What are MCP servers for?
MCP lets a compatible AI application use data and functions from external systems. This guide takes you from choosing a server to checking your first connection.
MCP stands for Model Context Protocol. It defines how an AI application communicates with a program that provides data or actions. MCP is not an AI model, and connecting a server does not retrain the model.
For example, a document search server could help an assistant find passages relevant to your question. What the assistant can read or change depends on the server, the application and the permissions you grant.
Data access
The agent reads your calendar, documents, database.
Actions
Search, create records, send messages – via tools.
Integration
GitHub, Slack, Notion and many more over one standard.
GitHub MCP
Repos, issues and pull requests for your agent.
PostgreSQL MCP
Database queries with schema inspection.
What is MCP?
An open standard that connects AI to external data, tools and workflows.
What access does a server request?
Always check the requested permissions; grant only what is needed.