Discover Awesome MCP Servers

Universal Database MCP

A small MCP server that lets an LLM query PostgreSQL, MySQL, MariaDB, SQL Server, or SQLite databases safely — read-only, role-restricted, and with sensitive data blacked out.

McpSidecar

This MCP server runs as a sidecar in a Docker sandbox, providing tools for Microsoft Learn documentation and code sample search, and a resource for answer format instructions, enabling an AI agent to answer programming questions securely.

Yandex Wordstat MCP

Enables keyword research and search trend analysis for the Russian market through Yandex Wordstat API. Provides access to popular search queries, search volume dynamics over time, and regional distribution data.

@bdelanghe/site-mcp

A local, read-only MCP server that exposes verified profile, posts, corpus, and other identity data from robertdelanghe.dev's signed static API.

mcp-device-datetime

Exposes the host device's current date and time, returning local time with timezone offset or UTC.

evolution-mcp

MCP server for GNOME Evolution that enables calendar and email operations such as listing calendars/events, sending emails, and searching messages through the Evolution Data Server.

mcpo-docker

Berikut adalah contoh Docker image untuk mcpo, sebuah alat yang mengekspos server MCP (Model Context Protocol) sebagai endpoint HTTP yang kompatibel dengan OpenAPI untuk OpenWebUI: ```dockerfile # Gunakan image dasar Python FROM python:3.11-slim-buster # Set direktori kerja di dalam container WORKDIR /app # Salin file requirements.txt (jika ada) dan instal dependensi COPY requirements.txt . RUN pip install --no-cache-dir -r requirements.txt # Salin kode sumber mcpo ke dalam container COPY . . # Ekspos port yang akan digunakan mcpo (sesuaikan dengan kebutuhan Anda) EXPOSE 8000 # Jalankan mcpo saat container dimulai CMD ["python", "main.py"] ``` **Penjelasan:** * **`FROM python:3.11-slim-buster`**: Baris ini menentukan image dasar yang akan digunakan. Dalam hal ini, kita menggunakan image Python 3.11 yang ringan (slim-buster). Anda dapat menyesuaikan versi Python sesuai kebutuhan proyek Anda. * **`WORKDIR /app`**: Baris ini menetapkan direktori kerja di dalam container menjadi `/app`. Semua perintah selanjutnya akan dijalankan dalam direktori ini. * **`COPY requirements.txt .`**: Baris ini menyalin file `requirements.txt` (jika ada) dari direktori lokal Anda ke direktori `/app` di dalam container. File `requirements.txt` biasanya berisi daftar dependensi Python yang dibutuhkan oleh proyek Anda. * **`RUN pip install --no-cache-dir -r requirements.txt`**: Baris ini menjalankan perintah `pip install` untuk menginstal dependensi yang tercantum dalam `requirements.txt`. Opsi `--no-cache-dir` mencegah pip menyimpan cache paket, yang dapat mengurangi ukuran image. * **`COPY . .`**: Baris ini menyalin semua file dan direktori dari direktori lokal Anda ke direktori `/app` di dalam container. Ini termasuk kode sumber mcpo Anda. * **`EXPOSE 8000`**: Baris ini mengekspos port 8000 dari container. Ini berarti bahwa aplikasi yang berjalan di dalam container akan dapat diakses melalui port 8000. Anda perlu menyesuaikan port ini dengan port yang digunakan oleh mcpo Anda. * **`CMD ["python", "main.py"]`**: Baris ini menentukan perintah yang akan dijalankan saat container dimulai. Dalam hal ini, kita menjalankan skrip Python `main.py`, yang diasumsikan sebagai titik masuk utama untuk mcpo. Anda mungkin perlu menyesuaikan perintah ini tergantung pada bagaimana mcpo Anda diatur. **Cara Menggunakan:** 1. **Simpan Dockerfile:** Simpan kode di atas sebagai file bernama `Dockerfile` di direktori root proyek mcpo Anda. 2. **Buat file `requirements.txt` (jika diperlukan):** Jika proyek mcpo Anda memiliki dependensi Python, buat file bernama `requirements.txt` di direktori root proyek Anda dan daftarkan semua dependensi di sana. Contoh: ``` fastapi uvicorn pydantic # ... dependensi lainnya ``` 3. **Bangun image Docker:** Buka terminal di direktori root proyek Anda dan jalankan perintah berikut: ```bash docker build -t mcpo-image . ``` Ini akan membangun image Docker dengan nama `mcpo-image`. Tanda titik (`.`) menunjukkan bahwa Dockerfile berada di direktori saat ini. 4. **Jalankan container Docker:** Setelah image berhasil dibangun, Anda dapat menjalankan container menggunakan perintah berikut: ```bash docker run -d -p 8000:8000 mcpo-image ``` * `-d`: Menjalankan container di latar belakang (detached mode). * `-p 8000:8000`: Memetakan port 8000 dari host ke port 8000 di dalam container. Anda dapat mengubah port host jika diperlukan. * `mcpo-image`: Nama image yang akan dijalankan. **Penting:** * Pastikan untuk mengganti `main.py` dengan nama file titik masuk utama mcpo Anda. * Sesuaikan port yang diekspos (`EXPOSE`) dan dipetakan (`-p`) dengan port yang digunakan oleh mcpo Anda. * Jika mcpo Anda memerlukan variabel lingkungan, Anda dapat menyetelnya menggunakan opsi `-e` saat menjalankan container (misalnya, `docker run -d -p 8000:8000 -e MCP_SERVER_URL=http://example.com mcpo-image`). * Pastikan kode mcpo Anda sudah siap dan berfungsi sebelum membangun image Docker. Contoh ini memberikan dasar untuk membuat image Docker untuk mcpo. Anda mungkin perlu menyesuaikannya lebih lanjut tergantung pada kebutuhan spesifik proyek Anda.

