SOSolon
Community
Build Java enterprise applications with a restrained, efficient, open, and ecological framework.
Directory
MCP Server Directory
Browse 6,627+ Model Context Protocol servers for Claude, Cursor, and VS Code. Find the perfect tools for your AI workflow.
MCP Servers listings
SO
Sourcebot
CommunityIndex and search code across multiple repositories and branches from various code hosting platforms.
SU
Supergateway
CommunityExposes MCP stdio-based servers over SSE or WebSockets, enabling remote access and integration.
SU
Superglue
CommunityAutomates data integration via a stable, self-healing SDK, providing automated schema-drift detection, retries, and remappings to maintain continuous data flow without connector m…
UL
UltraRAG
CommunityAccelerate the development and research of complex Retrieval-Augmented Generation (RAG) systems with a low-code, modular framework.
UN
Unla
CommunityTransforms existing API servers and services into Model Context Protocol (MCP) compliant endpoints with zero code changes.
VE
VectorChord
CommunityProvides scalable, fast, and disk-friendly vector search capabilities directly within PostgreSQL.
WI
Windows
CommunityEnables seamless integration between AI agents and the Windows operating system.
XC
XcodeBuild
CommunityEnables AI agents to interact with and automate Xcode projects through the Model Context Protocol.
AC
Agent Communication Protocol
CommunityEstablishes an open, standardized protocol for framework-agnostic agent communication.
AR
Agentic Radar
CommunityAnalyzes agentic systems to identify potential vulnerabilities and security insights.
AG
AI Gateway
CommunityExperiments with Azure API Management's AI capabilities, integrating with Azure OpenAI, AI Foundry, and more.
AT
Atproto
CommunityProvides a Python SDK for interacting with the AT Protocol (Bluesky).
AW
AWorld
CommunityFacilitates the building, evaluation, and running of general multi-agent assistance systems.
AD
Azure DevOps
AzureIntegrates Azure DevOps capabilities directly into development environments by providing a local server that enables interaction with various services.
BI
Bifrost
CommunityProvides a high-performance, resilient AI gateway for connecting to multiple large language model providers through a single, unified API.
CH
Chatsum
CommunitySummarizes chat messages based on user queries.
CC
Claude ChatGPT
CommunityEnables Claude to interact with the ChatGPT desktop application on macOS.
CC
Claude Code
CommunityEnables Claude Code as a one-shot MCP server, allowing LLMs to directly leverage Claude's coding capabilities.
CP
Context Portal
CommunityBuilds a project-specific knowledge graph to supercharge AI assistants with context-aware Retrieval Augmented Generation (RAG) capabilities.
CS
Context Space
CommunityProvides a comprehensive context engineering infrastructure with unified Model Context Protocol (MCP) tools and secure integrations for AI agents.
Directory
CommunityProvides a curated directory for discovering Awesome MCP Servers.
DO
Docs
CommunityIndexes and searches third-party library documentation using semantic splitting and vector embeddings.
EL
ElevenLabs
CommunityEnables interaction with Text to Speech and audio processing APIs for MCP clients.
What Are MCP Servers?
MCP (Model Context Protocol) servers are tools that connect AI assistants like Claude, Cursor, and other AI coding tools to external data sources, APIs, and services. They enable AI models to access real-time information, execute code, interact with databases, and perform actions beyond their base capabilities. Check out our curated collection of the best MCP servers for Cursor →
How MCP Servers Work
MCP servers act as intermediaries between AI assistants and external systems. When you ask Claude or Cursor to perform a task requiring external data, the MCP server handles the request, fetches the data, and returns it in a format the AI can understand and use.
Types of MCP Servers
- Code Completion Servers: Enhance AI coding assistants with context from your codebase, documentation, and project structure.
- API Integration Servers: Connect AI to REST APIs, GraphQL endpoints, and web services for real-time data access.
- File Management Servers: Enable AI to read, write, and organize files in your development environment.
- Data Analysis Servers: Connect AI to databases, data warehouses, and analytics tools.
