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
Provides AI agents with access to PostHog product analytics through the Model Context Protocol. Enables querying events, analyzing funnels, inspecting feature flags, and reviewing session recordings metadata. Supports HogQL queries for advanced analytics and cohort analysis for user segmentation.
Intuit's official MCP server for QuickBooks Online, exposing QBO accounting features as callable tools. Lets AI assistants read and write customers, invoices, bills, payments, and other entities, and pull financial reports such as profit and loss or balance sheet, so agents can answer bookkeeping questions and automate accounting workflows against live QBO data.
MCP server for Todoist that lets AI agents create, update, complete, and query tasks using natural language. Supports projects, due dates, priorities, labels, and filters, making it easy to manage a personal or team task list conversationally.
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.
A Model Context Protocol server for Strapi headless CMS. Lets AI assistants list content types, query and filter entries, and create or update content through the Strapi REST API, along with media upload support, so agents can manage a Strapi project's content without leaving the conversation.
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.