Sequa MCP

Enables AI assistants to access contextual knowledge from multiple repositories through Sequa's Contextual Knowledge Engine. Provides architecture-aware code understanding and cross-repository context for more accurate, production-ready code generation.

Host Terminal MCP

Enables AI assistants to execute terminal commands on a host machine with configurable, granular permission controls and safety protections. It features multiple security modes, including allowlists and manual approval, to ensure safe command execution within specified directories.

QuickSight MCP Server

An auto-generated MCP server that enables interaction with AWS QuickSight services through the Model Context Protocol. Provides programmatic access to QuickSight's business intelligence and analytics capabilities via the AWS QuickSight OpenAPI specification.

NitroStack Calculator MCP Server

Enables learning NitroStack fundamentals with a calculator-focused MCP server including tools, resources, and prompts.

LedgerMem MCP Server

Enables persistent memory storage and retrieval for MCP clients, allowing AI assistants to remember facts and context across conversations.

TrueConf Server MCP

Enables managing TrueConf Server conferences, recordings, invitations, participants, chats, and calendars from any MCP client. Supports OAuth authentication and exposes 32 tools for conference, recording, and invitation management.

mcp-gitlab

mcp-gitlab

atlas_mcp

An MCP server that brings AI-powered search and conversation to your FHIR clinical documents.

magic-api-mcp

Enables AI to manage and interact with a running magic-api instance, including CRUD operations on APIs, groups, functions, and datasources, with built-in magic-script knowledge.

PostgreSQL MCP AI Explorer

A Model Context Protocol server that enables natural language data exploration and visualization for PostgreSQL databases. It allows users to convert questions into SQL queries and interact with data through a Streamlit web interface featuring automated chart generation.

Durable Thinking

Persistent sequential thinking for MCP clients, stored durably on Cloudflare Workers with support for branching, revision, and history retrieval.

mcp-exchange

Enables currency exchange rate lookups, amount conversion, historical rate retrieval, and listing of supported currencies via the Frankfurter API.

Ged Invest MCP

An MCP server for construction tools that calculates wall formwork material takeoffs from geometry inputs, enabling LLMs to generate accurate bills of materials.

obsidian-mcp

Bidirectional MCP server that connects Claude with an Obsidian vault, enabling note management, full-text search, graph traversal, and daily notes operations.

Project Tessera

Local workspace memory for Claude Desktop. Indexes documents into a vector store with hybrid search, cross-session memory, auto-learn, and knowledge graph.

mcp-ipqualityscore

Wraps IPQualityScore's fraud-prevention API to enable AI agents to check IP reputation, email verification, and other fraud detection data through natural language queries.

mcp-reactome

Enables AI agents to query the Reactome biological pathway knowledge-base for pathways, participants, and orthologous events using natural language.

mcp-dev-record

A dedicated MCP (Model Context Protocol) server for recording and organizing conversation content, providing templated recording functionality.

apps-mcp

Unofficial MCP server for the Apps API that enables managing customers, payments, plans, coupons, and Discord integration through natural language.

inspect-logs-mcp

Enables LLMs to explore and analyze UK Government BEIS inspect_ai evaluation logs directly from tools like Claude Code and Cursor. It provides capabilities to list logs, view evaluation summaries, and inspect conversation histories for specific samples.

fathom-mcp

A Model Context Protocol server that provides AI assistants with direct access to local document collections through full-text search, supporting multiple formats and hierarchical collections.

orbit-mcp

A stdio-based MCP server that exposes the Orbit CPaaS API as tools, enabling sending SMS, managing campaigns, and other communication workflows through natural language in MCP clients.