PlugMCP’s MCP directory of 73,918+ from the official registry, GitHub, npm, and PyPI. Free to search and install in Cursor, Claude, VS Code, or ChatGPT. Add the MCP for MCPs when you want the catalog from chat.
OfficialOfficial registry servers show an Official badge. They sit in this list with everyone else.
Submit a serverFAQ
Filters are on. Search text and sort stay with them.
MCP Server for the Austrian Legal Information System (RIS) - Access Austrian federal laws, state laws, court decisions and more
The official e18e MCP server
【电报群发+电报私聊+TG批量加群+TG机器人 AI智能吵群】/[Telegram Bulk Messaging + Telegram Private Messaging + Telegram Bulk Group Joining + Telegram AI Bot for Auto-Chat]
Security scanner for AI agent tool definitions
A fast, read-only MCP server for AI-assisted analysis of APK, DEX, JAR, and other Android artifacts, powered by ASC.
Generate, edit and save Xfer Serum 2 presets from natural language, over MCP
An implementation of a vulnerable MCP server using mcp-go
Make OpenClaw usable for everyone — setup, manage, and grow it into a practical digital personal assistant.
GatherThread 共序：本地 AI 编程 Agent 多人联机协作、实时共享上下文。Self-hostable collaboration for local AI coding agents, Codex Desktop connector & DeepSeek Harness plugin.
117 MCP tools for GPU infrastructure + Agent FinOps — deploy LLMs, manage VMs (Proxmox/XO/vSphere), track cost per agent, enforce budgets and model policies. Works with Claude, Cursor, n8n, LangChain
MCP server for AI agents to explore SystemVerilog/Verilog netlists: trace connectivity, walk hierarchy, jump to source - without pasting RTL into context. Built on najaeda.
A Cloudflare Worker that implements the MCP Streamable HTTP transport for AI agents to interact with pump.fun on Solana.
Ship iOS and Android apps from your AI agent. MCP server for App Store Connect, Google Play Console and Expo EAS.
Playwright-based testing and eval framework for MCP servers with LLM-as-a-judge
MCP browser automation server. Exposes browser control tools to external AI systems via Model Context Protocol. Open-source & secure.
This contains a MCP Server that has all the documentation for WPILib.
MCP server for Xcode Instruments — AI agents get structured performance profiling (CPU, SwiftUI, memory, hitches) instead of raw xctrace XML
MCP server wrapping the ZenMoney personal finance API
MCP server for Obsidian vault management - enables Claude and other AI assistants to read, write, search, and organize your notes
Enable AI-driven automated Android dynamic analysis by controlling Frida through the Model Context Protocol for streamlined reverse engineering.
A real local terminal in Edge/Chrome that gives Codex, Claude Code, Kimi Code, and any MCP CLI 41 local MCP tools through Browser Core v2.
MCP server for testing Terminal User Interfaces - like Playwright for TUI applications
MCP Server for inspecting, creating, editing, running, exporting, and deleting macOS Alfred 5 workflows.
Model Context Protocol
A brain for your mail: MailFathom turns IMAP mailboxes into a self-hosted, AI-native service. Mail synchronizes into your own PostgreSQL, is indexed for search and retrieval, and is served to AI agent
EDINET XBRL parsing library and MCP server for Japanese financial data
Universal synchronization layer for AI orchestrators, agents, MCP configs, skills, commands, and dev-tool workflows.
MCP server for Kyverno
MCP server providing browser automation via Playwright (Python), enabling LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser.
The MCP server for Dolt
An MCP Server based on Housecall Pro API for use with Claude Desktop, OpenAI, Cursor etc. Interacts with Housecall Pro API endpoints using natural language.
Claude Code plugin marketplace & agent skills for RudderStack — instrument events, design tracking plans & data graphs, write transformations, build Profiles, and drive the CLI, MCP server, and Terraf
A Model Context Protocol (MCP) server for Python package intelligence, providing structured queries for PyPI packages and GitHub repositories. Features include dependency analysis, version tracking, a
Lets Claude Code and Cursor drive Chrome. Blind benchmark vs agent-browser: -33% tokens, -33% cost, -24% tool calls, +48% speed, 30/30. Direct CDP, a11y-tree refs, server-side plan executor. MIT, no p
Your AI forgets everything between sessions. This fixes that — 98%+ retrieval accuracy, 100% on LongMemEval, 99% token savings. 44 MCP tools. Fully local, zero cost.
A flexible system for managing various types of sources (papers, books, webpages, etc.) and integrating them with knowledge graphs.