Model Context Protocol
Reference for the Model Context Protocol (MCP): the standard that connects AI assistants to external tools, resources, and data sources, organized by method category.
What this covers
The Model Context Protocol (MCP) is a standard for connecting AI assistants to external tools, resources, and data sources over a common interface, so an LLM client can discover and call capabilities exposed by any MCP-compliant server. This page is a method reference organized by category. For broader AI development concepts, see AI Development.
When to use it
- Implementing or troubleshooting an MCP server or client
- Deciding which method category a new capability belongs in (a tool call vs. a resource read vs. a prompt)
- Debugging a session/connection issue between an MCP client and server
Session / Connection Methods
initialize, session/open, session/close, session/list
Tools Methods
tools/list, tools/call, tools/register, tools/unregister
Resource Methods
resources/list, resources/read, resources/write, resources/delete
Prompts / Messages
prompts/list, prompts/submit, prompts/feedback
Logging / Monitoring
logging/get, logging/subscribe, logging/clear
Server Info
server/info, capabilities/list