Choosing the Right MCP Server
When selecting an MCP server, consider:
- IDE Compatibility: Ensure it works with Cursor, VS Code, or your preferred editor
- Use Case Match: Choose servers designed for your specific needs
- Maintenance Status: Prefer actively maintained servers with recent updates
- GitHub Activity: Higher stars and recent commits indicate quality
Popular Use Cases
- AI-Powered Code Completion Enhance Cursor and Claude with project-specific context.
- Automated API Testing Connect AI to your APIs for intelligent testing and debugging.
- Database Querying Let AI write and execute SQL queries against your databases.
For detailed setup guides, see our Complete MCP Server Setup Guide →
Frequently Asked Questions About MCP Servers
Everything you need to know about installing, using, and troubleshooting Model Context Protocol.
How do I install MCP servers in Cursor?
To install MCP servers in Cursor: 1) Open Cursor settings (Cmd+,), 2) Navigate to MCP Servers section, 3) Click 'Add Server', 4) Enter server configuration (name and command), 5) Restart Cursor. Check out our curated collection of the best MCP servers for Cursor with detailed setup guides.
What's the difference between MCP servers and VS Code extensions?
MCP servers are protocol-level integrations that work across multiple AI assistants (Claude, Cursor, etc.), while VS Code extensions are editor-specific. MCP servers provide context to AI models, whereas extensions add IDE functionality. MCP is more portable and AI-focused.
Are these MCP servers free to use?
Most MCP servers listed are open-source and free. Some enterprise connectors (like Salesforce or Jira) may require paid API access to the underlying service, but the MCP server code itself is usually free.
Can I build my own MCP server?
Yes! The Model Context Protocol is open standard. You can build servers in Python or TypeScript/Node.js to expose your own internal APIs or databases to Claude and Cursor.
What is a Model Context Protocol (MCP) server?
An MCP server is a lightweight program that exposes specific capabilities (data access, tool execution, prompts) to AI assistants through a standardized protocol. MCP servers allow Claude and other AI models to securely interact with external systems like databases, APIs, file systems, and web services while maintaining security boundaries.
How do MCP servers work with Claude?
MCP servers connect to Claude Desktop or other MCP-compatible clients through a standardized JSON-RPC protocol. When you configure an MCP server in Claude Desktop, Claude can access its resources (data/content), use its tools (functions to execute), and leverage its prompts (templated interactions). The protocol ensures secure, controlled access to external capabilities.
What are the best MCP servers to start with?
Essential MCP servers for beginners include: Filesystem (local file access), SQLite/PostgreSQL (database queries), GitHub (repository access), Brave Search (web search), and Memory (persistent context). These cover common use cases and have excellent documentation. Start with 2-3 servers and expand based on your needs.
How do I install and configure MCP servers?
Most MCP servers install via npm (npx) or Python (uvx/pip). Configure them in Claude Desktop's config file (claude_desktop_config.json) by specifying the command, arguments, and any required environment variables like API keys. Our directory links to each server's documentation with specific installation instructions.
Are MCP servers secure?
MCP servers run locally on your machine with explicit permissions you configure. They can only access resources you authorize, and Claude cannot bypass these boundaries. However, always review server code, use official/verified servers when possible, limit permissions to what's necessary, and be cautious with servers that request broad access.
What's the difference between MCP resources, tools, and prompts?
Resources are data sources Claude can read (files, database results, API responses). Tools are functions Claude can execute (run queries, send messages, create files). Prompts are pre-defined templates for common interactions. Most MCP servers expose one or more of these capability types.
Which AI clients support MCP besides Claude Desktop?
MCP is supported by Claude Desktop (official), Cursor IDE, Continue (VS Code extension), and various community implementations. The protocol is open, so support is expanding to more AI development tools. Check our compatibility filters to find servers tested with your preferred client.
How often is this MCP servers directory updated?
Our MCP servers directory is updated weekly with new servers, documentation improvements, and compatibility updates. We monitor GitHub releases, community contributions, and Anthropic announcements to ensure our listings reflect the latest MCP ecosystem developments.
- Guide · 12 min
Top 20 MCP Servers for Cursor Users (2025)
- Guide · 8 min
MCP Server Curation Guide 2025
- Security · 7 min
MCP Server Security Best Practices 2025