Discover Awesome MCP Servers

Extend your agent with 84,516 capabilities via MCP servers.

All84,516
NTFY MCP Server

NTFY MCP Server

Enables bidirectional communication between AI agents and users through ntfy.sh push notifications, allowing agents to send messages and wait for user responses in asynchronous chat workflows.

Warpcast MCP Server

Warpcast MCP Server

Enables interaction with Warpcast (Farcaster) through Claude, allowing users to post casts, search and read content, get trending posts, and manage channel subscriptions using natural language.

uacos

uacos

Local-first code intelligence and safety layer for AI coding agents. MCP server exposes dependency graph, impact analysis, and AST-compressed repo context, backed by typed local memory, patch-scope safety gates, and git-independent transaction rollback.

document-index-mcp

document-index-mcp

Indexes local documents (PDF, Word, Markdown, text) into a SQLite database for AI agents to search and retrieve bounded, source-located passages. Runs fully locally with optional OCR, preserving privacy.

Debugger MCP

Debugger MCP

Enables AI agents like Claude to control VS Code's debugger, supporting any language with a Debug Adapter Protocol implementation.

GIT MCP Server

GIT MCP Server

Node.js server implementing Model Context Protocol for git operations, enabling AI assistants to manage git repositories through natural language commands.

Mirelia-Patent-Marketplace

Mirelia-Patent-Marketplace

A fully autonomous patent data marketplace for AI agents, providing highly structured JSON datasets with strategic insights. Supports instant M2M transactions via ROSE on the Oasis Network.

MCP CU Chat Server

MCP CU Chat Server

Renders Azure Content Understanding field schema as interactive table cards in VS Code Chat, enabling editing and persistence of field descriptions.

agentflow-mcp

agentflow-mcp

Provides enterprise architecture knowledge tools that ground agents in curated patterns, enabling translation of messy enterprise asks into realistic architecture recommendations, platform selection, risk checks, and brand context retrieval.

mcpserve

mcpserve

A minimal, decorator-based framework for building MCP servers in Python with zero dependencies. It enables you to define tools and resources via simple decorators, handling JSON-RPC protocol, type inference, and stdio transport automatically.

indonesia-civic-stack

indonesia-civic-stack

Provides access to Indonesian government data sources (BPOM, BPJPH, AHU, etc.) via a unified API and MCP tools.

docker-mcp-server

docker-mcp-server

Enables AI agents to manage Docker containers, images, Compose stacks, health checks, and logs through a unified MCP interface, ensuring containers stay running with self-healing capabilities.

coursera

coursera

Enables browsing your Coursera courses, viewing library maps and course outlines, and downloading transcripts and readings as text via MCP tools.

paperless-mcp

paperless-mcp

MCP server for Paperless-ngx document management. Enables AI models to search, retrieve, update documents and manage metadata.

agentbus

agentbus

Local MCP event log for multi-agent workspaces, enabling structured event publishing, cursor-based polling, and status checks via SQLite-backed sidecar.

YouTube Video Downloader MCP

YouTube Video Downloader MCP

An advanced MCP server that enables asynchronous downloading of YouTube videos and playlists with features for job tracking and library management. It utilizes yt-dlp and an SQLite database to store metadata, monitor download status, and manage content through Claude Desktop.

feishu-bridge

feishu-bridge

MCP server that enables AI agents to interact with Feishu (Lark) for calendar events, attendees, and user recent work via structured tools with graceful degradation and recovery hints.

office-editor-mcp

office-editor-mcp

An MCP server for creating and editing Word, Excel, and PowerPoint documents through AI assistants.

Tavily Web Search MCP Server

Tavily Web Search MCP Server

Enables web search capabilities through the Tavily API, allowing users to search the web for information using natural language queries through the Model Context Protocol.

Hyperliquid MCP Server v3

Hyperliquid MCP Server v3

A streamlined version of the Hyperliquid MCP Server that can be set up with a single command

codegraph

codegraph

Provides AI agents with a function-level dependency graph of the codebase through 30 MCP tools, enabling structural queries about code dependencies, callers, and impact analysis.

PyKernel MCP

PyKernel MCP

MCP server that provides a persistent IPython kernel for executing Python code with pre-loaded numpy, pandas, and matplotlib, supporting stateful computation and inline visualizations.

mcp-creditcard

mcp-creditcard

Provides a Luhn check-digit validation tool for numeric strings such as credit cards, IMEI, and national IDs.

waydroid-mcp

waydroid-mcp

Enables agents to interact with Android via text-based UI trees instead of screenshots, supporting taps, swipes, input, macro recording, and device control through an MCP server and CLI.

notebooklm-mcp

notebooklm-mcp

An MCP server that gives Claude (and any MCP-compatible agent) full access to Google NotebookLM — create notebooks, upload sources, ask questions, and generate audio overviews, quizzes, flashcards, mind maps, slide decks, videos, and reports.

简单操作指南

简单操作指南

Repositório para projeto MCP em branco com configuração do servidor GitHub MCP

stuck-order-mcp

stuck-order-mcp

MCP server for investigating payment/webhook drift, classifying order status mismatches, detecting duplicate charges, and escalating findings for human review. It is read-only for payment state and does not automatically retry or correct transactions.

vikunja-mcp

vikunja-mcp

Enables AI assistants like Claude to manage Vikunja tasks – view, add, complete, edit, and delete tasks through natural language commands via Vikunja's REST API.

KaitoMCPServer

KaitoMCPServer

A Python-based MCP server that uses uv for dependency management, requiring Python 3.13+ to run.

MCP Code Mode

MCP Code Mode

Enables AI agents to write and execute Python code in an isolated sandbox that can orchestrate multiple MCP tool calls, reducing context window bloat and improving efficiency for complex workflows.