Discover Awesome MCP Servers

PyMCP

Primarily to be used as a template for developing MCP servers with FastMCP in Python, PyMCP is somewhat inspired by the official everything MCP server in Typescript.

KoKo Finance MCP Server

A hosted MCP server for AI-powered credit card advice, enabling search, comparison, portfolio analysis, and personalized recommendations for US credit cards through natural language.

LangGraph FastAPI MCP Server Demo

Turns a shopping list FastAPI app into an MCP server, enabling a LangGraph chatbot to manage shopping lists via natural language.

medwriter-mcp

Medical Writer's AI Toolkit — 33 expert prompts for pharma medical writing as MCP tools

Grimoire

A local security knowledge base that indexes documentation like CVEs and CWEs using hybrid keyword and semantic search. It enables LLM agents to query indexed materials via MCP for accurate, offline retrieval during security audits and code reviews.

hyperliquid-info-mcp

hyperliquid-info-mcp

Smart Reader MCP

Reads PDF, image, or video files by sniffing format and delegating to specialized sibling MCP servers, extracting facts and metadata without LLMs.

ONEDeFi MCP Server

Enables AI-powered DeFi operations across Ethereum, Polygon, and Solana with automated portfolio optimization, risk assessment, and yield farming strategies. Provides intelligent portfolio diagnostics, investment strategy generation, and multi-chain DeFi protocol integration through natural language.

mcp-feedback-enhanced

Establishes feedback-oriented development workflows with dual Web UI and Desktop interfaces, enabling AI to confirm with users before actions and consolidate multiple tool calls into a single feedback request.

Kylas CRM MCP Server

Enables management of Kylas CRM lead operations, including creating leads, searching and filtering records, and resolving user, product, or pipeline IDs. It provides specialized tools for monitoring idle leads and accessing lead schema instructions through natural language.

Scrapeless MCP Server

Implementasi server Protokol Konteks Model yang memungkinkan asisten AI seperti Claude untuk melakukan pencarian Google dan mengambil data web secara langsung melalui permintaan bahasa alami.

Files-DB-MCP

Sistem basis data vektor lokal yang menyediakan agen pengkodean LLM dengan kemampuan pencarian semantik yang cepat dan efisien untuk proyek perangkat lunak melalui Protokol Kontrol Pesan.

Wiki.js MCP Server

An MCP server that provides a unified interface to manage Wiki.js pages, users, and groups via GraphQL API, enabling AI agents to create, read, update, and delete content and perform administrative tasks.

Discord MCP Server

Enables LLMs to read messages, discover channels, send messages, and monitor Discord communities using the Discord HTTP API.

FeedbinMCP

An MCP server that enables users to interact with their Feedbin RSS account directly through Claude. It provides tools for reading articles, managing read and starred states, and browsing subscribed feeds and tags.

google-research-mcp

Implements Anthropic's multi-agent research architecture with subagent spawning, adaptive stopping, and citation processing for automated research.

HiveClaude

Coordinates multiple Claude Code agents to work collaboratively on projects with role-based task management, shared state, and automated code review.

AIDC AI Design Engine

Deterministic AI data-center design engine exposed as MCP tools for sizing, validation, and physical layout. Supports NVIDIA Hopper, Blackwell, and Vera Rubin with anonymous access to the remote engine.

appnova-app-store-connect-mcp

Enables managing your iOS app's entire lifecycle with natural language through App Store Connect, offering 48 tools across 14 categories for ASO, reviews, analytics, subscriptions, pricing, and more.

SSH MCP Server

Enables SSH operations including connecting to remote servers, executing commands, and transferring files between local and remote systems. Supports multiple SSH connections with both password and private key authentication methods.

power-db-mcp

A multi-database MCP tool that enables LLM agents to securely query and write to databases via local stdio, supporting MySQL, Oracle, PostgreSQL, DM, SQLite and more.

CyberEdu MCP Server

Official MCP server for the CyberEdu CTF platform that automatically discovers and exposes all CyberEduClient methods as tools, enabling seamless interaction with the platform through MCP-compatible clients.

soundings-mcp

Enables users to fetch, analyze, and visualize RAOB upper-air sounding data, including station search, thermodynamic calculations, and Skew-T diagram generation with S3 upload support.

MCP-NOSTR

Jembatan yang memungkinkan model bahasa AI untuk menerbitkan konten ke jaringan Nostr dengan mengimplementasikan Protokol Konteks Model (Model Context Protocol/MCP).

Matomo MCP Server

A Model Context Protocol server that provides tools to interact with Matomo Analytics API, enabling management of sites, users, goals, segments, and access to analytics reports through a MCP interface.

Deep Research MCP Server

An MCP server for deep research that performs search, scraping, synthesis, fact-checking, and persistent memory, enabling users to conduct comprehensive research tasks via Claude.

MCP API Service

Server Protokol Konteks Model (MCP) yang berinteraksi dengan API sistem, memungkinkan pengguna untuk memeriksa koneksi, mencari karyawan, mendaftar sarapan, dan memperbarui informasi kimia berdasarkan shift.

mcp-model-proxy

A minimal local MCP server that wraps any Claude Messages API-compatible upstream into a unified ask_model tool. It enables MCP clients to interact with these models through a standard tool interface using stdio transport.

GCP BigQuery MCP Server

Enterprise-grade MCP server for Google Cloud BigQuery with keyless Workload Identity Federation authentication, enabling secure SQL query execution, dataset management, and schema inspection with comprehensive audit logging and encryption.

squad-mcp

A cost-optimized MCP server that orchestrates parallel specialist agents to review code changes, write tests, update docs, and suggest refactors, using a triage step to avoid unnecessary work.