The Model Context Protocol (MCP) is an open standard that connects AI apps to servers. A server offers tools and data; the model decides when to call a tool, and the server does the work, for example reading files or searching a knowledge base. A server runs locally next to the app or is hosted and reached over the network, which then needs authentication. This topic collects MCP servers, how they are built and how they are secured.
- Covered in
-
- Securing a Hosted MCP Server Plan for a hosted MCP server for the knowledge base that claude.ai on the web and on mobile can use, while nobody else can.
- Basis for
-
- How an LLM Wiki Works How an LLM wiki works, shown on this knowledge base: Markdown in its own Git repository, a Python tool with MCP for agents, and a website that only displays it.
- See also
-
- AI Agents AI apps whose language model calls tools to get work done, such as Claude Code and Claude Desktop, and how to run them safely.
- Tags