukan. Model kemudian dapat menggunakan AWS SDK untuk mengambil peran tersebut dan mengakses bucket S3." **Penjelasan:** * **SageMaker Execution Role:** Peran IAM yang diberikan ke instance SageMaker. Ini memberikan izin kepada instance untuk mengakses layanan AWS lainnya. * **AWS SDK:** Perpustakaan (library) yang memungkinkan model Anda berinteraksi dengan layanan AWS. * **Keuntungan:** Keamanan yang lebih baik (tidak ada kredensial yang di-hardcode), manajemen kredensial yang terpusat. **Contoh 2: Menggunakan AWS Secrets Manager untuk Menyimpan dan Mengakses Kunci API** * **Bahasa Inggris:** "Your model might need to call an external API that requires an API key. You can store the API key securely in AWS Secrets Manager and then retrieve it from your model at runtime. This prevents the API key from being exposed in your code or configuration files." * **Bahasa Indonesia:** "Model Anda mungkin perlu memanggil API eksternal yang memerlukan kunci API. Anda dapat menyimpan kunci API dengan aman di AWS Secrets Manager dan kemudian mengambilnya dari model Anda saat runtime. Ini mencegah kunci API terekspos dalam kode atau file konfigurasi Anda." **Penjelasan:** * **AWS Secrets Manager:** Layanan untuk menyimpan dan mengelola rahasia (secrets) seperti kunci API, kata sandi database, dan sertifikat. * **Runtime:** Waktu ketika model sedang berjalan dan memproses data. * **Keuntungan:** Keamanan yang ditingkatkan, rotasi rahasia yang mudah. **Contoh 3: Menggunakan AWS Systems Manager Parameter Store untuk Menyimpan Konfigurasi Model** * **Bahasa Inggris:** "You can use AWS Systems Manager Parameter Store to store configuration parameters for your model, such as the learning rate, batch size, or the path to a pre-trained model. This allows you to easily update the configuration without redeploying the model." * **Bahasa Indonesia:** "Anda dapat menggunakan AWS Systems Manager Parameter Store untuk menyimpan parameter konfigurasi untuk model Anda, seperti learning rate, ukuran batch, atau path ke model yang sudah dilatih sebelumnya (pre-trained model). Ini memungkinkan Anda untuk dengan mudah memperbarui konfigurasi tanpa perlu melakukan redeploy model." **Penjelasan:** * **AWS Systems Manager Parameter Store:** Layanan untuk menyimpan data konfigurasi dan rahasia. * **Learning Rate, Batch Size:** Contoh parameter yang sering digunakan dalam machine learning. * **Keuntungan:** Manajemen konfigurasi yang terpusat, pembaruan konfigurasi yang mudah. **Contoh 4: Menggunakan Amazon DynamoDB untuk Menyimpan Metadata Model** * **Bahasa Inggris:** "You can store metadata about your model in Amazon DynamoDB, such as the model version, training data used, and performance metrics. This metadata can be used for model tracking, auditing, and debugging." * **Bahasa Indonesia:** "Anda dapat menyimpan metadata tentang model Anda di Amazon DynamoDB, seperti versi model, data pelatihan yang digunakan, dan metrik kinerja. Metadata ini dapat digunakan untuk pelacakan model, audit, dan debugging." **Penjelasan:** * **Amazon DynamoDB:** Database NoSQL yang cepat dan scalable. * **Metadata:** Data tentang data (dalam hal ini, data tentang model). * **Keuntungan:** Pelacakan model yang lebih baik, kemampuan audit, dan debugging yang lebih mudah. **Contoh 5: Menggunakan AWS Lambda untuk Menyediakan Konteks Model Dinamis** * **Bahasa Inggris:** "You can use AWS Lambda to create a function that dynamically retrieves context information for your model based on the input data. For example, the Lambda function could retrieve user-specific data from a database and pass it to the model as context." * **Bahasa Indonesia:** "Anda dapat menggunakan AWS Lambda untuk membuat fungsi yang secara dinamis mengambil informasi konteks untuk model Anda berdasarkan data input. Misalnya, fungsi Lambda dapat mengambil data spesifik pengguna dari database dan meneruskannya ke model sebagai konteks." **Penjelasan:** * **AWS Lambda:** Layanan komputasi tanpa server (serverless) yang memungkinkan Anda menjalankan kode tanpa menyediakan atau mengelola server. * **Konteks Dinamis:** Informasi konteks yang berubah berdasarkan input. * **Keuntungan:** Fleksibilitas yang tinggi, kemampuan untuk menyediakan konteks yang dipersonalisasi. **Kesimpulan:** Contoh-contoh di atas menunjukkan beberapa cara untuk menggunakan Protokol Konteks Model dengan AWS. Dengan memanfaatkan layanan AWS seperti SageMaker, Secrets Manager, Parameter Store, DynamoDB, dan Lambda, Anda dapat mengelola dan menyediakan konteks model dengan aman dan efisien. Pilihan layanan yang tepat akan bergantung pada kebutuhan spesifik model dan aplikasi Anda. **Catatan:** Pastikan untuk selalu mengikuti praktik terbaik keamanan AWS saat mengelola kredensial dan data sensitif.

wiki-mcp-server

A lightweight personal wiki MCP server that allows AI assistants to save, search, and link markdown notes with backlinks and full-text search, functioning as a file-based second brain.

Verified Wages MCP

Provides current, source-cited US minimum wage, tipped wage, and FLSA overtime data for AI agents, with tools to query rates, verify wage floors, and list scheduled changes. It refreshes state-level wage information from DOL sources and refuses to guess when data is unavailable.

delivery-intelligence-mcp

Enables delivery leads to query explainable programme health, prioritized risks, dependency impacts, change request effects, blocked decisions, and evidence-backed claims with refusal on unsupported assertions, all via deterministic tools and telemetry.