Glossary

MCP Resources

MCP Resources expose read-only data to AI assistants. They let AI models query databases, read files, fetch configurations, or access any data from your system — without performing mutations or side effects.

Explanation

Resources are the data layer of MCP. While Tools perform actions, Resources provide context. Each resource has a URI pattern, a description, and a return type. AI assistants use resources when they need information to answer questions, summarize data, or make decisions before calling a tool. For example, a project management MCP server might expose resources like 'project://issues/open' for current open issues, or 'project://sprints/current' for the active sprint. Resources can be static (always available) or dynamic (templated URIs that accept parameters). They're especially valuable for AI-powered search, summarization, and analysis workflows where the AI needs to understand your data before taking action.

Related Terms

Ready to build your own MCP server?

Take the 2-minute quiz to find out if MCP is the right fit for your project, then get a step-by-step plan to ship it.