Model Context Protocols (MCPs)

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.

Compare the top MCP servers

MCP serverWhat it connects toTypeRepository
Qlik CloudInteract with Qlik Cloud applications and extract data from visualizations using the Qlik Cloud API.Unknownhttps://github.com/jwaxman19/qlik-mcp
WebRTC MCP Chat ServerA remote WebRTC chat server with secure temporary rooms and MCP support for background agents.Unknownhttps://github.com/brysgo/webrtc-mcp-chat
QuantConnectA server for local interactions with the QuantConnect API.Unknownhttps://github.com/QuantConnect/mcp-server
QdrantImplement semantic memory layer on top of the Qdrant vector search engineOpen Sourcehttps://github.com/qdrant/mcp-server-qdrant
PHP MCP Server for LaravelA Laravel wrapper for the php-mcp/server library to expose Laravel applications as MCP servers.Open Sourcehttps://github.com/php-mcp/laravel
PermShell MCPExecute shell commands with permission notifications.Unknownhttps://github.com/mcollina/perm-shell-mcp
PDF ToolsA server for manipulating PDF files, including merging, page extraction, and searching.Unknownhttps://github.com/hanweg/mcp-pdf-tools
Penpot MCP ServerIntegrates AI language models with the Penpot design platform to automate design workflows.Open Sourcehttps://github.com/montevive/penpot-mcp
Python MSSQL MCP ServerA Python MCP server for Microsoft SQL Server, enabling schema inspection and SQL query execution.Open Sourcehttps://github.com/amornpan/py-mcp-mssql
Python Notebook MCPEnables AI assistants to interact with local Jupyter notebooks (.ipynb).Unknownhttps://github.com/UsamaK98/python-notebook-mcp

What is an MCP server?

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.

Which clients support MCP servers?

Clients supporting MCP include Claude Desktop, Cursor, Windsurf, Continue, and various open-source autonomous agent frameworks that implement the Model Context Protocol client specifications.

Are MCP servers free or paid?

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.

How can developers submit a new MCP server?

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.

How are MCP listings ranked in the directory?

Listings are ranked using objective criteria, including repository maintenance activity, implementation completeness, documentation quality, community usage signals, and protocol compliance.

Are MCP servers safe to run locally?

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.

  • RunwayML + Luma AI — Interact with the RunwayML and Luma AI APIs for video and image generation tasks.
  • S3 Documentation MCP Server — A lightweight Model Context Protocol (MCP) server that brings RAG (Retrieval-Augmented Generation) capabilities to your LLM over Markdown documentation stored on S3.
  • Sailor — Generate and render Mermaid diagrams as images using LLMs.
  • RunPod MCP Server — Interact with the RunPod REST API to manage cloud GPU resources.
  • RubyGems — Fetch metadata for Ruby gems from the rubygems.org API.
  • Runbook — Integrates with Runbook to allow listing, reading, and searching over documents.
  • SACL MCP Server — A framework for bias-aware code retrieval using semantic-augmented reranking and localization.
  • Rust Docs Server — Fetches Rust crate documentation from docs.rs using the rustdoc JSON API.
  • RubyGems Package Info — Fetches comprehensive information about Ruby gems from RubyGems.org, including READMEs, metadata, and search functionality.
  • Runway API — Generate images and videos using the Runway API.
  • Ruby MCP Client — A Ruby client for the Model Context Protocol (MCP), enabling integration with external tools and services via a standardized protocol.
  • SafetyCulture MCP Server — Ask natural language questions about your SafetyCulture data using the SafetyCulture API.
  • salary-Web — An AI-powered payroll management tool for enterprises, integrated with DingTalk.
  • RuneScape — Interact with RuneScape (RS) and Old School RuneScape (OSRS) data, including item prices and player hiscores.
  • SABIS MCP Server — Access academic grades from the Sakarya University SABIS system via automated web scraping.
  • Salesforce Einstein by CData — A read-only MCP server for querying live Salesforce Einstein data using a CData JDBC driver.
  • s&box MCP Server — Enables AI assistants to interact with s&box game objects and components via WebSocket communication.
  • Rug-Check-MCP — Detects potential risks in Solana meme tokens to help avoid rug pulls and unsafe projects.
  • S3 Tools — Provides tools for interacting with AWS S3 buckets.
  • Rust Docs MCP Server — Query up-to-date documentation for Rust crates.
  • Salaah MCP — FastAPI and MCP service providing Islamic prayer times and other useful calculations.
  • Salesforce MCP Server — Enables natural language interaction with Salesforce data. Query, modify, and manage Salesforce objects and records.
  • Salesforce MCP — Interact with the Salesforce API using jsforce, requiring username and password for authentication.
  • Safe Local Python Executor — A tool for safely executing local Python code without requiring external data files.
  • AI Tools
  • Categories
  • Industries
  • CLI Coding Agents
  • MCP Servers
  • MCP Categories