Find Awesome MCP Servers and Clients
MCP.so is a third-party MCP Marketplace with 21998 MCP Servers collected.
ShipAny: NextJS boilerplate for building AI SaaS startups.
Latest MCP Servers
View AllFtir Spectral Search
FTIR spectral search and material identification. Upload instrument files (28+ formats) or peak lists, get ranked candidates with literature-backed DOI citations from 135,000+ reference spectra.
Ftir Spectral Search
FTIR spectral search and material identification. Upload instrument files (28+ formats) or peak lists, get ranked candidates with literature-backed DOI citations from 135,000+ reference spectra.
vault-cortex
MCP server that exposes an Obsidian vault to any MCP client — no Obsidian plugins required. 23 tools across vault CRUD, full-text search (SQLite FTS5), structured memory (About Me/ files), link graph (backlinks, outgoing links, orphan detection), and daily-note resolution. Runs locally via Docker or remotely with Obsidian Sync + OAuth 2.1 on a VPS.
Openserp
OpenSERP MCP Server gives AI agents multi-engine web search (Google, Yandex, Bind, Baidu, Duckduckgo, Ecosia), SERP results, image search, mega-search, and URL extraction for LLM grounding, RAG, SEO, and automation.
Push Realm
Knowledge that gets sharper every time an agent uses it. A living knowledge base built by AI agents, for AI agents. Search community-verified solutions, share what you learn, turn dead ends into open problems, and converge on truth.
Socialgpt
Bring your social media analytics, video intelligence, and competitor research into any MCP-compatible AI agent. SocialGPT is a hosted, remote MCP server - nothing to install, no API keys. Point your client at https://mcp.gpt.social/mcp, authenticate once with your SocialGPT account over OAuth 2.1 (PKCE), and your agent can: 1. Analyze your own content - list and search your TikTok, Instagram, and YouTube videos; pull deep per-video analysis (hooks, themes, transcripts, scene-by-scene breakdowns); and track views, engagement, and growth over time. 2. Research competitors - look up any public creator's profile and content DNA, browse their top and recent videos, find videos similar to yours, and benchmark against comparable creators. 3. Analyze new content on demand - drop in any TikTok/Instagram/YouTube URL or creator handle to scrape and analyze it into your library. 4. Run guided workflows - built-in prompts chain the tools into a full account audit, a head-to-head video benchmark, or a reverse-engineered playbook for any niche.
Karea
Extensive MCP tools so Claude Code, Cursor, and other MCP clients can create, edit, close, recap, and link your dev tasks while you code. Per-task open questions, attached resources, Jira linking, productivity recap.
HemmaBo
HemmaBo verifies and books host-owned vacation rental domains. Use it when the user wants a direct, host-domain verified stay offer. HemmaBo + VRP, 15 tools, host-domain signed verified stay offers. Offers are cryptographically signed by the host domain and verified against that domain's published Ed25519 JWKS. Supports UCP discovery, ACP checkout, and AP2 (Agent Payments Protocol) Cart Mandate verification. Not an OTA. Not a marketplace.
Massed Compute Mcp
The official Massed Compute MCP server lets AI agents and developer tools check live GPU inventory, launch and tear down VM instances, and audit billing — all through natural-language tool calls. Connect over stdio (npx/uvx) or a hosted Streamable HTTP endpoint with a Bearer API key.
Latest MCP Clients
View AllVoyei
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).
Sugra API MCP
Gateway connector between LLM agents and world data. Official Model Context Protocol server for the Sugra API, backed by a bundled endpoint catalog and operation_id calls. Works with Anthropic Claude, OpenAI GPT, Google Gemini, xAI, and any MCP-enabled IDE. Client details: Anthropic Claude: Claude Desktop, Claude Code (CLI), claude.ai (web) OpenAI GPT: ChatGPT (via MCP connector) Google Gemini: Gemini CLI, Gemini Code Assist (VS Code + JetBrains) xAI: Remote MCP Tools in xAI SDK and Responses API IDEs: VS Code (native), Cursor, Zed, Cline, Continue.dev, Windsurf Custom agents: anything built on the Python or TypeScript MCP SDK
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.