Browse Model Context Protocol (MCP) servers and integrations.
Model Context Protocol (MCP) servers are standardized interfaces that allow large language models and AI agents to securely interact with external systems, tools, and data stores. Instead of relying on bespoke integrations, an MCP server exposes defined tools, resources, and prompts over a unified protocol. This architecture enables AI coding assistants, desktop agents, and autonomous workflows to query databases, manipulate local files, execute terminal commands, and call external APIs with fine-grained control.
This directory catalogs 1186 active MCP servers structured across 20 functional domains. Developers can browse servers organized by target environment and capability, including Databases & Data Stores for querying relational and vector backends, Developer Tools & Code Intelligence for IDE enhancements, and DevOps, CI/CD & Version Control for deployment automation. Additional domains include Cloud & Infrastructure, Security & Compliance, Browser & Web Automation, AI Memory & Context, and Files, Documents & PDFs. Each category groups servers designed to grant models access to specific operational layers without requiring custom middleware.
Selecting the right MCP server depends on your client environment, transport protocol, and execution runtime. First, confirm compatibility with your AI client, such as Claude Desktop, Cursor, Windsurf, or custom agent runtimes built on the MCP SDK. Second, inspect the server transport type; most run locally over standard input/output (stdio), while others operate remotely via Server-Sent Events (SSE) or WebSockets. Finally, evaluate the required permission scopes and authentication mechanisms. Production workflows benefit from servers that enforce read-only modes or explicit confirmation prompts prior to executing destructive actions on your infrastructure.
| MCP server | What it connects to | Type | Repository |
|---|---|---|---|
| MCP-Wait | MCP-Wait is an MCP server that pauses execution within an agentic workflow to allow external tasks or asynchronous processes to | Unknown | https://github.com/automation-ai-labs/mcp-wait |
| YOURLS-MCP | YOURLS-MCP acts as a personal bridge between Claude Desktop and a self-hosted YOURLS installation, allowing the AI to manage web | Open Source | https://github.com/kesslerio/yourls-mcp |
| MCP-MySQL-Ops | MCP-MySQL-Ops is an MCP server that connects AI assistants to MySQL databases to provide database monitoring, performance analysis, and administration | Unknown | https://github.com/call518/MCP-MySQL-Ops |
| MCP Variance Log | MCP Variance Log is an MCP server that detects statistical variations and unusual interaction patterns in conversation structures and stores | Unknown | https://github.com/truaxki/mcp-variance-log |
| Video Gen Mcp Monolithic | Video Gen Mcp Monolithic is an MCP server that connects large language model interfaces to FAL AI services to handle | Unknown | https://github.com/h2a-dev/video-gen-mcp-monolithic |
| MCPSwift | MCPSwift is an MCP server framework that allows developers to create custom Model Context Protocol servers natively in Swift. It | Open Source | |
| MCP Telegram | MCP Telegram is an MCP server that connects Large Language Models to Telegram using the MTProto protocol and the Telethon | Unknown | https://github.com/dryeab/mcp-telegram |
| Zomato MCP | The Zomato MCP server acts as a digital bridge that allows AI assistants to handle food delivery tasks directly. Instead | Unknown | https://github.com/Zomato/mcp-server-manifest |
| Mealie | Mealie MCP Server is an MCP server that connects AI assistants like Claude Desktop directly to a running Mealie recipe | Open Source | https://github.com/rldiao/mealie-mcp-server |
| MCP Undetected Chromedriver | MCP Undetected Chromedriver is an MCP server that provides an interface for automated Google Chrome browser control while bypassing modern | Open Source | https://github.com/dragons96/mcp-undetected-chromedriver |
An MCP server is an application that implements the Model Context Protocol to expose data, tools, and prompts to AI assistants. It standardizes how models read external context and trigger actions in external systems.
Clients supporting MCP include Claude Desktop, Cursor, Windsurf, Continue, and various open-source autonomous agent frameworks that implement the Model Context Protocol client specifications.
The majority of MCP servers are open-source and free to run locally. However, some servers interface with third-party commercial APIs, cloud providers, or proprietary platforms that require paid subscriptions or API keys.
Developers can submit a server by providing its repository link, documentation, supported transport protocols (stdio or SSE), license type, and category classification through the FastPedia submission form.
Listings are ranked using objective criteria, including repository maintenance activity, implementation completeness, documentation quality, community usage signals, and protocol compliance.
MCP servers execute locally with the permissions of the host environment. Users should inspect server source code, verify required file system and network privileges, and configure client-side approval prompts before granting execution rights.