MCP Servers

The open registry for Model Context Protocol servers. Find the right tools, resources, and prompts for your AI agents — filtered by category, transport, or use case.

Servers

206

Tools

545

Categories

11

Contributors

182

5 servers

Sort by
Redis MCP ServerAnthropic

MCP server for Redis key-value store interaction. Enables AI agents to read and write data in Redis, manage keys, work with data structures (strings, hashes, lists, sets), and perform pub/sub operations. Useful for caching, session management, real-time data, and inter-service communication in distributed systems.

86.2k
SQLite MCP ServerAnthropic

MCP server for SQLite database interaction and business intelligence. Enables AI agents to query SQLite databases, create and modify tables, run analytical queries, and generate insights from data. Supports read-write operations with transaction safety and provides schema introspection for understanding database structure.

86.2k
MongoDB MCP ServerMongoDB

Official MCP server for interacting with MongoDB databases and MongoDB Atlas. Enables AI agents to query collections, run aggregations, manage indexes, inspect schemas, and perform CRUD operations. Also supports Atlas cloud management including cluster provisioning, database user management, performance advisor, and stream processing. Supports read-only mode for safe exploration.

1k
InfluxDB MCP ServerInfluxData

InfluxData's MCP server connects agents to InfluxDB 3 for SQL queries, schema exploration, and time-series database operations.

0
MCP Toolbox for DatabasesGoogle APIs

Google's MCP Toolbox provides secure, ready-made and custom tools for database queries, schema operations, and semantic search in agent workflows.

0

Skills vs MCP servers

what’s the difference?

Skillsthe “what to do”

A skill packages know-how — instructions, an example prompt, and recommended models — so an agent performs a task consistently. Skills add knowledge, not new connections.

MCP serversthe “how to connect”

An MCP server gives an agent new capabilities by connecting it to real systems (databases, APIs, files) over a transport. MCP adds connections and actions, not task instructions.

Rule of thumb: reach for a skill when you need the model to do a task well, and an MCP server when you need it to reach a tool or system. They compose — a skill can rely on tools an MCP server provides.

Built an MCP server?

Submit it to the registry — it’s open source and community-maintained.

Submit on GitHub