Find Awesome MCP Servers and Clients
MCP.so is a third-party MCP Marketplace with 22103 MCP Servers collected.
ShipAny: NextJS boilerplate for building AI SaaS startups.
Latest MCP Servers
View AllZooza Mcp Server
Official MCP server for Zooza — manage class schedules, attendance, bookings, and payments for dance schools, language academies, swim schools, sports clubs, and activity businesses through natural language. 19 tools, works with Claude and ChatGPT.
Pipeworx
Live data for AI — SEC filings, economics, FDA, patents, weather, markets, and more, with citations. One connector, 3,300+ tools across 750+ sources.
EWS Meeting MCP
Safely schedule Outlook meetings on on-prem Exchange EWS with room-aware slot suggestions, local credentials, preview-confirmed writes, and audit-friendly lifecycle records.
Template Vault
Template Vault is an AI-native website builder. Connect it once and your AI can generate a complete one-page website from a business brief in under a minute — real running URL, real Vercel deployment, custom domain on Pro+ tier. Six tools: `discover_business_needs` (interview the user before generating), `list_personalities`, `generate_site`, `get_generation_status`, `list_user_sites`, `publish_site`. Quotas tied to the user's Template Vault plan, so MCP calls don't bypass billing. The discovery-first workflow is the unusual bit — most MCP servers expose CRUD tools; ours expose a guided pipeline that makes the AI a better website-builder than a one-shot prompt would. Auth: OAuth 2.1 with PKCE. Works in claude.ai's "Add custom connector" flow with no manual client registration — paste the URL, click Allow, done.
Decibel Shield — Noise & Decibel Data
Noise data tools for AI agents — free, no auth, no config. Estimated noise levels for 50 world cities (ranked, WHO-anchored), measured noise-exposure rankings for the 100 largest US cities (federal BTS data), decibel levels of common sounds (CDC/NIOSH-sourced), NIOSH safe-exposure-time math, and info on the Decibel Shield iOS sound meter. Typed structured output on every tool. Data CC BY 4.0 — please cite decibelshield.app. Endpoint: https://decibelshield.app/api/mcp (Streamable HTTP). Docs: https://decibelshield.app/mcp/
Kordi
Track, analyze, and act on streaming & SaaS subscriptions from any AI agent. List subscriptions, score billing health, detect price hikes, find savings, and pause or cancel services via natural language.
Mlab - IOC & Threat Intelligence
Threat intelligence MCP server for SOC analysts, DFIR and security researchers. Scan and enrich IOCs directly from Claude, Cursor or any MCP client: IP addresses (IPv4/IPv6), domains, file hashes and blockchain addresses. Search CVEs by keyword, vendor or product, retrieve full CVE records, and explore a threat actor database (APTs, groups, TTPs) with reverse CVE-to-actor lookup. Includes scan history, bookmarks and quota management. Free tier available — no credit card required. Built by mlab.sh, the IOC & file intelligence platform.
FLUX
Official Black Forest Labs MCP server for FLUX image generation and editing — text-to-image, image-to-image, and multi-reference editing via the hosted endpoint at mcp.bfl.ai.
In Parallel
Give teams and AI assistants a shared understanding of goals, projects, decisions, and risks.
Latest MCP Clients
View AllFable5
Claude Fable 5: Anthropic's first public Mythos-class model, explained
Voyei
Voyei is a collaborative travel-planning app (Brazil-first, PT-BR). Its native MCP server lets you connect your own AI client — Claude, ChatGPT, Cursor or any MCP-compatible client — and have it read and edit your trips in real time, using your AI plan (Voyei never charges per token nor trains on your data). The AI can create and edit trips (days auto-generated), add and schedule places, manage reservations (hotels, restaurants, tours, events) and transport (flights, trains, cars, cruises), build budgets with expense-splitting, assemble packing lists, collaborate (shared notes, polls, messages, to-dos), update your travel Atlas and journey log, and search places & weather. Exposes 78 tools and 15 read resources, with granular OAuth scopes (read/write per area).
FAQ
Frequently Asked Questions about MCP Server
What is MCP (Model Context Protocol)?
MCP is an open-source protocol developed by Anthropic that enables AI systems like Claude to securely connect with various data sources. It provides a universal standard for AI assistants to access external data, tools, and prompts through a client-server architecture.
What is MCP Server?
MCP Server is a system that provides context, tools, and prompts to AI clients. It can expose data sources like files, documents, databases, and API integrations, allowing AI assistants to access real-time information in a secure way.
How do MCP Server work?
MCP Server work through a simple client-server architecture. They expose data and tools through a standardized protocol, maintaining secure 1:1 connections with clients inside host applications like Claude Desktop.
What can MCP Server provide?
MCP Server can share resources (files, docs, data), expose tools (API integrations, actions), and provide prompts (templated interactions). They control their own resources and maintain clear system boundaries for security.
How does Claude use MCP?
Claude can connect to MCP server to access external data sources and tools, enhancing its capabilities with real-time information. Currently, this works with local MCP servers, with enterprise remote server support coming soon.
Is MCP Server secure?
Yes, security is built into the MCP protocol. Server controls its own resources, there's no need to share API keys with LLM providers, and the system maintains clear boundaries. Each server manages its own authentication and access control.
What is mcp.so?
mcp.so is a community-driven platform that collects and organizes third-party MCP Servers. It serves as a central directory where users can discover, share, and learn about various MCP Servers available for AI applications.
How can I submit my MCP Server to mcp.so?
You can submit your MCP Server by creating a new issue in our GitHub repository. Click the 'Submit' button in the navigation bar or visit our GitHub issues page directly. Please provide details about your server including its name, description, features, and connection information.