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
Official HubSpot MCP server connecting AI tools to the HubSpot CRM. Enables agents to read and manage contacts, companies, deals, and tickets, search the CRM, and create engagements such as notes and tasks. Honors HubSpot scopes and rate limits via OAuth.
A collection of Apple-native tools exposed through the Model Context Protocol, letting AI assistants work with built-in macOS apps. Provides access to Messages, Notes, Contacts, Calendar, Reminders, Mail, and Maps so agents can send messages, create notes and events, and look up contacts directly on a Mac.
Community MCP server that connects a personal WhatsApp account to AI assistants. Using the WhatsApp multi-device web API, it lets agents search and read your messages and contacts and send messages, including media. Messages are stored locally in SQLite and only shared with the model when the agent accesses them through tools, keeping data on your machine.
MCP server for Salesforce that lets AI agents query and modify CRM data using SOQL, manage standard and custom objects (Accounts, Contacts, Opportunities, Cases), describe object metadata, and execute Apex anonymous blocks. Supports both production and sandbox orgs via OAuth or username-password flows.
MCP server for Intercom. Lets AI agents search and read conversations and contacts, retrieve message history, and query help-center articles via the Intercom API. Useful for support analytics, conversation summarization, and building assistants that reason over customer communications.
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.